Deep learning-based fusion of hyperspectral images (HSI) and LiDAR has achieved strong performance in multimodal remote sensing classification, but its success is heavily constrained by the high cost of pixel-wise annotation. In extremely label-scarce regimes, such as 2-5 labeled samples per class, conventional deep models are prone to severe overfitting, while standard semi-supervised learning (SSL) methods often suffer from confirmation bias because pseudo-labels are generated from unstable early-stage representations. To address these challenges, we propose Prototype-Guided Progressive Learning (PGPL), a unified framework for few-shot HSI-LiDAR classification. Instead of relying solely on model confidence in latent space, PGPL first constructs a reliable initialization pool directly in the original data domain using spectral-angle and elevation-consistency cues, and then progressively expands the training set through class-balanced pseudo-label admission and temporal confidence stabilization. In this way, the framework improves pseudo-label reliability during both initialization and subsequent self-training. Extensive experiments on three benchmark datasets demonstrate that PGPL consistently outperforms state-of-the-art supervised and semi-supervised baselines under the corresponding 2-5-shot settings, achieving overall accuracy gains of 4.64% points on Houston, 1.16% on Trento, and 3.92% on MUUFL over the strongest competing methods, while also yielding higher pseudo-label purity. The source code will be publicly available at https://github.com/zhangyiyan001/PGPL.

Tiny object detection (TOD) in remote sensing imagery remains challenging because foreground signals are extremely weak in deep feature hierarchies and are easily overwhelmed by high-response background interference. To mitigate this observed foreground-background signal modulation imbalance (FBSMI) difficulty, we propose a signal modulation network (SMN) for remote-sensing TOD. SMN comprises two complementary components. First, an adaptive Wiener filter modulator (AWFM) is inserted after backbone stages to suppress background-dominated noise while preserving weak target-related responses at multiple resolutions. Second, we introduce the novel denoising diffusion transformer (DDT), a feature-space conditional diffusion module that operates on detector feature tensors rather than image pixels. DDT generates multiple diffusion-guided semantic feature variants from high-level fused features and expands the local representation space around weak tiny object evidence. Extensive experiments on AI-TOD, SODA-A, DOTAv2.0, and DIOR-R demonstrate that SMN not only effectively mitigates the FBSMI problem, but also improves detection accuracy, particularly for very tiny and tiny objects, compared with state-of-the-art methods.

Efficient tiny object detection (TOD) in large-size remote sensing imagery (LSRSI) is particularly challenging in real-world remote sensing applications. We observe that as the input size of the remote sensing scene increases, TOD faces more severe foreground signal identification issues. To address this, we are the first to design a backbone network from the perspective of low-level spatial feature preservation and utilization, specifically for tiny object feature extraction in large-size remote sensing scene patches. The proposed architecture, referred to as the resolution preserving and utilization network (RPUN), demonstrates excellent foreground tiny object feature response identification ability when increasing the input size of remote sensing scenes, effectively maintaining detection performance comparable to that of smaller input slices. Additionally, we introduce GF2UBSv2, a large-scale panchromatic satellite imagery dataset focused on tiny urban bridge detection. Extensive experiments conducted on GF2UBSv2, DIOR, SODA-A, and DOTAv2.0 demonstrate the superior performance of RPUN compared with state-of-the-art methods. The code and dataset are available at: https://github.com//Nankle.

Structural color, which arises from the interaction of light with micro- and nanostructured materials, has been recognized as an environmentally sustainable alternative to traditional dyes and pigments. In this study, Direct Ink Writing has been utilized as the additive manufacturing technique for fabricating structurally colored materials which here, are bottlebrush block copolymers. The experimental workflow has been integrated with an artificial intelligence-driven optimization process, enabling an efficient exploration of the printing parameter space. Image analysis techniques have been employed to characterize the resultant color profiles, with hue in the HSV color space serving as the primary objective function for optimization. The development of software architecture that facilitates real-time data collection and feedback has been undertaken in collaboration with the National Center for Supercomputing Applications (NCSA). Preliminary results have demonstrated the feasibility of the proposed approach in tuning structural coloration, while ongoing efforts aim to enhance automation capabilities and expand the scope of parameter optimization.

The fusion of hyperspectral images (HSIs) and multispectral images (MSIs) is crucial for overcoming the limitations of low spatial resolution in HSI. Currently, supervised learning methods tend to yield satisfactory integration results when applied to data distributions similar to those of the training set; however, they often exhibit insufficient generalization when confronted with real-world application scenarios. In contrast, unsupervised methods exhibit good generalization capabilities; however, they typically require careful tuning of hyperparameters to achieve satisfactory results, primarily due to the lack of sufficiently clear training objectives. To fully leverage the advantages of both supervised and unsupervised learning, this letter proposes an unsupervised pretraining framework (UPFW) guided fusion approach, which effectively enhances the performance of HSI-MSI fusion by introducing low-resolution supervised pretraining and full-resolution unsupervised adaptive strategy. Specifically, in the first stage, the model adapts to the learning spatial and spectral degradation parameter; in the second stage, we propose an adaptive fusion network (ADFNet) and conduct supervised learning on low-resolution scale to obtain a pretrained fusion network model with a clear objective-oriented; in the third stage, we utilize the pretrained model for full-resolution unsupervised fusion, thereby enhancing the model’s generalization capabilities and applicability. Experimental results show that compared to traditional methods and other deep learning approaches, the proposed method achieves significant advantages in spectral fidelity and spatial detail recovery across multiple public datasets.

Deep learning-based frameworks have shown great potential in the field of hyperspectral image (HSI) classification owing to their superior modeling capabilities. However, the existence of mixed pixels and spectral heterogeneity limits the discriminant performance of the classifier, which makes it impossible to distinguish the mixed spectra effectively in actual scenarios. To address this gap, we propose a subpixel spectral variability network ($\text {S}^{2}\text {VNet}$) for HSI classification, which incorporates complete subpixel information and class features modeled by spectral variability and nonlinear mixture characteristics to enhance classification performance.$\text {S}^{2}\text {VNet}$is capable of extracting endmembers and abundances based on the nonlinear autoencoder (AE) framework and estimating variability parameters by simultaneously considering scaling factors and perturbation terms to ensure accurate endmember construction. The enhanced subpixel fusion module is further designed to automatically integrate three aspects of abundances, spectral cosine correlation information, and pixel-level class features to provide a robust joint representation for the classifier. Extensive experiments on four public HSI datasets demonstrate the superiority and generalization of the proposed method when benchmarked with state-of-the-art methods. The code will be available athttps://github.com/hanzhu97702/S2VNet.

Remote sensing visual grounding (RSVG) aims to accurately localize specific targets in remote sensing (RS) images based on natural language descriptions. However, existing RSVG datasets often contain overly simplistic textual descriptions, exhibit imbalanced object size distributions, and lack semantic connections between targets and the surrounding contexts. Moreover, current approaches rely on global visual features for region-level localization, while the interaction between visual and textual modalities remains limited. To address these challenges, we propose improvements from both the dataset and algorithm perspectives. First, we explore the semantic correlation between remote sensing objects and their scene context. Based on high-resolution Gaofen satellite imagery, we expand several typical object categories and construct richer textual descriptions that reflect object-background associations. By refining and extending the existing DIOR-RSVG dataset, we build a new dataset named DGF-RSVG. Second, to enhance the semantic alignment between global visual features and textual features, we propose a novel global vision-language multimodal feature interaction enhancement module (GME). In parallel, we design a local attention enhancement module (LAE) to facilitate fine-grained interaction between object-related textual features and regional visual proposals. These two modules form the foundation of our newly developed detection framework: the global-local attention enhanced detector (GLAED). Extensive experiments show that GLAED achieves state-of-the-art performance on the DGF-RSVG dataset, outperforming the closest competitor by 4.3% in [email protected]. It also achieves highly competitive results on the DIOR-RSVG dataset, demonstrating the effectiveness of both our proposed dataset and model framework.

Robust and accurate image matching and registration are foundational tasks for numerous applications. However, current methods often fail when dealing with multimodal remote sensing images (MRSI) that exhibit significant spatial geometric differences (SGD) and nonlinear radiometric differences (NRD). To address these challenges, this paper proposes a novel MRSI matching method: matching using side window Gaussian space (MSG). MSG leverages an intuitive concept that human visual perception relies heavily on salient features at image edges for precise matching. Specifically, the proposed method: (1) constructs a multi-scale side window Gaussian filter scale space (MSGSS) that preserves edge information at different scales while blurring the image; (2) enhances the repeatability of keypoints by performing corner detection on edge maps; (3) increases descriptor robustness by using second-order gradients combined with steerable filtering; (4) further utilizes a two-stage matching strategy within a constrained search space and designs a new distance, making full use of densely distributed edge keypoints. Quantitative and qualitative experiments conducted on 5 datasets spanning 957 image pairs across 9 multimodal types demonstrate that MSG outperforms nine advanced algorithms (six feature-based methods: SIFT, OS-SIFT, RIFT, CoFSM, HOWP, POS-GIFT; and three deep learning-based methods: SuperPoint+SuperGlue, LoFTR, ReDFeat). The results indicate that MSG achieved a number of correct matches (NCM) much higher than the compared algorithms, with the highest success rate (SR), lowest RMSE and good time efficiency, while achieving both scale and rotation invariance. Codes are available at https://github.com/ZCYla/MSG.

Accurately distinguishing between background and anomalous objects within hyperspectral images poses a significant challenge. The primary obstacle lies in the inadequate modeling of prior knowledge, leading to a performance bottleneck in hyperspectral anomaly detection (HAD). In response to this challenge, we put forth a groundbreaking coupling paradigm that combines model-driven low-rank representation (LRR) methods with data-driven deep learning techniques by learning disentangled priors (LDP). LDP seeks to capture complete priors for effectively modeling the background, thereby extracting anomalies from hyperspectral images more accurately. LDP follows a model-driven deep unfolding architecture, where the prior knowledge is separated into the explicit low-rank prior formulated by expert knowledge and implicit learnable priors by means of deep networks. The internal relationships between explicit and implicit priors within LDP are elegantly modeled through a skip residual connection. Furthermore, we provide a mathematical proof of the convergence of our proposed model. Our experiments, conducted on multiple widely recognized datasets, demonstrate that LDP surpasses most of the current advanced HAD techniques, exceling in both detection performance and generalization capability.

Anomaly detection is one of the most popular research topics in hyperspectral remote sensing. A variety of traditional model-driven methods fail to reveal features of data with diversity due to monotonous, fixed analytical modes. This paper analyzes mathematical-statistical properties of hyperspectral images (HSIs) and proposes an interesting approach of information entropy estimation based on point-set topology (IEEPST) to resolve anomaly detection from a brand new perspective, thus eliminating the limitations caused by the data-model discrepancy. Specifically, the original HSI data are mapped into topological spaces to enable ordered arrangements, in preparation for revealing data features. Particularly, information entropy estimation is introduced for the first time in the adoption of point-set topology to adequately unravel the data arrangements in topological spaces, whereby the land cover information is efficiently extracted for detection. Experimental results demonstrate that IEEPST accommodates both detection accuracy and computational efficiency, and is highly competitive with other sophisticated and state-of-the-art methods.

BACKGROUND: Long non-coding RNAs (lncRNAs) can prevent, diagnose, and treat a variety of complex human diseases, and it is crucial to establish a method to efficiently predict lncRNA-disease associations. RESULTS: In this paper, we propose a prediction method for the lncRNA-disease association relationship, named LDAGM, which is based on the Graph Convolutional Autoencoder and Multilayer Perceptron model. The method first extracts the functional similarity and Gaussian interaction profile kernel similarity of lncRNAs and miRNAs, as well as the semantic similarity and Gaussian interaction profile kernel similarity of diseases. It then constructs six homogeneous networks and deeply fuses them using a deep topology feature extraction method. The fused networks facilitate feature complementation and deep mining of the original association relationships, capturing the deep connections between nodes. Next, by combining the obtained deep topological features with the similarity network of lncRNA, disease, and miRNA interactions, we construct a multi-view heterogeneous network model. The Graph Convolutional Autoencoder is employed for nonlinear feature extraction. Finally, the extracted nonlinear features are combined with the deep topological features of the multi-view heterogeneous network to obtain the final feature representation of the lncRNA-disease pair. Prediction of the lncRNA-disease association relationship is performed using the Multilayer Perceptron model. To enhance the performance and stability of the Multilayer Perceptron model, we introduce a hidden layer called the aggregation layer in the Multilayer Perceptron model. Through a gate mechanism, it controls the flow of information between each hidden layer in the Multilayer Perceptron model, aiming to achieve optimal feature extraction from each hidden layer. CONCLUSIONS: Parameter analysis, ablation studies, and comparison experiments verified the effectiveness of this method, and case studies verified the accuracy of this method in predicting lncRNA-disease association relationships.

Vision transformer (ViT) is a prevalent technique for capturing long-distance dependencies and has shown impressive performance in the field of hyperspectral image (HSI) classification. However, the core component of ViT, namely, self-attention, faces challenges in balancing high-computational complexity and global modeling within entire input sequences. To alleviate this issue, a novel Gaussian retentive network, called GRetNet, is devised in this letter to enhance the comprehension of fine-grained spatial and spectral features while reducing computational costs. This method provides a powerful classification backbone and can adaptively generate priors to perceive more effective spatial information by introducing a spatial decay mask to assign different weights at various positions. Furthermore, the Gaussian multi-head attention (GMA) is designed to provide dynamic recalibration of feature significance based on statistical distribution and focuses on distinct spectral patterns across different heads, thereby rendering a more concise and robust modeling for HSI classification. Compared with the state-of-the-art classification algorithms, the proposed GRetNet method can yield better classification results and computational efficiency on four benchmark hyperspectral datasets, which verifies its effectiveness and superiority.

Deep learning (DL)-based unsupervised band selection (UBS) methods have received more attention, but the majority of current approaches face challenges associated with striking a balance between computational burden and the UBS performance, and the spatial-spectral information has not been fully investigated. With the aim of addressing these issues, we have proposed a novel method called spatial-spectrum fully-attention network (SSFAN), which includes a spatial-spectral samples generator (SSSG) and a nearest neighbor scoring (NNS) module. Aiming to improve the UBS performance without a huge computational burden, the SSSG can directly generate numerous nonoverlapped samples for the input of DL model, where the global spatial-spectral information is utilized in a more efficient way. For the purpose of further improving the robustness of SSFAN, the NNS can assign different weights to each band by jointly exploiting the prior knowledge in both spatial and spectral domains. Note that the NNS considered the time consumption when investigating the spatial-spectral prior information, so this does not conflict with the problem of UBS balance. We have conducted experiments on three commonly used remote sensing hyperspectral image datasets, where our proposed methods have shown a more effective and robust performance than current state-of-the-art approaches. The source code will be made publicly available at https://github.com/duang33/SSFAN.

The detection of objects with larger aspect ratios (OLAR) is a challenging problem in a special application scenario, such as remote sensing object recognition and scene text detection. However, current object detectors perform poorly in OLAR feature extraction because they are incapable of adaptively responding to object shapes, which leads to severe misalignment between impure feature representations and region proposals. In this letter, we aim at solving this problem by proposing our shape-sensitive convolution network (SSC-Net). SSC-Net is carefully embedded with a feature enhancement module (SSC module) specifically suitable for OLAR. This module can use fewer sampling points to achieve more intelligent feature sampling area transformation, thus achieving the goal of enhancing OLAR feature representation. Extensive experiments on benchmark datasets that are rich in OLARs have proved the superiority of our method. Besides, we further verified the plug-and-play performance of the SSC module, and the experimental results show that it can significantly improve the detection performance of the detector for OLAR.

The foundation model has recently garnered significant attention due to its potential to revolutionize the field of visual representation learning in a self-supervised manner. While most foundation models are tailored to effectively process RGB images for various visual tasks, there is a noticeable gap in research focused on spectral data, which offers valuable information for scene understanding, especially in remote sensing (RS) applications. To fill this gap, we created for the first time a universal RS foundation model, named SpectralGPT, which is purpose-built to handle spectral RS images using a novel 3D generative pretrained transformer (GPT). Compared to existing foundation models, SpectralGPT 1) accommodates input images with varying sizes, resolutions, time series, and regions in a progressive training fashion, enabling full utilization of extensive RS Big Data; 2) leverages 3D token generation for spatial-spectral coupling; 3) captures spectrally sequential patterns via multi-target reconstruction; and 4) trains on one million spectral RS images, yielding models with over 600 million parameters. Our evaluation highlights significant performance improvements with pretrained SpectralGPT models, signifying substantial potential in advancing spectral RS Big Data applications within the field of geoscience across four downstream tasks: single/multi-label scene classification, semantic segmentation, and change detection.

With the aid of transformers, significant progress has been achieved in hyperspectral image change detection (HSI-CD) in recent times. Nonetheless, most contemporary detection methods fail to incorporate diverse diagnostic features extracted from hyperspectral (HS) images. In addition, relying solely on algebraic-based techniques to extract information of difference is insufficient for achieving satisfactory detection performance. In this regard, we propose an innovative triple-path local-to-global network (TL2GN), complemented by a hybrid head transformer (HybridHT), called TL2GH2T, tailored for HSI-CD tasks. To be specific, TL2GH2T first investigates spatial, spectral, and spatial–spectral features from a local-to-global perspective. Then, a novel spatial and spectral token fusion (SSTF) module is developed to integrate the above three tokenized features, producing discriminative features from two HS images separately. Moreover, drawing inspiration from chromosomal crossover mechanisms, we propose a HybridHT. Its goal is to simultaneously learn cross correlation and self-correlation information of bitemporal features from a global perspective, producing highly discriminative distinctions. Our approach, validated through extensive experimentation on four varied HS benchmarks, exhibits exceptional performance in HSI-CD, outperforming contemporary methods in both visual and quantitative evaluations.

The timely and accurate prediction of winter wheat yields is of importance in maintaining food security. However, existing deep-learning methods used for crop yield prediction are limited. While most methods utilize recurrent neural networks (RNNs) to interpret crop time series data, they struggle to learn geographical spatial information from input data and often prove challenging to interpret with prior knowledge. In this study, hyperspectral images were used as the input to a BS-Nets network for band selection, and a graph-based RNN framework GT-long-short-term memory (LSTM) [two channels based LSTM-graph neural network (GNN)], was proposed for predicting the winter wheat yield at the county level. Using the BS-Nets for hyperspectral bands selection at the field scale, we obtained the top 4 bands in selection results for all six stages, the results were band 46 (791 nm), 50 (825 nm), 66 (954 nm), and 161 (2484 nm). Based on the results of hyperspectral bands selection, at the county scale, the similar wavelength bands of Sentinel-2 red-edge 3 (783 nm), NIR (834 nm), red-edge 4 (865 nm), SWIR2 (2190 nm) were chosen as inputs for the GT-LSTM county-level estimates of winter wheat yield. When only remote sensing data were used, the highest prediction accuracy ($R^{2}= 0.688$, RMSE = 0.54 t/ha) was obtained for DOY135 (30 days before harvest). The incorporation of the meteorological data improved the accuracy by 7% ($R^{2}= 0.714$, RMSE = 0.50 t/ha), and the optimal time for predicting wheat yield was at DOY115 (50 days before harvest). Further addition of GNN layers to the model improved the accuracy of the results by an additional 14% ($R^{2}= 0.757$, RMSE = 0.43 t/ha), and the best prediction results were then obtained at DOY105 (60 days before harvest).

The fusion of multimodal data plays a crucial role in classification tasks. However, existing research typically mines and analyzes the individual features of each data source separately before considering how to fuse them. In contrast, our approach first constructs interactive enhanced fusion features (IEFFs) for initial fusion while considering the extraction of individual features and, finally, integrates them effectively to utilize the information from each data source more comprehensively. To this end, we propose a novel interactive enhanced network based on multihead self-attention (MSA) and graph convolution. Specifically, we extract individual features from hyperspectral image (HSI) and light detection and ranging (LiDAR) data and then construct IEFFs based on the row and column features of the central pixel. Individual features focus on the local characteristics of a single data source, while IEFFs strengthen the feature expression of the central pixel through matrix operations, integrating the complementary information of multimodal data. Subsequently, we use graph convolutional networks (GCNs) to construct graph structures for four types of features (interactive enhanced HSI features, interactive enhanced LiDAR features, HSI individual features, and LiDAR individual features), modeling the pixels as nodes and capturing spatial relationships. On this basis, we apply an MSA mechanism to mine spectral dependencies, further extracting global spectral features. Finally, we design a multimodal gated fusion module (MGFM) that effectively integrates these features through its weighting mechanism. The weight allocation is adjusted dynamically according to the characteristics of the feature, achieving optimal fusion of multimodal data. Extensive experiments on three popular HSI and LiDAR datasets verify the superior performance of our method. Our code will be available athttps://github.com/haofeng0003/MSA-GCN.

Convolution neural networks (CNNs) are extensively utilized in hyperspectral image (HSI) classification due to their remarkable capability to extract features from patterns with fixed shapes. These networks have been shown to effectively capture features at the pixel level. However, the fixed shape of convolution kernels poses a challenge for CNNs to adapt to the diverse shapes found in HSIs. Graph neural networks (GNNs), particularly graph convolution networks (GCNs), possess robust feature extraction capabilities on graph structures and are extensively applied in HSI classification. However, one significant challenge in using GNNs is the selection of appropriate neighboring nodes for information aggregation. To address the existing challenges of GCN and CNN and leverage their respective advantages, this paper introduces a novel patch-based CNN-GCN fusion classification network, named multi-scale random-shape convolution and adaptive graph convolution fusion network (MRCAGCFN). It consists of a spectral transformation module and three main modules we proposed: a multi-scale random-shape convolution module for extracting convolution features, where the shape of the convolution kernel is randomized and a multi-scale approach is applied to enhance adaptability to data with diverse shapes; an adaptive feature-fusion graph convolution module for extracting graph convolution features, where the weights for neighborhood aggregation are learned adaptively to reduce feature fusion from dissimilar nodes and strengthen feature fusion from similar nodes; and an adaptive local feature processing module for processing features, where two different methods are employed to convert patch-level features to pixel-level features, thereby improving feature representation. MRCAGCFN combines the strengths of CNN and GCN while introducing enhancements to better accommodate diverse feature shapes. Experimental results on three HSI classification datasets demonstrate that our proposed MRCAGCFN outperforms some existing methods. The codes of our MRCAGCFN will be available at https://github.com/shengrunhua/MRCAGCFN.

Deep learning (DL) has been widely applied to hyperspectral image (HSI) classification, owing to its promising feature learning and representation capabilities. However, limited by the spatial resolution of sensors, existing DL-based classification approaches mainly focus on pixel-level spectral and spatial information extraction through complex network architecture design while ignoring the existence of mixed pixels in actual scenarios. To tackle this difficulty, we propose a novel dual-branch subpixel-guided network for HSI classification, called DSNet, which automatically integrates subpixel information and convolutional class features by introducing a deep autoencoder unmixing architecture to enhance classification performance. DSNet is capable of fully considering physically nonlinear properties within subpixels and adaptively generating diagnostic abundances in an unsupervised manner to achieve more reliable decision boundaries for class label distributions. The subpixel fusion module is designed to ensure high-quality information fusion across pixel and subpixel features, further promoting stable joint classification. Experimental results on three benchmark datasets demonstrate the effectiveness and superiority of DSNet compared with state-of-the-art DL-based HSI classification approaches. The codes will be available athttps://github.com/hanzhu97702/DSNet, contributing to the remote sensing community.

Cross-scene image classification aims to transfer prior knowledge of ground materials to annotate regions with different distributions and reduce hand-crafted cost in the field of remote sensing. However, existing approaches focus on single-source domain generalization to unseen target domains, and are easily confused by large real-world domain shifts due to the limited training information and insufficient diversity modeling capacity. To address this gap, we propose a novel multi-source collaborative domain generalization framework (MS-CDG) based on homogeneity and heterogeneity characteristics of multi-source remote sensing data, which considers data-aware adversarial augmentation and model-aware multi-level diversification simultaneously to enhance cross-scene generalization performance. The data-aware adversarial augmentation adopts an adversary neural network with semantic guide to generate MS samples by adaptively learning realistic channel and distribution changes across domains. In views of cross-domain and intra-domain modeling, the model-aware diversification transforms the shared spatial-channel features of MS data into the class-wise prototype and kernel mixture module, to address domain discrepancies and cluster different classes effectively. Finally, the joint classification of original and augmented MS samples is employed by introducing a distribution consistency alignment to increase model diversity and ensure better domain-invariant representation learning. Extensive experiments on three public MS remote sensing datasets demonstrate the superior performance of the proposed method when benchmarked with the state-of-the-art methods.

Current hyperspectral anomaly detection (HAD) benchmark datasets suffer from low resolution, simple background, and small size of the anomalies. These factors also limit the performance of the well-known low-rank representation (LRR) models in terms of robustness on the separation of background and target features and the reliance on manual parameter selection. To this end, we build a new HAD benchmark dataset for improving the robustness in complex scenarios, AIR-HAD for short, and propose an interpretable network with deep unfolding a binary subspace learning, named LRR-Net+, which is capable of spectrally decoupling the background structure and object properties in a more generalized fashion and eliminating the bias introduced by vital interference targets simultaneously. In addition, LRR-Net+ integrates the solution process of the alternating direction method of multipliers (ADMM) optimizer with the deep network, guiding its search process and imparting a level of interpretability to parameter optimization. Additionally, the integration of physical models with DL techniques eliminates the need for manual parameter tuning. The manually tuned parameters are seamlessly transformed into trainable parameters for deep neural networks, facilitating a more efficient and automated optimization process. Extensive experiments conducted on the AIR-HAD dataset show the superiority of our LRR-Net+ in terms of detection performance and generalization ability, compared to top-performing competitors. Furthermore, our AIR-HAD benchmark datasets will be made available freely and openly athttps://github.com/danfenghong/IEEE_TGRS_LRR-Net.

With hyperspectral remote sensors (imaging spectrometers) imaging a scene, the specificity of the target of interest is manifested in the significant differences between it and the surrounding background in terms of quantity, spatial distribution, and spectral characteristics, which provides conditions for the implementation of pixel-level diagnostics for target detection. Traditional model-driven methods utilize specific model assumptions to parse hyperspectral image (HSI) data in scenes with variability and are prone to encounter limitations due to model-data discrepancy. Most data-driven methods are limited in practical applications due to the great demand for training samples, the large number of parameters to be determined, and the costly computational complexity. To address the limitations of the existing methods, this article adopts point-set topology theories to analyze the properties of hyperspectral data at the mathematical-statistical level and seek a solution for the information retrieval task of target detection, whereby a target detection method through information entropy estimation based on point-set topology is proposed. First, parallel topological spaces are constructed to order the original HSI data to ensure that the differences in data features between various classes of land covers are reflected in intuitive properties in the topological spaces. Second, in conjunction with the priori information about the target, information entropy estimation is introduced to select optimal separable spaces for the target and the background by measuring the degree of ordering of data to achieve an accurate separation. Finally, a proper way to quantify and highlight the differences in data features between various land covers in the optimal separable spaces is explored for the algorithmic output to perform the information retrieval task. The proposed target detection through information entropy estimation based on point-set topology (TD-IEEPST) exploits an innovative combination of point set topology theories and information entropy estimation to achieve efficient extraction of land cover information for detection, ensuring both theoretical interpretability and computational efficiency. Extensive experimental results on real hyperspectral datasets verify that the proposed method is ahead of other widely used and state-of-the-art methods in terms of computational cost, detection effects, and robustness, and promising to provide technical support for detection response requirements in practical applications.

As one of the most active research hotspots in hyperspectral remote sensing, anomaly detection is widely used because it takes effect without any priori information about the target or the background. Most of the traditional model-driven methods fail to reveal features of data with diversity due to fixed analytical modes. A variety of data-driven methods encounter difficulties in practical applications due to their costly computational complexity. In this article, an innovative combination of point-set topology and information entropy theories is utilized to analyze the mathematical–statistical properties of hyperspectral images (HSIs), thus eliminating the limitations caused by the data-model discrepancy. Specifically, the original HSI data are mapped into topological spaces in a specific form to enable ordered arrangements, in preparation for revealing data features. In particular, information entropy estimation is introduced for the first time in the adoption of point-set topology to adequately unravel the data arrangements in topological spaces, whereby the land cover information is efficiently extracted for detection. Accordingly, an interesting approach of information entropy estimation based on point-set topology (IEEPST) is proposed to resolve anomaly detection from a brand new perspective, pursuing prominent detection accuracy while ensuring computational efficiency. The experimental results on benchmark HSI datasets demonstrate that IEEPST achieves detection performance with high probabilities of detection (PD) and low false alarm rates (FARs) at an inexpensive computational cost. The proposed IEEPST is highly competitive with other sophisticated and state-of-the-art methods.

Cloud contamination greatly limits the potential utilization of optical images for geoscience applications. An effective alternative is to extract data from synthetic aperture radar (SAR) images to remove clouds due to the strong penetration ability of microwaves. In this article, we propose a novel unified spatial–spectral residual network that utilizes SAR images as auxiliary data to remove clouds from optical images. The method can better establish the relationship between SAR and optical images and be divided into two modules: feature extraction and fusion module and reconstruction module. In the feature extraction and fusion module, a gated convolutional layer is introduced to discriminate cloud pixels from clean pixels, which makes up for the lack of distinguishing ability of vanilla convolutional layers and avoids the error of cloud areas in feature extraction. In the reconstruction module, spatial and channel attention mechanisms are introduced to obtain global spatial and spectral information. The network is tested on three datasets with different spatial resolutions and compositions of land covers to verify the effectiveness and applicability of the method. The results show that the method outperforms other mainstream algorithms that simultaneously use SAR images as auxiliary data with a gain of about 2.3 dB in terms of peak signal-to-noise ratio PSNR on the SEN12MS-CR dataset.

Target detection is a critical task in interpreting hyperspectral remote sensing images. Small target (such as airplanes) detection is challenging, especially in large-scale complex scenes with high spectral variability of different land cover types. In this paper, we propose a transfer learning-based, large-scale, robust hyperspectral target detector (TLH2TD) to improve the accuracy of hyperspectral target detection (HTD) in large-scale complex scenes. TLH2TD learns the spatial features of hyperspectral targets from high-resolution remote sensing images and achieves high-precision HTD with fused spatial-spectral features. It comprises three parts: (1) The coupled target-background sample expansion (CTBSE) module is designed to expand the labeled hyperspectral target and background samples with sufficient high-resolution, labeled RGB images and a few labeled hyperspectral samples. (2) The hard positive and negative example mining (HPNEM) module trains the hard positive and negative samples to enhance the discriminative ability of the network, addressing the problem of inadequate sample training in large-scale hyperspectral images (HSIs). (3) The spatial-spectral weighted subspace (SSWS) module is designed to fuse the spatial features extracted from the target detection network and the spectral features based on the Mahalanobis distance. The results show that: (1) The TLH2TD achieves average area under the curve (AUC) values of 0.96, 0.96, and 0.93 on small-sized, medium-sized, and large-sized HSIs, respectively, achieving the highest accuracy compared with other HTD algorithms. (2) The TLH2TD exhibits the highest detection time efficiency for medium-sized and large-sized HSIs. (3) For large-sized HSIs, when most HTD algorithms fail, TLH2TD exhibits significantly higher accuracy and time efficiency than other methods. This is an important achievement to meet the robust target detection tasks of large-scale hyperspectral remote sensing images.

The integrated use of multisource remote sensing (RS) data in Earth observation missions has garnered considerable attention. Hyperspectral images (HSIs) offer extensive spatial and spectral detail, whereas light detection and ranging (LiDAR) data provide elevation information. Therefore, the fusion of HSI and LiDAR data can enhance the accuracy (ACC) of image classification. However, contemporary supervised multimodal deep learning techniques depend heavily on extensive human-annotated training datasets. To address this challenge, we propose a contrastive prototypical clustering network enhanced with a dual-feature attention module. Specifically, two sets of enhanced modal views are constructed from the multimodal RS images for the subsequent contrastive learning. The proposed dual-feature attention module emphasizes channel and spatial attention separately for each modality, integrating both to adjust the feature representation across different channels and positions. By learning the importance weights of each channel and position, this module highlights the hierarchical structure and enhances the discriminative quality of the features. The learned features are utilized through an online clustering mechanism and a self-supervised training strategy that combines contrastive loss and cluster loss to achieve efficient and effective land cover classification. Extensive experiments on three widely used HSI and LiDAR datasets demonstrate that the proposed method outperforms current state-of-the-art approaches. The code for this method is openly available at:https://github.com/RogsDing/DFCPC.

Hyperspectral image (HSI) change detection (CD) focuses on identifying changes in the internal components of land cover and land use. Convolutional neural networks (CNNs) have made significant progress in HSI-CD. Concurrently, graph convolutional networks (GCNs) have gained considerable attention for their ability to utilize unlabeled data and explicitly exploit correlations between adjacent parcels. However, CNNs are constrained by fixed, small-size convolutional kernels, which severely limit their receptive field. On the other hand, GCNs use superpixels to reduce the number of nodes, which will lead to losing pixel-level features, resulting in partial feature representations from both networks. To leverage the strengths of both CNNs and GCNs, a model was proposed that incorporates two subnetworks: decomposed multiscale gated guided CNNs and strengthened residual graph convolution. The decomposed multiscale gated guided CNNs are designed to capture pixel-level features at various scales using different kernel sizes. A gated change information fusion (GCF) unit integrates these multiscale pixel-level features. Meanwhile, the strengthened residual graph convolution was used to aggregate change information, which can prevent node information from becoming homogeneous. Additionally, a feature fusion module (FFM) is employed to combine features from the two subnetworks. The proposed model effectively utilizes both multiscale convolution and graph features, facilitating the learning of multilevel contextual semantic features. The experimental results on three HSI datasets demonstrate that this model outperforms several state-of-the-art methods. The code is available athttps://github.com/zhangyiyan001/srgmgn.

Hyperspectral imaging enables advanced change detection but struggles with extensive redundant data across spatial and spectral dimensions. This bloats model size and computational loads. To address this problem, we propose a new gated spectral–spatial–temporal attention network with spectral similarity filtering (HyGSTAN) with a lightweight yet accurate architectural design. Specifically, our HyGSTAN introduces three innovative modules: 1) spectral similarity filtering to reduce spectral redundancy via cosine similarity; 2) gated spectral-spatial attention to capture intra-image spatial features using single-head weak self-attention and gated mechanisms; and 3) gated spectral–spatial–temporal attention to extract inter-image temporal changes. Experiments on three benchmark datasets demonstrate HyGSTAN’s ability to balance accuracy, model complexity, and computational efficiency. The proposed attention mechanisms extract more discriminative information without sacrificing performance. The source code of this work will be released at https://github.com/Welcome-to-LISA/HyGSTAN.

Single-image super-resolution (SISR) for high-resolution (HR) remote sensing image (RSI) acquisition is becoming increasingly valuable and important, and convolutional neural networks (CNNs) have produced considerable progress in this field. In RSIs, many similar geo-objects recur within the same scene, maintaining the same positions in both low resolution (LR) and HR. Based on this observation, we found that these similar geo-objects could be utilized to reconstruct texture details in LR by exploiting the consistent non-local relationships between these geo-objects in LR and HR, thereby improving the quality of SISR. Therefore, we propose a novel graph convolutional network (GCN) for SISR including a dynamic graph attention mechanism to learn the in-scale and cross-scale non-local features of RSIs. In scale, we propose a dynamic graph attention block (DGAB) that adaptively determines non-local patches upon the scene correlation derived from RSIs and further fuses patch-wise non-local information weighed by the attention scores of topological relationships and radiation characteristics in RSIs. Across different scales, we also introduce a dynamic graph attention mixing block (DGAMB) to upsample LR non-local information to HR non-local information. Most SISR methods have the upsampling blocks at the end of the network, ignoring feature extraction in high-dimensional space. To address this problem, DGAMB was designed as an upsampler in the middle of the model, enhancing the level of high-dimensional information extraction from the model. The experiments based on the WHU Building and UC Merced datasets show that our proposed method outperforms state-of-the-art methods. Our code is available athttps://github.com/WenjuanZhang-aircas/NSGCN.

Hyperspectral anomaly detection (HAD) aims to highlight the pixels that are different from the surrounding pixels without any prior information. However, as a hyperspectral image (HSI) tends to possess a huge data volume in the spectral domain, the dimension curse is inevitable in HAD. The unsupervised band selection (UBS) method is an effective tool to avoid the dimensionality curse in the HAD task. To obtain a more robust band subset without the help of any HAD detectors, we propose a spectral–spatial out-of-distribution (OOD)-based UBS method for HAD (HADUBS), which can acquire the optimal band subset in a more straightforward way. Our key observation is that the OOD term of pixels can reveal the differences and similarities of anomaly representation ability of different bands. Hence, we developed an OOD-based feature subspace representation module to obtain latent feature spaces with a better indication of the anomaly detection ability. Moreover, we introduced a UBS strategy called mutual information (MI)-based local outlier factor (MILOF) to significantly improve the discriminative ability of the selected band subset by investigating the locally sparse prior of anomalies. Extensive experimental results on five common HAD datasets demonstrate the superior performance of HADUBS. The source code will be made publicly available athttps://github.com/duang33/HADUBS.

Hyperspectral image change detection (HSI-CD) has recently become a research hotspot. Current methods rely heavily on a huge amount of training samples to perform the change detection tasks. While acquiring data from the same region of bi-temporal HSIs is extraordinarily time-consuming and laborious. Therefore, this letter proposes an unsupervised method based on three dimensional (3D) depthwise separable convolutional autoencoders (DSConvAE). First, the dual-branch symmetrical 3D DSConvAE is pre-trained with limited samples to obtain the optimal weights, which facilitates extracting discriminative spatial and spectral features subsequently. Second, we adopt the temporal-specific feature concatenation strategy to acquire comprehensive characteristics from bi-temporal HSIs. Third, the general autoencoders are employed at the end of the model to further explore the high-level and abstract feature vectors. Finally, we compare the mean square loss calculated from the spatial-spectral branches and apply threshold judgement to generate the ultimate detection maps. Experimental results on three public HSI datasets demonstrate that the proposed framework outperforms other comparative methods by significant improvements.

Spatial-spectral classification (SSC) has become a trend for hyperspectral image (HSI) classification. However, most SSC methods mainly consider local information, so that some correlations may not be effectively discovered when they appear in regions that are not contiguous. Although many SSC methods can acquire spatial-contextual characteristics via spatial filtering, they lack the ability to consider correlations in non-Euclidean spaces. To address the aforementioned issues, we develop a new semisupervised HSI classification approach based on normalized spectral clustering with kernel-based learning (NSCKL), which can aggregate local-to-global correlations to achieve a distinguishable embedding to improve HSI classification performance. In this work, we propose a normalized spectral clustering (NSC) scheme that can learn new features under a manifold assumption. Specifically, we first design a kernel-based iterative filter (KIF) to establish vertices of the undirected graph, aiming to assign initial connections to the nodes associated with pixels. The NSC first gathers local correlations in the Euclidean space and then captures global correlations in the manifold. Even though homogeneous pixels are distributed in noncontiguous regions, our NSC can still aggregate correlations to generate new (clustered) features. Finally, the clustered features and a kernel-based extreme learning machine (KELM) are employed to achieve the semisupervised classification. The effectiveness of our NSCKL is evaluated by using several HSIs. When compared with other state-of-the-art (SOTA) classification approaches, our newly proposed NSCKL demonstrates very competitive performance. The codes will be available at https://github.com/yuanchaosu/TCYB-nsckl.

Deep learning (DL) has recently risen to prominence in hyperspectral target detection (HTD). Nevertheless, how to tackle the extreme training sample imbalance together with achieving target highlighting and background suppression is challenging. Additionally, due to the spectral redundancy of hyperspectral imagery (HSI), it is a new course for HTD through band selection (BS) to retain crucial bands thereupon improving the subsequent detection performance. Accordingly, we propose a DL-based BS-HTD (DLBSTD) algorithm, incorporating DL-based BS with DL-based HTD for the first time. Most significantly, a multi-depth and multi-branch network (MDBN) for HTD based on a novel BS method is proposed. First of all, the BS method including an alternating local-global reconstruction network (ALGRN) and a correlation measurement strategy provides representative bands containing key target information for MDBN. For the training sample imbalance of MDBN, we develop a BS-based method to select multifarious representative background training samples and propose a target band random substitution (TBRS) strategy to augment an ample target training set. Lastly, the MDBN composed of a multi-depth feature extraction (MDFE) module, three fusion strategies, and the parallel local convolution and gated recurrent unit (Conv-GRU) fully taps the spectral feature relationships to highlight targets and suppress backgrounds. Compared with nine competitive HTD algorithms, we carry out plentiful experiments on four classical datasets exhibiting that the proposed DLBSTD has strong generalization and salient detection performance of target highlighting and background suppression.

With the abundant emergence of remote sensing data sources, multimodal remote sensing observation has become an active field. Extracting valuable information from multi-modal data has the potential to make a significant contribution to applications such as urban planning and monitoring. However, existing studies are deficient in extracting spectral and spatial features from hyperspectral remote sensing data. Meanwhile, the method of fusing multimodal features has limitations and poses a challenge to the convergence of the model loss function, which increases the complexity of the network model optimisation process. Therefore, this paper proposes an Adaptive Multi-scale Spatial–Spectral Enhancement Network for Classification of Hyperspectral and LiDAR Data called AMSSE-Net. First, we perform deep mining of spectral features in hyperspectral images by the involution operator. The main idea is to take full advantage of the involution operator in characterising spectral features by using the property that the convolution kernel shares the feature channels within the group. Furthermore, the multi-branching approach is used to extract the multi-scale information, and then the spectral-spatial features are formed with the strategy of hierarchical fusion. Meanwhile, we employ three-layer convolution for extracting shallow features from LiDAR data, offering supplementary information. Finally, we propose the ”Adaptive Feature Fusion Module,” an innovative and comprehensive mechanism designed for the fusion of features from diverse sources in multi-source data fusion. These dynamically assigned weights guide the selection of the optimal model, which is determined by the joint loss across the three methods, ultimately leading to the generation of an accurate prediction map. This approach not only helps to deeply explore the spectral spatial information in the hyperspectral data, but also effectively fuses the hyperspectral information with the elevation information from the LiDAR data. The expression ability of model features is rapidly improved by adaptive weighting, which in turn enhances the performance and generalisation ability of the model. Compared with some existing methods, extensive experiments on three popular HSI and LiDAR datasets show that our proposed AMSSE-Net can achieve better classification performance. The codes will be available at https://github.com/haofeng0003/AMSSE-Net, contributing to the RS community.

Without any prior information, hyperspectral anomaly detection is devoted to locating targets of interest within a specific scene by exploiting differences in spectral characteristics between various land covers. Traditional methods originated from the signal processing perspective, and most of them rely heavily on specific model assumptions. Because of the model-driven attributes, such methods cannot mine the deep-level features of data to adapt to the variability of scenes and cannot fully extract the information of land covers contained in images to accurately separate anomalies from the background. By independently designing a chessboard-shaped topological framework that avoids making any distribution assumptions but directly mines high-dimensional data features to break through the limitations of traditional detectors, this article proposes a novel chessboard topology-based anomaly detection (CTAD) method to dissect images and extract detailed information of land covers adaptively, thereby enabling highly accurate detection. Extensive experimental results on hyperspectral images (HSIs) in real scenes demonstrate that the proposed CTAD can be adapted to the variability of scenes by autonomously learning data features and exhibiting strong generalization and detection capabilities, facilitating practical applications.

Hyperspectral target detection (HTD) is a pixel-wise detection method based on limited prior targets and spectral differences, which has been widely studied and applied in many fields. Recently, deep learning (DL) plays an important role in hyperspectral imagery (HSI) processing. However, for HTD, the severe lack of class-balanced training sets is an enormous challenge. Meanwhile, it is difficult to suppress backgrounds while highlighting targets through the deep network. To address these issues, we propose a spectral aggregation and separation network (SASN) with a target band random mask (TBRM) for HTD in this paper. For the training sets of SASN, a multifarious representative background selection strategy (MRBS) is first proposed to obtain a multifarious and representative background training set. Next, aiming at the notorious class imbalance, a data augmentation (DA) method, TBRM, is proposed to generate adequate target training set by repeating randomly zero-masking the spectral bands of a prior target. Subsequently, in the training of SASN, residual connection and squeeze-and-excitation (SE) channel attention mechanism are applied to fully extract high discriminative features and nonlinear ones in the spectra. Besides, to better separate the targets and backgrounds, a triplet-soft loss function is presented, which makes the training in the direction of spectral separation of background samples from both the prior target and target samples. During testing, the trained SASN distinguishes the spectral similarities and differences simultaneously for highlighting targets and suppressing backgrounds. Moreover, extensive experimental results validate that the proposed method has superior detection performances, background suppression capacity, and separability compared with ten cutting-edge HTD algorithms on six benchmark HSI datasets.

Remote sensing of leaf chlorophyll content (LCC) is critical in precision agriculture, forest monitoring, and pest management. Chlorophyll absorbs light in the visible and red-edge spectrum areas. However, many multispectral sensors lack red-edge bands. Subsequently, the development of effective visible chlorophyll-related indicators is important. The hue angle defined in the CIE xy chromaticity diagram, which reflects the human eye’s color discrimination ability relying on visible light (400–700 nm), is introduced in this study for LCC estimation. This study proposes a new multispectral hue angle calculation method employing D65 standard illuminant data, investigates the effect of illuminant factors and band settings on hue angle calculation, and presents tristimulus weight coefficients for calculating MERIS, MSI, and ETM+ hue angles. Furthermore, the sensitivity of the link between LCC and different hue angles, as well as vegetative indices (VIs), is assessed in dense and sparse canopies. The results show that using wavelength-independent illuminant data or discrete bands overcalculates the reflectance-based hue angle. Moreover, our proposed hue angle calculated using D65 standard illuminant data is more sensitive to LCC than the existing hue angle using wavelength-independent illuminant data. In dense canopies, the multispectral hue angle has a stronger relationship with LCC than in sparse canopies. The multispectral hue angle generally appears weaker or similar to the red-edge VIs (MTCI and CIred-edge), but stronger than the non-red-edge VIs (CIgreen, NDVI, NGRDI, and TGI). These findings imply that the multispectral hue angle calculated from visible bands provides the potential to monitor LCC of large-scale plants.

Considerable endeavors have been expended towards enhancing the representation performance for Hyperspectral Anomaly Detection (HAD) through physical model-based methods and recent deep learning-based approaches. Of these methods, the Low-Rank Representation (LRR) model is widely adopted for its formidable separation capabilities for background and target features, however, its practical applications are limited due to the reliance on manual parameter selection and subpar generalization performance. To this end, this paper presents a new HAD baseline network, referred to as LRR-Net, which synergizes the LRR model with deep learning techniques. LRR-Net leverages the alternating direction method of multipliers (ADMM) optimizer to solve the LRR model efficiently and incorporates the solution as prior knowledge into the deep network to guide the optimization of parameters. Moreover, LRR-Net transforms the regularized parameters into trainable parameters of the deep neural network, thus alleviating the need for manual parameter tuning. Additionally, this paper proposes a sparse neural network embedding to demonstrate the scalability of the LRR-Net framework. Empirical evaluations on eight distinct datasets illustrate the efficacy and superiority of the proposed approach compared to state-of-the-art methods.

Given a priori knowledge, hyperspectral target detection aims to locate objects of interest within specific scenes by utilizing differences in spectral characteristics among various land covers. However, for those traditional model-driven detectors with monotonic analytical mode, they perform mediocrely in the disassembly of hyperspectral image (HSI) data, failing to cope with real scenes with complexity. The discrepancy between fixed model assumptions and HSI data severely reduces detection effects, leading to the inability of such methods to mine deep-level features and adapt to the variability of imaging scenes. To overcome the limitations of traditional methods, we propose a chessboard-shaped topological framework for high-dimensional data structures to disassemble an HSI from both spatial and spectral dimensions adaptively. With hyperspectral target detection is refined into an information retrieval task in a topological space, a target detection method based on chessboard-shaped topology (CTTD) is proposed. In the topological space, latent and hidden data features of original images are presented in an intuitive way. Therefore, the differences in both spatial and spectral dimensions between the two classes of objects, namely target and background, are specifically amplified and exploited to perform the information retrieval task with superior performance. Extensive experimental results on benchmark HSI data sets demonstrate that CTTD can efficiently adapt to the variability of real scenes while extracting abundant and detailed information for accurate target localization. Moreover, both detection effects and computational efficiency exhibited by the proposed method provide a strong support for its popularization in practical applications.

Efforts to enhance the detection accuracy of hyperspectral (HS) anomaly detection (AD) have been significant, but the impact of noise resulting from HS data acquisition and transmission has not been well studied. Furthermore, the separation of denoising and subsequent interpretation makes it challenging to evaluate and control the influence of noise on the detection results. To this end, we proposed a joint anomaly detection and noise removal (ADNR) paradigm called DSR-ADNR, which develops a double subspace representation method to obtain both denoised and detection results simultaneously. DSR-ADNR uses a low-dimensional orthogonal basis to represent HS images and extract distinctive features for AD. The feature matrix is represented by a dictionary-based low-rank subspace that captures the complex nature of the low-dimensional features. In each iteration, DSR-ADNR utilizes the nonlocal self-similarity of the feature matrix to remove noise and improve intermediate detection performance. Meanwhile, the progressive LR representation of the background and anomalies for the feature matrix upgrades the explicit LR expression of nonlocal self-similar patches for better denoising. The well-designed linearized alternating direction method of multipliers with an adaptive penalty (LADMAP) is utilized to solve the proposed DSR-ADNR. Extensive experiments on simulated and real-world data sets demonstrate the effectiveness of DSR-ADNR in the HS AD task under different noise cases.

The recent success of attention mechanism-driven deep models, like Vision Transformer (ViT) as one of the most representative, has intrigued a wave of advanced research to explore their adaptation to broader domains. However, current Transformer-based approaches in the remote sensing (RS) community pay more attention to single-modality data, which might lose expandability in making full use of the ever-growing multimodal Earth observation data. To this end, we propose a novel multimodal deep learning framework by extending conventional ViT with minimal modifications, abbreviated as ExViT, aiming at the task of land use and land cover classification. Unlike common stems that adopt either linear patch projection or deep regional embedder, our approach processes multimodal RS image patches with parallel branches of position-shared ViTs extended with separable convolution modules, which offers an economical solution to leverage both spatial and modality-specific channel information. Furthermore, to promote information exchange across heterogeneous modalities, their tokenized embeddings are then fused through a cross-modality attention module by exploiting pixel-level spatial correlation in RS scenes. Both of these modifications significantly improve the discriminative ability of classification tokens in each modality and thus further performance increase can be finally attained by a full tokens-based decision-level fusion module. We conduct extensive experiments on two multimodal RS benchmark datasets, i.e., the Houston2013 dataset containing hyperspectral and light detection and ranging (LiDAR) data, and Berlin dataset with hyperspectral and synthetic aperture radar (SAR) data, to demonstrate that our ExViT outperforms concurrent competitors based on Transformer or convolutional neural network (CNN) backbones, in addition to several competitive machine learning-based models. The source codes and investigated datasets of this work will be made publicly available at https://github.com/jingyao16/ExViT.

Arbitrary-oriented object detection (AOOD) is widely used in aerial images because of its efficient object representation. However, current detectors employ the over-standardized feature extraction structure, resulting in detectors has no ability to adaptively readjust feature representations of detection units. Meanwhile, we observe that many detection units could not focus on the objects of interest in their receptive field and are easily affected by the background information and interference targets, leading to the weaking of feature expression ability. We call them sub-optimal detection units. To address this issue, we propose a novel feature enhancement module called fountain feature enhancement module (FFEM). FFEM ingeniously uses the fountain-like structure to reconstruct the features of sub-optimal detection units, generating fountain features that can automatically condense spatial regional features, which effectively enhances detectors’ overall representation ability. Then, a high-performance AOOD detector called fountain fusion net (FFN) is proposed with FFEM embedded, and many novel AOOD components are tested for their progressiveness. We validated our FFN and FFEM using three remote sensing datasets ‒ DOTA, HRSC2016, and UCAS-AOD as well as one scene text dataset‒ICDAR 2015. Extensive experiments demonstrate the effectiveness of our proposed method on improving current detectors to achieve state-of-the-art performance based on this novel idea.

Owing to the powerful feature extraction and representation capabilities, deep learning (DL) has been successfully applied in hyperspectral unmixing (HU). However, only relying on hyperspectral data for unmixing fails to distinguish objects with similar spectral information, resulting in the degradation of unmixing performance. To this end, this paper presents a novel multimodal unmixing network, MUNet for short, by considering the height information of light detection and ranging (LiDAR) data in a squeeze-and-excitation (SE) attention fashion to guide the unmixing process toward a more accurate performance. MUNet is capable of efficiently embedding the height information obtained from LiDAR data into the autoencoder unmixing architecture through the attention mechanism, thereby fusing more spatial information to obtain ideal unmixing results. Experimental results conducted on the real multimodal dataset demonstrate the effectiveness and superiority of the proposed MUNet compared to several state-of-the-art deep unmixing approaches.

Cloud cover is a common problem in optical satellite imagery, which leads to missing information in images. To rapidly acquire noncloud images, we design a cloud removal method to recover single-temporal remote sensing image based on land cover data which is easier to obtain than multitemporal data. Considering that the same features have the same radiation characteristics, we extract the similar pixels from same category around the missing pixels and calculate the value of missing pixels according to the distance weights of these pixels. The performance of the proposed method was evaluated on MODIS images and Landsat images and the results also prove that universal applicability of this algorithm in different resolutions and surface contents.

In this letter, a novel neural architecture search (NAS) method based on reinforcement learning, called RLNAS, is devised to realize the automatic architecture design in the field of hyperspectral unmixing (HU). This method first train the search network in the constructed self-supervised datasets based on hyperspectral images. The block-based searching and weight-sharing strategies are then introduced to reduce the computational cost in the training phase. The final optimal architecture is obtained by optimizing the multi-objective reward function to balance the trade-off between accuracy and computational efficiency. Compared with the state-of-the-art unmixing algorithms, the proposed RLNAS method can yield better unmixing results on synthetic and real hyperspectral datasets, which verifies its effectiveness and superiority. In addition, the proposed method offers promising potential of the NAS for HU.

Deep learning (DL) has been garnering increasing attention in remote sensing (RS) due to its powerful data representation ability. In particular, deep models have been proven to be effective for RS data classification based on a single given modality. However, with one single modality, the ability in identifying the materials remains limited due to the lack of feature diversity. To overcome this limitation, we present a simple but effective multimodal DL baseline by following a deep encoder–decoder network architecture, EndNet for short, for the classification of hyperspectral and light detection and ranging (LiDAR) data. EndNet fuses the multimodal information by enforcing the fused features to reconstruct the multimodal input in turn. Such a reconstruction strategy is capable of better activating the neurons across modalities compared with some conventional and widely used fusion strategies, e.g., early fusion, middle fusion, and late fusion. Extensive experiments conducted on two popular hyperspectral and LiDAR data sets demonstrate the superiority and effectiveness of the proposed EndNet in comparison with several state-of-the-art baselines in the hyperspectral-LiDAR classification task. The codes will be available athttps://github.com/danfenghong/IEEE_GRSL_EndNet, contributing to the RS community.

Owing to easy acquisition and large coverage from the space, multispectral (MS) imaging has garnered growing interest in various applications of remote sensing. However, the limited spectral information of MS data, to a great extent, leads to difficulties in classifying the materials more accurately, particularly for those classes that have very similar visual appearances. To address this issue effectively, we attempt to enhance the spectral resolution of MS imagery, enabling the identification of materials at a more precise level by the means of richer spectral information. More specifically, we propose to learn locality-constrained sparse coding (LCSC) for short, on partially overlapped hyperspectral (HS)-MS pairs (i.e., dictionary). LCSC is capable of capturing neighboring relations well by enforcing the local constraint for each pixel. Such a strategy makes it possible to better reconstruct HS products from MS images and partially overlapped HS images. Reconstruction and unmixing are explored as potential applications to assess the performance of spectral enhancement. Extensive experiments are conducted on two HS-MS data sets in comparison with several state-of-the-art baselines, which demonstrate the effectiveness of the proposed LCSC algorithm in the task of spectral enhancement.

Fractional vegetation cover (FVC) is an important indicator for exploring hydrosphere, pedosphere, atmosphere, biosphere, and their interactions. Deep learning (DL) is a potential tool to handle large-scale data and approximate the complex nonlinear relationship between variables. It is, therefore, suitable for FVC estimation. However, few DL-based algorithms have been developed to estimate FVC as it is difficult to obtain a large amount of training data. This letter presents a novel method by means of deep transfer learning to address this issue. The proposed technique consists of two steps. In the first step, a large amount of simulated training samples were generated by a physical model (PROSPECT + SAIL radiative transfer model, PROSAIL). In the second step, a long short-term memory (LSTM) network was pretrained with the simulated training dataset obtained in the first step. Then limited real samples from satellite images were used to fine-tune the pretrained network. Experiments were conducted for the Sentinel-2 multispectral satellite images of two areas and the results were compared with those obtained by the traditional the Normalized Difference Vegetation Index (NDVI)-based method and two machine learning approaches. The results demonstrate that the performance of our method outperforms other advanced FVC estimation methods.

Hyperspectral images (HSIs) exist in directional stripes commonly due to the failure of pushbroom acquisition. These stripes are not only vertically and horizontally oriented but also tend to be oblique. Furthermore, they can also be aperiodic and heavy. To address this problem, we propose a hyperspectral destriping algorithm, namely, GF-destriping. Taking advantage of the high sparsity and strong directionality of stripes in HSIs, Gabor filters are used to detect the stripes band by band first, and then, an advanced inpainting method, FastHyIn, is used to recover to the striped image. The numerical experiments on simulated data and real data sets show that our proposed algorithm is efficient and superior to state-of-the-art HSI destriping algorithms.

Owing to the powerful and automatic representation capabilities, deep learning (DL) techniques have made significant breakthroughs and progress in hyperspectral unmixing (HU). Among the DL approaches, autoencoders (AEs) have become a widely-used and promising network architecture. However, these AE-based methods heavily rely on manual design and may not be a good fit for specific datasets. To unmix hyperspectral images more intelligently, we propose an automatic neural architecture search model for HU, AutoNAS for short, to determine the optimal network architecture by considering channel configurations and convolution kernels simultaneously. In AutoNAS, the self-supervised training mechanism based on hyperspectral images is first designed for generating the training samples of the supernet. Then, the affine parameter sharing strategy is adopted by applying different affine transformations on the supernet weights in the training phase, which enables finding the optimal channel configuration. Furthermore, on the basis of the obtained channel configuration, the evolutionary algorithm with additional computational constraints is introduced into networks to achieve flexible convolution kernel search by evaluating unmixing results of different architectures in the supernet. Extensive experiments conducted on four hyperspectral datasets demonstrate the effectiveness and superiority of the proposed AutoNAS in comparison with several state-of-the-art unmixing algorithms.

Hyperspectral image (HSI) has received considerable attention in the field of target detection due to its powerful ability to capture the spectral information of land covers, and plenty of detection algorithms have been explored. However, these methods generally leverage the difference between the spectrum of the target to be detected and the background spectrum to accomplish target detection, and so are susceptible to the problem of spectral variability. In this article, we propose a global-to-local hierarchical detection algorithm for HSI (G2LHTD). Firstly, extended morphological attribute profile (EMAP) is first used to model global spatial texture information from HSI. Subsequently, a diverse-direction constrained energy minimization (D2CEM) detector is developed to consider the spatial information within eight neighborhoods around each pixel in HSI, yielding comprehensive local spatial information. More substantially, to effectively discriminate the neighborhood information in diverse directions, we devise an adaptive neighborhood feature aggregation (ANFA) strategy, which will comprehensively evaluate the significance of neighborhood information in diverse directions. As a result, the spatial features of HSI can be comprehensively considered for hyperspectral target detection (HTD). Extensive experiments, conducted on four standard datasets, demonstrate the effectiveness of the proposed method. The codes of this work will be available at https://github.com/zhonghaocheng/G2LHTD_Master for the sake of reproducibility.

In recent years, deep learning (DL) has attracted increasing attention in hyperspectral unmixing (HU) applications due to its powerful learning and data fitting ability. The autoencoder (AE) framework, as an unmixing baseline network, achieves good performance in HU by automatically learning low-dimensional embeddings and reconstructing data. Nevertheless, the conventional AE-based architecture, which focuses more on the pixel-level reconstruction loss, tends to lose some significant detailed information of certain materials (e.g., material-related properties) in the reconstruction process. Therefore, inspired by the perception mechanism, we propose a cycle-consistency unmixing network, called CyCU-Net, by learning two cascaded AEs in an end-to-end fashion, to enhance the unmixing performance more effectively. CyCU-Net is capable of reducing the detailed and material-related information loss in the process of reconstruction by relaxing the original pixel-level reconstruction assumption to cycle consistency dominated by the cascaded AEs. More specifically, cycle consistency can be achieved by a newly proposed self-perception loss, which consists of two spectral reconstruction terms and one abundance reconstruction term. By taking advantage of the self-perception loss in the network, the high-level semantic information can be well preserved in the unmixing process. Moreover, we investigate the performance gain of CyCU-Net with extensive ablation studies. Experimental results on one synthetic and three real hyperspectral data sets demonstrate the effectiveness and competitiveness of the proposed CyCU-Net in comparison with several state-of-the-art unmixing algorithms.

Tensor-based methods have been widely studied to attack inverse problems in hyperspectral imaging since a hyperspectral image (HSI) cube can be naturally represented as a third-order tensor, which can perfectly retain the spatial information in the image. In this article, we extend the linear tensor method to the nonlinear tensor method and propose a nonlinear low-rank tensor unmixing algorithm to solve the generalized bilinear model (GBM). Specifically, the linear and nonlinear parts of the GBM can both be expressed as tensors. Furthermore, the low-rank structures of abundance maps and nonlinear interaction abundance maps are exploited by minimizing their nuclear norm, thus taking full advantage of the high spatial correlation in HSIs. Synthetic and real-data experiments show that the low rank of abundance maps and nonlinear interaction abundance maps exploited in our method can improve the performance of the nonlinear unmixing. A MATLAB demo of this work will be available athttps://github.com/LinaZhuangfor the sake of reproducibility.

Deep learning (DL) has aroused wide attention in hyperspectral unmixing (HU) owing to its powerful feature representation ability. As a representative of unsupervised DL approaches, autoencoder (AE) has been proven to be effective to better capture nonlinear components of hyperspectral images than the traditional model-driven linearized methods. However, only using hyperspectral images for unmixing fails to distinguish objects in complex scene, especially for different endmembers with similar materials. To overcome this limitation, we propose a novel multimodal unmixing network for hyperspectral images, called MUNet, by considering the height differences of light detection and ranging (LiDAR) data in a squeeze-and-excitation (SE)-driven attention fashion to guide the unmixing process, yielding performance improvement. MUNet is capable of fusing multimodal information and using the attention map derived by LiDAR to aid network that focuses on more discriminative and meaningful spatial information regarding scenes. Moreover, attribute profile (AP) is adopted to extract the geometrical structures of different objects to better model the spatial information of LiDAR. Experimental results on synthetic and real datasets demonstrate the effectiveness and superiority of the proposed method compared with several state-of-the-art unmixing algorithms. The codes will be available athttps://github.com/hanzhu97702/IEEE_TGRS_MUNet, contributing to the remote sensing community.

Hyperspectral (HS) images are characterized by approximately contiguous spectral information, enabling the fine identification of materials by capturing subtle spectral discrepancies. Owing to their excellent locally contextual modeling ability, convolutional neural networks (CNNs) have been proven to be a powerful feature extractor in HS image classification. However, CNNs fail to mine and represent the sequence attributes of spectral signatures well due to the limitations of their inherent network backbone. To solve this issue, we rethink HS image classification from a sequential perspective with transformers, and propose a novel backbone network called \ul{SpectralFormer}. Beyond band-wise representations in classic transformers, SpectralFormer is capable of learning spectrally local sequence information from neighboring bands of HS images, yielding group-wise spectral embeddings. More significantly, to reduce the possibility of losing valuable information in the layer-wise propagation process, we devise a cross-layer skip connection to convey memory-like components from shallow to deep layers by adaptively learning to fuse "soft" residuals across layers. It is worth noting that the proposed SpectralFormer is a highly flexible backbone network, which can be applicable to both pixel- and patch-wise inputs. We evaluate the classification performance of the proposed SpectralFormer on three HS datasets by conducting extensive experiments, showing the superiority over classic transformers and achieving a significant improvement in comparison with state-of-the-art backbone networks. The codes of this work will be available at https://github.com/danfenghong/IEEE_TGRS_SpectralFormer for the sake of reproducibility.

Due to rich spectral and spatial information, the combination of hyperspectral and multispectral images (MSIs) has been widely used for Earth observation, such as wetland classification. However, mining of meaningful features and effective fusion of multisource remote sensing data are still urgent problems to be solved. In this article, graph-feature-enhanced selective assignment network (GSANet) is proposed. On the one hand, a graph feature extraction module (GFEM) is designed to extract topological structure information and combine with the rich spectral–spatial information. In particular, the features obtained by convolution are first mapped to the graph feature space, and the graph convolution operation is used to achieve propagation between nodes for preserving topological structure information. Moreover, to reduce the difference of graph features resulting from the mapping function and better explore the complementary properties of multisource data, a novel graph fusion strategy-graph dependence fusion is designed. A transition graph is generated to enhance the association and interaction between different graph features, so as to avoid the information loss caused by simple fusion operation. On the other hand, a selective feature assignment module (SFAM) is developed to adaptively assign weights to different discriminative features. SFAM assigns weights to different features to selectively emphasize informative features and suppress less useful ones. Extensive experiments are conducted on two multisource remote sensing datasets, and the improvement of at least 1.27% and 0.98% compared to other state-of-the-art work demonstrates the superiority of the proposed GSANet.

Water clarity (Zsd) is a widely used quality indicator that can be estimated from remote sensing imagery. China’s newest generation Advanced HyperSpectral Imager (AHSI) onboard the ZY1-02D satellite is expected to enable accurate water clarity retrieval for inland waters, since AHSI can provide abundant band choices while its 30-m spatial resolution is advantageous for monitoring small inland water bodies. In this study, to retrieve Zsd from the ZY1-02D imagery for inland waters with varying turbidities, we propose a classification-based, semi-analytical method in which the red/blue band ratio is employed to distinguish clear to moderately turbid water and highly turbid waters. Two Quasi Analytical Approaches (QAAs), QAAv5 and QAAm14, are used to estimate the total absorption coefficient (a(λ)) and the backscattering coefficient (bb(λ)) for clear to moderately turbid water and highly turbid waters, respectively. The estimated a(λ) and bb (λ) are utilized to obtain the diffuse attenuation coefficient Kd, followed by the Zsd calculations. Compared with 70 matchups of in situ measured Zsd values (0–6.5 m), the ZY1-02D image-derived Zsd achieved an R2 of 0.98, with an average unbiased relative error and root mean square error of 29.1% and 0.52 m, respectively. In addition, the proposed method can yield Zsd with higher accuracies than that of optimized empirical models. Therefore, the ZY1-02D AHSI imagery can retrieve reliable Zsd for both clear (> 3 m) and turbid waters (0–3.0 m), thereby serving as a useful satellite data source for monitoring the water clarity of large-scale inland water bodies.

Hyperspectral target detection can be described as locating targets of interest within a hyperspectral image based on prior information of targets. The complexity of actual scenes limits the performance of traditional statistical methods that rely on model assumptions, and traditional machine learning methods rely on mapping functions with limited complexity. To address these problems, we propose a Siamese transformer network for hyperspectral image target detection (STTD). The contribution of this article is threefold. First, we propose a novel method of constructing training samples using only the image itself and the limited prior information, which is suitable for target detection based on the Siamese network framework. Second, the Siamese network framework is utilized to solve the problem of similarity metric learning, i.e., make homogeneous features as close as possible and heterogeneous features as far as possible. Third, the most state-of-the-art network, transformer, is applied as the backbone of our proposed Siamese network to extract global features from spectra with long-range dependencies to achieve target detection. Furthermore, we make adaptive improvements to transformer for hyperspectral images. The proposed method shows its unique advantages in suppressing the background to a low level and highlighting the target with high probability. Experiments on five different datasets demonstrate the superiority of the proposed STTD as compared to the state-of-the-art.

Given the prior information of the target, hyperspectral target detection focuses on exploiting spectral differences to separate objects of interest from the background, which can be treated as information retrieval (IR) task in machine learning (ML). Most traditional detection methods work in the original feature space and rely heavily on specific assumptions, which cannot guarantee effective extraction of features for the target and background in hyperspectral images (HSIs). Mass estimation (ME) is a base modeling mechanism that has been proven to effectively solve problems in IR and is not restricted by specific assumptions. In this article, we propose a novel target detection method through ensemble-based IR with ME (EIRME). By directly deriving the ordering from a sample set to rank data points, ME provides a simple and straightforward ranking measure to ensure that points similar to the given target are far away from dissimilar points. For the estimation of mass distribution, the proposed method utilizes a tree-structured mapping to generate a feature space, in which the separability of the target and background is further improved. In particular, to break through the technical difficulty that the direct migration of IR methods with mass measure cannot specifically meet the high-precision requirements of target detection in HSIs, we develop a specialized measurement, topological mass, which innovatively combines the mass measure with tree topology to quantify the spectral difference for detection output. Moreover, the IR with ME based on parallel measurements through ensemble trees provides a robust solution with better generalization capacity and higher precision for hyperspectral target detection, facilitating practical applications. Experimental results on benchmark HSI datasets prove that the specialized measurement that we developed successfully overcomes the drawbacks of the direct migration of IR methods with ME and exhibits unique advantages. In addition, comparisons with the most classic and advanced detection algorithms demonstrate the superiority of the proposed method.

Recently, deep learning-based denoising methods for hyperspectral images (HSIs) have been comprehensively studied and achieved impressive performance because they can effectively extract complex and nonlinear image features. Compared with deep learning-based methods, the nonlocal similarity-based denoising methods are more suitable for images containing edges or regular textures. We propose a powerful HSI denoising method, termed NL-3DCNN, combining traditional machine learning and deep learning techniques. NL-3DCNN exploits the high spectral correlation of an HSI by using subspace representation and corresponding representation coefficients are termed eigenimages. The high spatial correlation in eigenimages is exploited by grouping nonlocal similar patches, which are denoised by a 3D convolutional neural network. The numerical and graphical denoising results of simulated and real data show that the proposed method is superior to state-of-the-art methods.

Due to the limitations of imaging systems, satellite hyperspectral imagery (HSI), which yields rich spectral information in many channels, often suffers from poor spatial resolution. HSI super-resolution (SR) refers to the fusion of high spatial resolution multispectral imagery (MSI) and low spatial resolution HSI to generate HSI that has both a high spatial and high spectral resolution. However, most existing SR methods assume that the two original images used are perfectly registered: in reality, nonrigid deformation areas can exist locally in the two images even if prior registration of the control points has been carried out. To address this problem, we propose a novel unsupervised spectral unmixing and image deformation correction network—NonRegSRNet—with multimodal and multitask learning that can be used for the joint registration of HSI and MSI and to produce SR imagery. More specifically, NonRegSRNet integrates the dense registration and SR tasks into a unified model that includes a triplet convolutional neural network. This allows these two tasks to complement each other so that better registration and SR results can be achieved. Furthermore, because the point spread function (PSF) and spectral response function (SRF) are often unavailable, two special convolutional layers are designed to adaptively learn the parameters of the PSF and SRF, which makes the proposed model more adaptable. Experimental results demonstrate that the proposed method has the ability to produce highly accurate and stable reconstructed images under complex nonrigid deformation conditions. (Code available athttps://github.com/saber-zero/NonRegSRNet)

Hyperspectral imaging measures the amount of electromagnetic energy across the instantaneous field of view at a very high resolution in hundreds or thousands of spectral channels. This enables objects to be detected and the identification of materials that have subtle differences between them. However, the increase in spectral resolution often means that there is a decrease in the number of photons received in each channel, which means that the noise linked to the image formation process is greater. This degradation limits the quality of the extracted information and its potential applications. Thus, denoising is a fundamental problem in hyperspectral image (HSI) processing. As images of natural scenes with highly correlated spectral channels, HSIs are characterized by a high level of self-similarity and can be well approximated by low-rank representations. These characteristics underlie the state-of-the-art methods used in HSI denoising. However, where there are rarely occurring pixel types, the denoising performance of these methods is not optimal, and the subsequent detection of these pixels may be compromised. To address these hurdles, in this article, we introduce RhyDe (Robust hyperspectral Denoising), a powerful HSI denoiser, which implements explicit low-rank representation, promotes self-similarity, and, by using a form of collaborative sparsity, preserves rare pixels. The denoising and detection effectiveness of the proposed robust HSI denoiser is illustrated using semireal and real data.

Over the past decades, enormous efforts have been made to improve the performance of linear or nonlinear mixing models for hyperspectral unmixing (HU), yet their ability to simultaneously generalize various spectral variabilities (SVs) and extract physically meaningful endmembers still remains limited due to the poor ability in data fitting and reconstruction and the sensitivity to various SVs. Inspired by the powerful learning ability of deep learning (DL), we attempt to develop a general DL approach for HU, by fully considering the properties of endmembers extracted from the hyperspectral imagery, called endmember-guided unmixing network (EGU-Net). Beyond the alone autoencoder-like architecture, EGU-Net is a two-stream Siamese deep network, which learns an additional network from the pure or nearly pure endmembers to correct the weights of another unmixing network by sharing network parameters and adding spectrally meaningful constraints (e.g., nonnegativity and sum-to-one) toward a more accurate and interpretable unmixing solution. Furthermore, the resulting general framework is not only limited to pixelwise spectral unmixing but also applicable to spatial information modeling with convolutional operators for spatial-spectral unmixing. Experimental results conducted on three different datasets with the ground truth of abundance maps corresponding to each material demonstrate the effectiveness and superiority of the EGU-Net over state-of-the-art unmixing algorithms. The codes will be available from the website: https://github.com/danfenghong/IEEE_TNNLS_EGU-Net.

Owing to the powerful ability in learning low-dimensional representations and reconstruction, autoencoders (AEs) have been successfully applied in hyperspectral unmixing (HU). However, AE-based unmixing architectures, to a great extent, need to be carefully designed in a manual fashion, leading to the bulk of costs in manpower and time. To unmix hyperspectral images more intelligently, we propose an AI-powered evolvable neural architecture search method for HU, EvoNAS for short, to optimally determine the network architecture by the means of the evolutionary algorithm instead of gradient-based or reinforcement learning-based rewards. In EvoNAS, a supernet with all candidate architectures is first trained to learn the unmixing mapping in a self-supervised manner. The optimal network is then constructed by evaluating unmixing results of different architectures in the supernet. EvoNAS is capable of saving tremendous computational cost, since it inherits the weights of the pre-trained supernet and avoids training from scratch during the search phase. Experimental results conducted on two real hyperspectral datasets verify the effectiveness and superiority of the EvoNAS and show the huge potential of the NAS for HU.

With the ever-growing availability of remote sensing (RS) data from either satellite or airborne sensors, simultaneous processing and analysis of multimodal data have been paid more and more attention by researchers in various RS-related applications. In this paper, we propose a multimodal convolutional neural network with an advanced cross-channel reconstruction module, called CCR-Net. As the name suggests, CCR-Net enables a more compact fusion of different RS data sources by the means of the reconstruction strategy across modalities that can mutually exchange information in a more effective way. Experiment are conducted on a widely-used dataset, including hyperspectral and Light Detection and Ranging (LiDAR) data, i.e., Houston2013, to verify the effectiveness and superiority of the proposed CCR - N et in comparison with several state-of-the-art baseline methods.

Over the past decades, numerous methods have been proposed to solve the linear or nonlinear mixing problems in hyperspectral unmixing (HU). The existence of spectral variabilities and nonlinearity limits, to a great extent, the unmixing ability of most traditional approaches, particularly in complex scenes. In recent years, deep learning (DL) has been garnering increasing attention in nonlinear HU owing to its powerful learning and fitting ability. However, the DL-based methods tend to generate trivial unmixing results due to the lack of considering physically meaningful endmember information. To this end, we propose a novel siamese network, called the deep half-siamese network (Deep HSNet), for HU by fully considering diverse endmember properties extracted using different endmember extraction algorithms. Moreover, the proposed Deep HSNet, beyond the previous autoencoder-like architecture, adopts another subnetwork to learn the endmember information effectively to guide the unmixing process in a reasonable and accurate way. The experimental results conducted on the synthetic and real hyperspectral data sets validate the effectiveness and superiority of the Deep HSNet over several state-of-the-art unmixing algorithms.

Subspace learning (SL) plays an essential role in hyperspectral image (HSI) classification since it can provide an effective solution to reduce the redundant information in the image pixels of HSIs. Previous works about SL aim to improve the accuracy of HSI recognition. Using a large number of labeled samples, related methods can train the parameters of the proposed solutions to obtain better representations of HSI pixels. However, the data instances may not be sufficient to learn a precise model for HSI classification in real applications. Moreover, it is well known that it takes much time, labor, and human expertise to label HSI images. To avoid the abovementioned problems, a novel SL method that includes the probability assumption called SL with the conditional random field (SLCRF) is developed. In SLCRF, the 3-D convolutional autoencoder (3DCAE) is first introduced to remove the redundant information in HSI pixels. Besides, the relationships are also constructed using spectral-spatial information among the adjacent pixels. Then, the conditional random field (CRF) framework can be constructed and further embedded into the HSI SL procedure with the semisupervised approach. Through the linearized alternating direction method termed LADMAP, the objective function of SLCRF is optimized using a defined iterative algorithm. The proposed method is comprehensively evaluated using the challenging public HSI data sets. We can achieve state-of-the-art performance using these HSI sets.

Super-resolution (SR) techniques play a crucial role in increasing the spatial resolution of remote sensing data and overcoming the physical limitations of the spaceborne imaging systems. Though the convolutional neural network (CNN)-based methods have obtained good performance, they show limited capacity when coping with large-scale super-resolving tasks. The more complicated spatial distribution of remote sensing data further increases the difficulty in reconstruction. This article develops a dense-sampling super-resolution network (DSSR) to explore the large-scale SR reconstruction of the remote sensing imageries. Specifically, a dense-sampling mechanism, which reuses an upscaler to upsample multiple low-dimension features, is presented to make the network jointly consider multilevel priors when performing reconstruction. A wide feature attention block (WAB), which incorporates the wide activation and attention mechanism, is introduced to enhance the representation ability of the network. In addition, a chain training strategy is proposed to optimize further the performance of the large-scale models by borrowing knowledge from the pretrained small-scale models. Extensive experiments demonstrate the effectiveness of the proposed methods and show that the DSSR outperforms the state-of-the-art models in both quantitative evaluation and visual quality.

Remotely sensed images, especially in urban areas, have highly complex spatial distribution, since the ground objects have diverse ranges of sizes and shapes. This largely increases the difficulty of super-resolution (SR) tasks. Current deep convolutional neural network (CNN)-based SR methods often show limited performance when coping with complicated images. This article develops a second-order multi-scale super-resolution network (SMSR) to explore reconstruction tasks for difficult cases. Specifically, we propose a single-path feature reuse which cleverly captures multi-scale feature information through aggregating the features learned at different depths of a single path. Further, we present a second-order learning mechanism, which double reuses small-difference and large-difference features at local and global levels, makes use of the learned multi-scale information at maximum. The proposed methods achieve multi-scale learning using small-size convolution only, resulting in a lightweight and high-performance SR network. Experimental results show the superiority of our SMSR over state-of-the-art methods in super-resolving complicated image patterns. The effectiveness of SMSR is also demonstrated through its support to object recognition task.

Extensive attention has been widely paid to enhance the spatial resolution of hyperspectral (HS) images with the aid of multispectral (MS) images in remote sensing. However, the ability in the fusion of HS and MS images remains to be improved, particularly in large-scale scenes, due to the limited acquisition of HS images. Alternatively, we super-resolve MS images in the spectral domain by the means of partially overlapped HS images, yielding a novel and promising topic: spectral superresolution (SSR) of MS imagery. This is challenging and less investigated task due to its high ill-posedness in inverse imaging. To this end, we develop a simple but effective method, called joint sparse and low-rank learning (J-SLoL), to spectrally enhance MS images by jointly learning low-rank HS-MS dictionary pairs from overlapped regions. J-SLoL infers and recovers the unknown HS signals over a larger coverage by sparse coding on the learned dictionary pair. Furthermore, we validate the SSR performance on three HS-MS data sets (two for classification and one for unmixing) in terms of reconstruction, classification, and unmixing by comparing with several existing state-of-the-art baselines, showing the effectiveness and superiority of the proposed J-SLoL algorithm. Furthermore, the codes and data sets will be available at https://github.com/danfenghong/IEEE_TGRS_J-SLoL, contributing to the remote sensing (RS) community.

Convolutional neural networks (CNNs) are becoming increasingly popular in modern remote sensing image processing tasks and exhibit outstanding capability for hyperspectral image (HSI) classification. However, for the existing CNN-based HSI-classification methods, most of them only consider single-scale feature extraction, which may neglect some important fine information and cannot guarantee to capture optimal spatial features. Moreover, many state-of-the-art methods have a huge number of network parameters needed to be tuned, which will cause high computational cost. To address the aforementioned two issues, a novel multiscale residual network (MSRN) is proposed for HSI classification. Specifically, the proposed MSRN introduces depthwise separable convolution (DSC) and replaces the ordinary depthwise convolution in DSC with mixed depthwise convolution (MDConv), which mixes up multiple kernel sizes in a single depthwise convolution operation. The DSC with mixed depthwise convolution (MDSConv) can not only explore features at different scales from each feature map but also greatly reduce learnable parameters in the network. In addition, a multiscale residual block (MRB) is designed by replacing the convolutional layer in an ordinary residual block with the MDSConv layer. The MRB is used as the major unit of the proposed MSRN. Furthermore, to enhance further the feature representation ability, the proposed network adds a high-level shortcut connection (HSC) on the cascaded two MRBs to aggregate lower level features and higher level features. Experimental results on three benchmark HSIs demonstrate the superiority of the proposed MSRN method over several state-of-the-art methods.

Classification and identification of the materials lying over or beneath the earth's surface have long been a fundamental but challenging research topic in geoscience and remote sensing (RS), and have garnered a growing concern owing to the recent advancements of deep learning techniques. Although deep networks have been successfully applied in single-modality-dominated classification tasks, yet their performance inevitably meets the bottleneck in complex scenes that need to be finely classified, due to the limitation of information diversity. In this work, we provide a baseline solution to the aforementioned difficulty by developing a general multimodal deep learning (MDL) framework. In particular, we also investigate a special case of multi-modality learning (MML)-cross-modality learning (CML) that exists widely in RS image classification applications. By focusing on “what,” “where,” and “how” to fuse, we show different fusion strategies as well as how to train deep networks and build the network architecture. Specifically, five fusion architectures are introduced and developed, further being unified in our MDL framework. More significantly, our framework is not only limited to pixel-wise classification tasks but also applicable to spatial information modeling with convolutional neural networks (CNNs). To validate the effectiveness and superiority of the MDL framework, extensive experiments related to the settings of MML and CML are conducted on two different multimodal RS data sets. Furthermore, the codes and data sets will be available at https://github.com/danfenghong/IEEE_TGRS_MDL-RS, contributing to the RS community.

Convolutional neural networks (CNNs) have been attracting increasing attention in hyperspectral (HS) image classification due to their ability to capture spatial-spectral feature representations. Nevertheless, their ability in modeling relations between the samples remains limited. Beyond the limitations of grid sampling, graph convolutional networks (GCNs) have been recently proposed and successfully applied in irregular (or nongrid) data representation and analysis. In this article, we thoroughly investigate CNNs and GCNs (qualitatively and quantitatively) in terms of HS image classification. Due to the construction of the adjacency matrix on all the data, traditional GCNs usually suffer from a huge computational cost, particularly in large-scale remote sensing (RS) problems. To this end, we develop a new minibatch GCN (called miniGCN hereinafter), which allows to train large-scale GCNs in a minibatch fashion. More significantly, our miniGCN is capable of inferring out-of-sample data without retraining networks and improving classification performance. Furthermore, as CNNs and GCNs can extract different types of HS features, an intuitive solution to break the performance bottleneck of a single model is to fuse them. Since miniGCNs can perform batchwise network training (enabling the combination of CNNs and GCNs), we explore three fusion strategies: additive fusion, elementwise multiplicative fusion, and concatenation fusion to measure the obtained performance gain. Extensive experiments, conducted on three HS data sets, demonstrate the advantages of miniGCNs over GCNs and the superiority of the tested fusion strategies with regard to the single CNN or GCN models. The codes of this work will be available at https://github.com/danfenghong/IEEE_TGRS_GCN for the sake of reproducibility.

Target detection aims to locate targets of interest within a specific scene. The traditional model-driven detectors based on signal processing have proved to be very effective. However, the detection performance of such traditional methods relies heavily on the model assumption, which is limited by the discrepancy with real hyperspectral images (HSIs) data. In this article, a target detection method through tree-structured encoding (TD-TSE) for HSIs is proposed. Instead of modeling the target and the background to extract valid features, we construct a binary tree based on the features of the data itself and segment the HSI to improve the separability of the target and the background. For the purpose of highlighting the target and suppressing the background, a novel measurement of separation, distance on tree, is calculated via binary encoding based on the constructed tree structure, and the detection output can be obtained according to such distance. To further reduce the generalization error resulting from random subsampling, the statistical average of the distances on multiple independent trees is estimated to improve the robustness of TD-TSE. The proposed method is not constrained by any model assumptions, which is fundamentally different from the most widely used hyperspectral target detectors in the field of signal processing. Moreover, the construction of binary trees without any labeled samples and the linear complexity of the proposed method make it highly practical for the hyperspectral data in real scenes. Extensive experiments on three benchmark HSI data sets demonstrate the effectiveness of the proposed TD-TSE for hyperspectral target detection.

Due to the limitations of hyperspectral imaging systems, hyperspectral imagery (HSI) often suffers from poor spatial resolution, thus hampering many applications of the imagery. Hyperspectral super resolution refers to fusing HSI and MSI to generate an image with both high spatial and high spectral resolutions. Recently, several new methods have been proposed to solve this fusion problem, and most of these methods assume that the prior information of the point spread function (PSF) and spectral response function (SRF) are known. However, in practice, this information is often limited or unavailable. In this work, an unsupervised deep learning-based fusion method-HyCoNet-that can solve the problems in HSI-MSI fusion without the prior PSF and SRF information is proposed. HyCoNet consists of three coupled autoencoder nets in which the HSI and MSI are unmixed into endmembers and abundances based on the linear unmixing model. Two special convolutional layers are designed to act as a bridge that coordinates with the three autoencoder nets, and the PSF and SRF parameters are learned adaptively in the two convolution layers during the training process. Furthermore, driven by the joint loss function, the proposed method is straightforward and easily implemented in an end-to-end training manner. The experiments performed in the study demonstrate that the proposed method performs well and produces robust results for different data sets and arbitrary PSFs and SRFs.

Collaborative Representation Detection (CRD) is a very effective anomaly detection method, which is directly based on the concept that pixel under test (PUT) can be approximately linear represented by its spatial adjacent background pixels. If the adjacent background pixels are contaminated, the approximate value of PUT linearly represented by the surrounding pixels is inaccurate. In this work, an improved method for anomaly detection in hyperspectral imagery is proposed based on CRD. In our proposed method, the least squares technique first is adopted to obtain the preliminary linear representation coefficient, which is positively correlated with its contribution to PUT. Then, the purified background pixels are obtained according to the numerical value of the representation coefficient. Generally, the anomaly pixels are usually different from the background pixels, so saliency weight is imposed on the test pixel to make full use of the spatial information of inner window pixels around the test pixel. Extensive experiments for real hyperspectral datasets show that the proposed method outperforms the CRD method and other traditional detection methods.

Hyperspectral images (HSIs), featured by high spectral resolution over a wide range of electromagnetic spectra, have been widely used to characterize materials with subtle differences in the spectral domain. However, a large number of bands and an insufficient number of sample pixels for each class are challenging for traditional machine learning-based classifiers. As alternative tools for feature extraction, neural networks have received extensive attention. This letter proposes to combine t-distributed stochastic neighbor embedding (t-SNE) with a convolutional neural network (CNN) for HSI classification. Our framework is designed to automatically capture the potential assembly features, which are extracted from both the dimension-reduced CNN (DR-CNN) and the multiscale-CNN. Experimental results show that the proposed classification framework outperforms several state-of-the-art techniques for three real data sets.

Multisensor fusion is of great importance in Earth observation related applications. For instance, hyperspectral images (HSIs) provide wealthy spectral information while light detection and ranging (LiDAR) data provide elevation information, and using HSI and LiDAR data together can achieve better classification performance. In this paper, an unsupervised feature extraction framework, named as patch-to-patch convolutional neural network (PToP CNN), is proposed for collaborative classification of hyperspectral and LiDAR data. More specific, a three-tower PToP mapping is first developed to seek an accurate representation from HSI to LiDAR data, aiming at merging multiscale features between two different sources. Then, by integrating hidden layers of the designed PToP CNN, extracted features are expected to possess deeply fused characteristics. Accordingly, features from different hidden layers are concatenated into a stacked vector and fed into three fully connected layers. To verify the effectiveness of the proposed classification framework, experiments are executed on two benchmark remote sensing data sets. The experimental results demonstrate that the proposed method provides superior performance when compared with some state-of-the-art classifiers, such as two-branch CNN and context CNN.

Classification is an important application of hyperspectral image (HSI). However, it is also a challenging research topic due to the spatial variability of spectral signature and limited training samples. To address these problems, a novel unsupervised feature learning method called latent relationship guided the stacked sparse autoencoder (LRSSAE) is developed in this article, which can effectively exploit the latent relationship under feature space to improve the ability of feature learning. Moreover, the superpixels constraint is employed on the feature representation to avoid the “salt-and-pepper” problem, and it is enforced on the latent relationship to enhance the latent relationship learning additionally. In LRSSAE, combining the stacked sparse autoencoder (SSAE) with the graph regularizations of latent relationship in each hidden layer and the superpixel constraints in the top layer, we extract feature representation in an unsupervised manner. And then, we present a customized iterative algorithm to optimize the LRSSAE. We evaluate the proposed method on three widely used HSI data sets comprehensively. The results demonstrate that our method achieves promising classification performance on these data sets and obtains improvements of 5.06%, 5.77%, and 2.11% in overall accuracy compared to the best SSAE method.

Spectral-spatial framework has been widely applied for hyperspectral image classification task. Some well-established models, such as group sparse representation (GSR), have gained a certain advance but still mainly focus on the usage of local spatial similarity and neglect the nonlocal spatial information. Recently, nonlocal self-similarity (NLSS) has been exploited to support the spatial coherence tasks. However, current NLSS-based methods are biased toward the direct use of nonlocal spatial information as a whole, while the underlying spectral information is not well exploited. In this article, we proposed a novel method to exploit local spectral similarity through nonlocal spatial similarity, with the integration of local spatial consistency in a single framework. Specifically, the proposed approach first exploits the NLSS by searching the nonoverlapped similar patches in defined scopes. Then, spectral similarity is determined locally within the found patches. After that, the found similar data and the original data are fused in a designed pattern. Finally, the GSR-based classifier (GSRC) is applied to process the fused data characterized by the manifold learning algorithm. The experimental results based on three real hyperspectral data sets demonstrate the efficiency of the proposed method, with improvements over the other related nonlocal or local similarity-based methods.

Early detection of banana disease can limit the spread of disease, as well as reduce the treatment costs. However, the disease symptoms are so unapparent in the earlier stage that makes the labeled samples acquisition difficult and expensive. Meanwhile, it is much easier to obtain labeled samples at the late stage where the disease symptoms are obvious. In this paper, we exploit machine learning methods to use labeled samples from the late stage to train the model, then detect the banana disease in the earlier stage. Morphological openings and closings are utilized to extract the spectral-spatial features from banana leaves at both earlier and late stages, initial experimental results demonstrate significant improvements over using only spectral information.

The land-use map is an important data that can reflect the use and transformation of human land, and can provide valuable reference for land-use planning. For the traditional image classification method, producing a high spatial resolution (HSR), land-use map in large-scale is a big project that requires a lot of human labor, time, and financial expenditure. The rise of the deep learning technique provides a new solution to the problems above. This paper proposes a fast and precise method that can achieve large-scale land-use classification based on deep convolutional neural network (DCNN). In this paper, we optimize the data tiling method and the structure of DCNN for the multi-channel data and the splicing edge effect, which are unique to remote sensing deep learning, and improve the accuracy of land-use classification. We apply our improved methods in the Guangdong Province of China using GF-1 images, and achieve the land-use classification accuracy of 81.52%. It takes only 13 hours to complete the work, which will take several months for human labor.

Spectral unmixing (SU) is a useful tool for hyperspectral remote sensing image analysis. However, due to the interference of spectral variance and non‐linearity caused by photon multiple‐scattering, the result might be an inaccuracy. In addition, the unmixing performance of typically relies on the prior knowledge of endmembers. Although many classical endmember extraction algorithms have been presented, it is hard to obtain accurate endmembers in practical applications. This study presents a bilinear normal mixing model named as BNMM to tackle these issues. In fact, BNMM employs the polynomial post‐non‐linear mixing model to alleviate the effect of non‐linearity and uses a normal distribution model to reduce the influence of endmembers variability. Based on the BNMM, the authors develop a Hamiltonian Monte Carlo algorithm for SU. The experimental results demonstrate that the proposed algorithm outperforms other classical unmixing algorithms in the case of simulated and benchmark datasets.

Large-scale Landsat image classification is essential for the production of land cover maps. The rise of convolutional neural networks (CNNs) provides a new idea for the implementation of Landsat image classification. However, pixels in Landsat images have higher uncertainty compared with high-resolution images due to its 30-m spatial resolution. In addition, the current deep learning methods tend to lose detailed information such as boundaries along with the stacking of convolutional and pooling layers. To solve these problems, we propose a new method called entropy and MRF model (EMM)-CNN based on Pyramid Scene Parsing Network. The EMM-CNN uses entropy to decrease the uncertainty of pixels. Then, the Markov random filed (MRF) model is employed to construct the connections between neighboring pixels and defined a prior distribution to prevent the cross entropy from sacrificing detailed information for the overall accuracy. Finally, transfer learning based on the pretrained ImageNet is introduced to overcome the shortage of training samples and boost the speed of the training process. Experimental results demonstrate that the proposed EMM-CNN is able to obtain classification results with fine structure by decreasing the uncertainty and retaining detailed information of the detected image.

Since the 1960s, remote sensing (as an innovative, comprehensive, and interdisciplinary academic area) has been adopted in a wide range of disciplines related to Earth observation, including hydrology, ecology, oceanography, glaciology, geology, military, intelligence, business, economy, and planning [1]-[3]. The constant development of the remote sensing image acquisition technology now allows for the collection of a wide variety of images with different characteristics and resolutions, obtained by remote sensing instruments mounted on spacecraft or aircraft platforms. These images record some type of signal or energy measured from the Earth's surface, which depends on the type of sensor used.

Remote sensing has evolved into a multidisciplinary field involving many different areas such as sensor technology, computing, and advanced applications. Information extraction now plays a fundamental role in the exploitation of the massive amount of data collected by earth observation instruments. In this Point of View, the authors analyze the evolution of this field, identifying three main phases in its development. The first period, which was marked by advances in digital signal processing, led to a significant development of statistical processing methods. The second phase was based on advances in physical models and brought an era of quantitative remote sensing which lasted until the first decade of this century. In the third and current period, information extraction techniques are gradually adopting advanced artificial intelligence models in an effort to cope with the tremendous increase in data volume. This article describes some of these recent advances and addresses challenges caused by the 4Vs (volume, velocity, variety, and veracity) of big data. Finally, the authors offer insight into future directions in this multidisciplinary field.

The performance of hyperspectral image (HSI) classification relies on the pixel information obtained from hundreds of contiguous and narrow spectral bands. Existing approaches, however, are limited to exploit an appropriate latent subspace for data representation within the pixel-level or superpixel-level. To utilize spectral information and spatial correlation among pixels in HSI and avoid the “salt-and-pepper” problem generated in the pixel-based HSI classification, a novel pixel-level and superpixel-level aware subspace learning method called PSASL is developed. The PSASL constructs the subspace learning framework based on the reconstruction independent component analysis algorithm. The spectral–spatial graph regularization and label space regularization are developed as the pixel-level constraints. To avoid the “salt-and-pepper” problem generated in the pixel-based classification methods, superpixel-level constraints are introduced for integrating the data representations defined in the subspace and class probabilities of the pixels in the same superpixel. The subspace learning and the pixel-level regularization are combined with the superpixel-level regularization to form a unified objective function. The solution to the objective function is efficiently achieved by employing a customized iterative algorithm, and it converges very fast. A discriminative data representation and a universal multiclass classifier are learned simultaneously. We test the PSASL on three widely used HSI data sets. Experimental results demonstrate the superior performance of our method over many recently proposed methods in HSI classification.

Urban black and odorous water (BOW) is a serious global environmental problem. Since these waters are often narrow rivers or small ponds, the detection of BOW waters using traditional satellite data and algorithms is limited both by a lack of spatial resolution and by imperfect retrieval algorithms. In this paper, we used the Chinese high-resolution remote sensing satellite Gaofen-2 (GF-2, 0.8 m). The atmospheric correction showed that the mean absolute percentage error of the derived remote sensing reflectance (Rrs) in visible bands is 25.19%. We first measured Rrsspectra of two classes of BOW [BOW with high concentrations of iron (II) sulfide, i.e., BOW1 and BOW with high concentrations of total suspended matter, i.e., BOW2] and ordinary water in Shenyang. Then, in situ Rrsdata were converted into Rrs corresponding to the wide GF-2 bands using the spectral response functions. We used the converted Rrsdata to calculate several band combinations, including the baseline height, [Rrs(green) - Rrs(red))/(Rrs(green) + Rrs(red)], and the color purity on a Commission Internationale de L'Eclairage (CIE) chromaticity diagram. The color purity was found to be the best index to extract BOW from ordinary water. Then, Rrs(645) was applied to categorize BOW into BOW1 and BOW2. We applied the algorithm to two synchronous GF-2 images. The recognition accuracy of BOW2 and ordinary water are both 100%. The extracted river water type near Weishanhu Road was BOW1, which agreed well with ground truth. The algorithm was further applied to other GF-2 data for Shenyang and Beijing.

The challenges in hyperspectral image (HSI) classification lie in the existence of noisy spectral information and lack of contextual information among pixels. Considering the three different levels in HSIs, i.e., subpixel, pixel, and superpixel, offer complementary information, we develop a novel HSI feature learning network (HSINet) to learn consistent features by self-supervision for HSI classification. HSINet contains a three-layer deep neural network and a multifeature convolutional neural network. It automatically extracts the features such as spatial, spectral, color, and boundary as well as context information. To boost the performance of self-supervised feature learning with the likelihood maximization, the conditional random field (CRF) framework is embedded into HSINet. The potential terms of unary, pairwise, and higher order in CRF are constructed by the corresponding subpixel, pixel, and superpixel. Furthermore, the feedback information derived from these terms are also fused into the different-level feature learning process, which makes the HSINet-CRF be a trainable end-to-end deep learning model with the back-propagation algorithm. Comprehensive evaluations are performed on three widely used HSI data sets and our method outperforms the state-of-the-art methods.

Ship detection is an important and challenging topic in remote sensing applications. In current literatures, sea-land segmentation is generally requested before ship detection. This makes the implementation of the methods highly complicated. Therefore, based on Faster R-CNN, this paper proposes a ship detection method for large-scale images, which does not need sea-land segmentation as preprocessing step and can detect ships directly from complicated background including sea and land. We use large-scale images consisting of GF-1 and GF-2 satellite images to test our network. Experimental results prove that the proposed method plays a role in removing the interference of objects on land.

A framework based on color feature extraction of social media photos and correlation analysis with air quality parameters is proposed to monitor environmental change. More specifically, photos of the Beijing Olympic Park from Panoramio website have been analyzed as a case study. The aerosol optical depth data at 500 nm wavelength (AOD 500) obtained from sun-photometer observation network station has been used as reference. Results show a proof of concept that social media photos have an interesting potential for air pollution estimate and remote sensing parameter validation with a low cost.

Spectral-spatial classification has been widely exploited for hyperspectral imagery. However, current methods either focus on local spatial similarity or global nonlocal self-similarity (NLSS). In this paper, we propose novel methods to couple both global spatial similarity and local spectral similarity together in a single framework. In particular, our approaches exploit global spatial similarity by searching non-overlap nonlocal patches, whereas spectral similarity is determined locally within the found patches. Experimental results on two real hyperspectral data sets demonstrate the efficiency of the proposed methods, with 5%-7% (overall classification accuracy) improvements over approaches that only consider either global or local similarity.

In this letter, a new method for higher order nonlinear hyperspectral unmixing is introduced. The proposed scheme relies on the harmonic description of the endmembers contributions to characterize the interactions among the materials showing up in the given scenes. Moreover, it aims at directly estimating the probability of occurrence of each material in the images, so to provide an accurate quantification of the endmembers also in complex scenarios. Experimental results carried out on synthetic and real data sets show that the proposed method is able to obtain good unmixing performance when compared to other state-of-the-art architectures.

Low-rank representation (LRR) can construct the relationships among pixels for hyperspectral image (HSI) classification with a given dictionary and a noise term. However, the accuracy of HSI classification based on LRR methods is degraded with the redundant and noise information existed in pixels. The neglect of semantic information around pixels in the LRR methods may cause “salt-and-pepper” problem in HSI classification. To avoid the aforementioned problems, a novel self-supervised low-rank representation method called SSLRR is developed. In SSLRR, the LRR and spectral–spatial graph regularization are developed as the pixel-level constraints to remove the redundant and noise information in HSIs. Superpixel constraints including data structure and relationship construction are further utilized to provide supervised feedback information to the subspace learning to avoid the “salt-and-pepper” problem generated in the pixel-based classification methods, and simultaneously enhance the performance of LRR. The pixel-level and superpixel-level regularizations are explicitly integrated into a unified objective function for LRR. By means of the linearized alternating direction method with adaptive penalty, the solution to the objective function is achieved by employing a customized iterative algorithm. We perform comprehensive evaluation of the proposed method on three challenging public HSI data sets. We obtain new state-of-the-art performance on these data sets, and achieve improvements of 44.3%, 13.4%, and 30.1% in overall accuracy compared to the best LRR method.

As a list of remotely sensed data sources is available, how to efficiently exploit useful information from multisource data for better Earth observation becomes an interesting but challenging problem. In this paper, the classification fusion of hyperspectral imagery (HSI) and data from other multiple sensors, such as light detection and ranging (LiDAR) data, is investigated with the state-of-the-art deep learning, named the two-branch convolution neural network (CNN). More specific, a two-tunnel CNN framework is first developed to extract spectral-spatial features from HSI; besides, the CNN with cascade block is designed for feature extraction from LiDAR or high-resolution visual image. In the feature fusion stage, the spatial and spectral features of HSI are first integrated in a dual-tunnel branch, and then combined with other data features extracted from a cascade network. Experimental results based on several multisource data demonstrate the proposed two-branch CNN that can achieve more excellent classification performance than some existing methods.

This paper analyzes four practical change detection algorithms with Landsat-8 data on landslide mapping in the Kaikoura earthquake happened on November 14, 2016. Eleven band groups built from seven reflective bands of Landsat-8 data were used in the experiment. Total 21 change detection results based on various combinations of band groups and algorithms were obtained. The results were qualitatively and quantitatively analyzed based on manual interpretation and the ROC curve. It shows that all results have high false alarm rates and the accuracy varies for different combinations. Further analysis indicates that false alarms are those being easily affected by phenology factors and human activities, such as cropland, river, snow, and shadow etc. The high false alarm rate indicated by the ROC curve is additionally due to small but hard to avoid errors in the preparation of ground truths. Furthermore, change vector analysis offers plenty of information but does not directly enhance landslide. Based on above analysis, several possible ways to improve the change detection based landslide monitoring method are given at the end of the paper.

The added value of multiple data sources on tree species mapping has been widely analyzed. In particular, fusion of hyperspectral (HS) and LiDAR sensors for forest applications is a very hot topic. In this paper, we exploit the use of multi-scale features to fuse HS and LiDAR data for tree species mapping. Hyperspectral data is obtained from the APEX sensor with 286 spectral bands. LiDAR data has been acquired with a TopoSys sensor Harrier 56 at full waveform. We generate multi-scale features on both HS and LiDAR data, by considering the diameter and the height layer of different tree species. Experimental results on a forested area in Belgium demonstrate the effectiveness of using multi-scale features for fusion of HS image and LiDAR data both visually and quantitatively.

Atmospheric absorption bands centered at 2.7 micron are used in missile warning systems for target detection and tracking. Since image simulation is an important tool for sensor development, relevant research should be conducted for sensors using the 2.7 micron absorption bands. In this paper, we propose a surface reflectance image simulation method for this absorption bands, to prepare surface input images for corresponding end-to-end simulation. Considering that surface reflectance is related to the surface material type, reflectance images in the absorption bands are simulated from abundance inversion and spectral mixing. Specifically, spectra in spectral libraries are used as endmembers for data source images, and abundance inversion are conducted to acquire abundance maps of these types of materials. Then, spectral mixing is conducted to generate reflectance images with reflectance in the absorption bands of endmembers and abundance maps. Accuracy analysis shows this method is feasible and with good accuracy.

This paper proposes a new supervised hyperspectral nonlinear unmixing method based on normalization. The main contribution is presented by reducing the overfitting of model and taking account to spatial correlation, using the normalization. The l2-norm constraints of abundance and nonlinear coefficient are added to the P-Linear spectral mixing model. Moreover different positive parameters are given to control the trade-off between regularity and fitting. Finally, the problem can be expressed as a convex optimization problem, minimizing the cost function and the global optimum can be determined. The proposed method, abbreviated as NPLA (Normalized P-Linear Algorithm), is validated using hyperspectral synthetic and real datasets. The results indicate that the proposed method exhibits better performance on RMSE of abundance, reconstruction error and computed cost compared to other related classical hyperspectral nonlinear unmixing methods.

Hyperspectral images (HSIs) cover hundreds of narrow spectral bands, thus yielding high spectral resolution, enabling precise identification of different materials. However, the existence of dead pixels in the light sensors produces a number of irrelevant measurements, which may compromise the usefulness of HSIs. In this paper, a new hyperspectral inpainting method, named HyInpaint, is proposed. The original HSI is represented on a low dimensional subspace and its estimation is formalized with respect to the subspace representation coefficients on a given basis. The coefficients are estimated by minimizing an objective function which, in addition to the data term, contains a regularizer based on the Criminisi's inpainting method. The optimization is carried out by an instance of the alternating direction method of multipliers (ADMM), adopting the plug-and-play methodology. The effectiveness of the proposed HyInpaint approach is illustrated on Tiangong-1 hyperspectral visible near infrared (VNIR) wavebands data.

This letter proposes to integrate the locality sensitive discriminant analysis (LSDA) with the group sparse representation (GSR) for a hyperspectral imagery classification. The LSDA is to project the data set to a lower-dimensional subspace to preserve local manifold structure and discriminant information, while the GSR is to encode the projected testing set as a sparse linear combination of group-structured training samples for classification. The proposed approach, denoted as LSDA-GSR classifier (GSRC), is evaluated using two real hyperspectral data sets. Experimental results demonstrate that it can provide considerable improvement to the original counterparts, i.e., SRC and GSRC, with a relatively low computational cost.

This letter introduces a new spectral-spatial classification method for hyperspectral images. A multiscale superpixel segmentation is first used to model the distribution of classes based on spatial information. In this context, the original hyperspectral image is integrated with segmentation maps via a feature fusion process in different scales such that the pixel-level data can be represented by multiscale superpixel-level (MSP) data sets. Then, a subspace-based support vector machine (SVMsub) is adopted to obtain the classification maps with multiscale inputs. Finally, the classification result is achieved via a decision fusion process. The resulting method, called MSP-SVMsub, makes use of the spatial and spectral coherences, and contributes to better feature characterization. Experimental results based on two real hyperspectral data sets indicate that the MSP-SVMsub exhibits good performance compared with other related methods.

The convergence of remote sensing technologies with social media, coupled with advances in other location-aware technologies such as WiFi and smartphones, is moving us on a fast track to a situation in which we can readily know, at any time, where everybody and everything are located on the surface of the Earth, and to exploit the power of social media in different contexts. Remote sensing technology involves the use of systems and algorithms to record information about the surface of the Earth from a remote location [1]. Although reliable as a data source, remote sensing data may not always be available. However, these data can be complemented by other sources of data, such as geographic information systems (GIS) and social media [2], in order to address time-critical applications. For instance, relating publicly available social media information with remote sensing or GIS data can lead to a more efficient management of emergency response (which refers to applications in which real/near-real-time response is needed, such as natural disasters). Social media are now playing a more relevant role in our daily lives and provide a unique opportunity to gain valuable insight on information flow and social networking within the society. As a result, the integration of social media data with other consolidated technologies such as remote sensing or GIS is of great importance.

The rapid development of social media data and the associated growth in volume, velocity, and variety has fostered the idea of using these data to guide traditional remote sensing image retrieval and information extraction tasks. Although important progress has been made in recent years in harvesting spatial and temporal data from social media, the exploitation of these data for decision making still needs further investigation, particularly in the context of its integration with remote sensing and geographic information systems. In this paper, we first discuss the relation between localization techniques and spatial technologies, pointing out their similarities and differences. Then, we provide a discussion on location analysis of social media data, and the fusion of multiple data sources, with specific attention to the integration of social media content (including localization) with remote sensing-based spatial technologies. Next, we provide specific examples addressing the use of social media data to perform information extraction from large remote sensing data repositories. Although significant possibilities for the integration of localization and spatial technologies can be seen in the examples provided, our survey suggests that the convergence of remote sensing and social media data will continue to deeply transform these technologies.

The significant development of social media over the past decade has been complemented by the rise of spatial technologies to provide new mapping mechanisms that allow users engage with online information services and also with each other in an unprecedented way. Users of these technologies now provide a comprehensive geosocial overlay of the physical environment of the planet.

A large number of world's population lives within coastal areas. These environmentally sensitive zones bear both natural pressures such as erosion, accretion and natural disasters and anthropogenic impacts such as urban growth, resource exploration and pollution. The decay of coastal ecosystem has an interactive influence on surrounding residents. Monitoring the change of coastlines could help the government and coastal managers make sounds policies. This paper presents a track of coastline changes at Tampa Bay (TB) and Xiangshan Harbor (XH) during the last 30 years. There are several methods used to obtain coastlines. One popular way is waterline extraction method using normalized difference water index (NDWI). Several studies recommended on-screen digitizing technique to delineate coastline based on classified NDWI images. However, in this study, a GIS technique, converting raster to polyline, was applied to capture coastlines to reduce laboring work. The preliminary analysis results indicate that the coastlines in TB only had slight changes during these 30 years while the coastlines in XH suffered severe erosions and anthropogenic impacts. In recent decades, TB managements put lots of efforts on ecosystem protection, such as implementing the Tampa Bay Estuary Program to keep a healthy and stable coastal ecosystem. Therefore, the government of XH needs to pay more attention to ecosystem protection during the process of urbanization and to learn the advanced experience and policies of protecting TB coastlines.

This paper proposes a new supervised classification method for hyperspectral images combining the spectral and spatial information. The main contribution is presented by combining subspace-based support vector machine (SVMsub) and Markov random field (MRF). A SVM classifier integrated with a subspace projection is first used to model the posterior distributions of the classes from the spectral information. Then, the spatial information is modeled by a multilevel MRF. Finally, the maximum posterior probability classification is computed via the α-Expansion graph-cut-based optimization algorithm. The proposed method, abbreviated as SVMsub-MRF, is validated using a real typical hyperspectral data set. The results indicate that the proposed method exhibits better performance on accuracy and computational cost compared to other related classical hyperspectral image classification methods.

The kernel minimum noise fraction (KMNF) method is a nonlinear dimensionality reduction method for hyperspectral images. KMNF can transform the original data into higher dimensional feature space by using nonlinear transformation project. The key issue of KMNF is the noise estimation. The original KMNF performs noises estimation based on spatial neighborhood information. However, the spatial resolution of hyperspectral images always is not very high, and the images usually have seriously mixed pixels. Therefore, the spatial information is not enough to precisely estimate noise for KMNF. Differently, we adopt spectral correlation information which is more stable to estimate noise for KMNF. The proposed method is named the optimized KMNF method (OKMNF). Experimental results using real hyperspectral dataset demonstrate that OKMNF has much better performance than KMNF.

Endmember variability is receiving growing attention in the hyperspectral image (HSI) unmixing field. As an extension of linear mixing model (LMM), normal compositional model (NCM) assumes that the pixels of the HSI are linear combinations of random endmembers (as opposed to deterministic for the LMM). NCM explains spectral differences between the observed pixels and endmembers as endmember mixtures and endmember variances, the characteristic of which makes it possible to incorporate the endmember spectral variability in the unmixing process. But the tricky issue for using NCM is the estimation of endmember variances inhering in materials. This letter presents a new approach, termed region-based stochastic expectation maximization, to learn endmember variances from spatial information. The idea is assuming that significant homogeneous regions (composed of similar materials or similar mixture) exist in the HSI, such regions usually give visual indication that spatial-based spectral variability really exists in hyperspectral data. As modeled in NCM, spectral variances in homogeneous region can be approximately linear represented by endmember variances. Hence, given region-based spectral variances, we are able to learn endmember variances. In experiments with simulated data and Moffett field data, the proposed approach competes with other unmixing methods considering endmember variability, with better endmember variance estimates.

Numerous observations and modeling results have shown that there is noticeable directional variation in the solar-induced chlorophyll fluorescence (SIF), and this has not been well investigated. In this paper, 16 multiangular spectral observations were carried out on winter wheat to assess the bidirectional SIF emission. First, the bidirectional SIF emission was retrieved from the spectral measurements made by a high-performance QE Pro spectrometer and an automatic multiangle observation system using the 3FLD algorithm. The bidirectional shape of the SIF emission was found to be similar to that of the canopy reflectance in the solar principal plane, with a mean correlation coefficient of 0.94 and 0.97 at the O2-B and O2-A bands, respectively. The modified Rahman-Pinty-Verstraete (MRPV) model, a semiempirical bidirectional reflectance distribution function (BRDF) model, was then employed to describe the bidirectional variation in the SIF and reflectance with a mean root-mean-square-error value of 0.036 and 0.041 mW m-2sr-1nm-1for the SIF at the O2-B and O2-A bands, respectively. Finally, both the bidirectional reflectance and SIF were BRDF corrected to nadir using the MRPV model. Most of the directional variation was successfully corrected by this method-the mean correction ratios were 87% and 81% for the reflectance at the O2-B and O2-A bands and 84% and 72% for the SIF at the O2-B and O2-A bands, respectively. Therefore, the SIF emission cannot be regarded as isotropic, and the high similarity between the bidirectional SIF and reflectance, together with the BRDF correction results, indicates that the bidirectional SIF emission can be adjusted using either the BRDF reflectance models or prior knowledge.

Mid-infrared atmospheric absorption bands centered at 4.3 μm are applied in target detection. Image simulation, as an important tool for the adaption and optimization of a sensor, ought to be conducted for the development of instruments using this spectral range. In this paper, a top-of-atmosphere (TOA) image simulation method is proposed, and this method is tested on two bands of the sensor SPIRIT III (band S1: 4.21-4.37 μm, S2: 4.23-4.47 μm). Band translation models are established for the generation of surface emissivity images, and an analytic radiative transfer model is modified and utilized to simulate TOA radiance fast and accurately. Accuracy analysis of the proposed method shows relative errors of within ±6% and ±1% in simulated surface emissivity and TOA radiance, respectively. Moreover, image simulation is often used for band selection in the sensor design stage. To illustrate how our proposed simulation method was applied in band selection, we used simulated TOA radiance of bands S1 and S2 as an example and compared their possibility of false alarms caused by high-temperature objects. Experimental results show that high-temperature objects are more unlikely to become false alarms on band-S1 images. Therefore, the spectral range of S1 is a better option for target detection application than S2. This TOA simulation method can be also applied in band selection among other 4.3-μm absorption bandwidths, as was done in this paper.

Hyperspectral image classification has been a very active area of research in recent years. It faces challenges related with the high dimensionality of the data and the limited availability of training samples. In order to address these issues, subspace-based approaches have been developed to reduce the dimensionality of the input space in order to better exploit the (limited) training samples available. An example of this strategy is a recently developed subspace-projection-based multinomial logistic regression technique able to characterize mixed pixels, which are also an important concern in the analysis of hyperspectral data. In this letter, we extend the subspace-projection-based concept to support vector machines (SVMs), a very popular technique for remote sensing image classification. For that purpose, we construct the SVM nonlinear functions using the subspaces associated to each class. The resulting approach, called SVMsub, is experimentally validated using a real hyperspectral data set collected using the National Aeronautics and Space Administration's Airborne Visible/Infrared Imaging Spectrometer. The obtained results indicate that the proposed algorithm exhibits good performance in the presence of very limited training samples.

Imaging spectroscopic technique has been used for the mineral and rock geological mapping and alteration information extraction successfully with many reasonable results, but it is mainly used in arid and semi-arid land with sparse vegetation covering. In the case of the dense vegetation covering, the outcrop of the altered rocks is small and distributes sparsely, the altered rocks is difficult to be identified directly. The target detection technique using imaging spectroscopic data should be introduced to the extraction of small geological targets under dense vegetation covering area. In the paper, we take Ding-Ma gold deposit as the study area which located in Zhenan country, Shanxi province, China. Some target detection algorithms which are appropriate to the small geological target detection are introduced based on the study of the principle of the algorithms. At last, the small altered rock targets under the covering of vegetation in forest are detected and discriminated using imaging spectroscopy data with the methods of spectral angle map(SAM), Orthogonal Subspace Projection(OSP), Constrained Energy Minimization(CEM), Adaptive Coherence/Cosine Estimator(ACE), Adaptive Matched Filter(AMF), Elliptically Contoured Distributions(ECD). The detection results are reasonable and indicate the ability of target detection algorithms for geological target detection in the forest area.

Land surface temperature (LST) is required by a series of surface studies and usually estimated using thermal infrared remote sensing data. In this paper, we propose a method to retrieve LST for MODIS data using its mid-infrared bands 22 and 23. As the central wavelengths of bands 22 and 23 are quite close, we assume that (1) band-averaged surface e-missivities are equal in these two bands, and (2) the Planck integration between these two bands comply to a statistical relationship. Based on these two assumptions, land surface temperature is retrieved after atmospheric correction on the radiance images. A test case is selected to estimate LST using our proposed method. The estimated LST image shows good consistency with the corresponding standard MODIS land surface temperature product, with the relative errors of ±1%. The experiment results suggest this methodology is effective to retrieve MODIS land surface temperature quickly.

The imaging Fourier transform spectrometer (IFTS) carried on HJ-1A is the first spaceborne hyperspectral earth observation sensor in China. Shifts in the spectral channel center wavelengths of IFTS may occur after launch due to vibrations, and to changes in instrument temperature and pressure. In this paper, we described an improved on-orbit spectral calibration method, which is based on spectrum angle matching between the spectrometer-measured radiance spectrum and the modeled radiance spectrum at atmospheric absorption bands. Compared with the laboratory calibration result of IFTS, spectral shifts ranged from -3.18 to -3.4 nm were derived depending on cross-track spectral position at 760-nm oxygen bands, and from -3.53 to -3.79 nm at 820-nm water vapor bands. With the updated spectral calibration coefficient, the reflectance of vegetation and desert in our study site were reconstructed by applying a further atmospheric correction, and the strong spikes around the atmospheric absorption bands were almost obviously suppressed.

A new hyperspectral unmixing algorithm is proposed based on the normal compositional model (NCM) to estimate the endmembers and abundance parameters jointly in this paper. The NCM considers the hyperspectral imaging as a stochastic process and interprets each pixel value as a random vector, which is linearly mixed by the endmembers. More precisely, these endmembers are also treated as random variables as opposed to deterministic values in order to capture spectral variability that is not well described by the linear mixing model (LMM). However, the higher complexity of such an unmixing model leads to more difficulty in parameter estimation. A particle swarm optimization-expectation maximization (PSO-EM) algorithm, a “winner-take-all” version of the EM, is proposed to solve the parameter estimation problem, which employs a partial E step. The main contribution of the proposed PSO-EM is making optimum use of particle swarm optimization method (PSO) in the partial E step, which solves the difficulty of the integrals in the NCM model. The performance of the proposed methodology is evaluated through synthetic and real data experiments. Our obtained results demonstrate the superior performance of PSO-EM compared to other NCM-based as well as LMM-based methods.

A precise and high-resolution spatiotemporal distribution of atmospheric carbon dioxide (CO2) is important in identifying and quantifying the CO2source and sinks on regional scales and emissions from discrete point sources. We propose the use of a regional gap-filling method by modeling the spatiotemporal correlation structures of column-averaged CO2dry air mole fractions (Xco2) on a regional scale, using data from the Atmospheric CO2Observations from Space retrievals of the Greenhouse Gases Observing Satellite (ACOS-GOSAT) measurements over mainland China. The accuracy of the gap-filling results is verified by cross-validation and comparison with ground-based measurements. As the results of the spatiotemporal gap-filling method are applied to mainland China, the correlation coefficient (r2) between the predicted values and true ones is greater than 0.85, the mean absolute prediction error is less than 1.5 ppm in cross-validation, and the seasonal cycle of the gap-filled data is generally in agreement with ground-based measurements. Finally, we compare the prediction accuracy based on our method with that based on the commonly used spatial-only kriging to further demonstrate the improved prediction accuracy. The applied regional gap-filling method, which makes full use of the multitemporal ACOS-GOSAT data, can generate a regional regular spatial distribution map of (Xco2) at high spatial and temporal resolutions.

We have presented an improved short-wave infrared (SWIR)-based iterative algorithm for the atmospheric correction (AC) of Moderate Resolution Imaging Spectroradiometer (MODIS) data over Lake Taihu, China. The algorithm was validated by means of matchup comparison between MODIS-retrieved and in situ remote sensing reflectances (Rrs). Four examples of the matchup comparison were first carried out for the observation stations within a ±5-min time window of MODIS overpass and field measurements. It is shown in the examples that the retrieved Rrsspectra compare reasonably well with the in situ measurements not only over relatively clear waters (with Rrs(859) about 0.0014 sr-1) but also over turbid waters (with Rrs(859) about 0.013 sr-1). The matchup comparison was further carried out for a total of 54 observation stations within a ±2-h time window, indicating that the AC algorithm has good performance for producing water spectra from MODIS data over Lake Taihu. The development of an algal bloom event has been monitored using MODIS-measured Rrs(443) and Rrs(859), showing that MODIS data, combined with the AC algorithm, can be a useful tool for monitoring the water quality of Lake Taihu. The SWIR iterative algorithm, along with the chlorophyll-a concentration (Chl-a) retrieval model using red to near-infrared bands, has the potential of monitoring Chl-a quantitatively and providing useful information for decision makers to manage the water environment and to prepare for events as algal blooms.

The paper presents a supervised classification method based on superpixels and Markov random field (MRF). Hyperspectral image is over-segmented into superpixels that are as basic unit of Markov random field instead of operating at the pixel level. Adaptive weight coefficient is introduced to determine contextual relationship between superpixels. Support vector machines are implemented for better estimation of spectral contribution to this approach. An experiment of real hyperspectral image reveals efficient performance.

This letter presents a new technique for clustering hyperspectral images that exploits neighborhood-constrained spatial information. The main feature of the proposed method is the introduction of a neighborhood homogeneity index (NHI) and the use of this index to measure the spatial homogeneity in a local area. A new similarity measurement integrates NHI and spectral information using an adaptive distance norm for clustering. The performance of the proposed neighborhood-constrained-clustering algorithm was assessed through a synthetic image and a real hyperspectral image and compared with those obtained by advanced spectral-spatial clustering algorithms. Experimental results show that the proposed scheme gives better performances.

HJ-CCD data has a great potential in monitoring water quality of inland waters. To test the HJ-CCD data application results of inland water quality monitoring, we carried out a sampling experiment in Lake Taihu. When HJ-1 satellite passing, we obtained synchronously 30 samples of remote sensing reflectance spectra, the concentration of total suspended matter (TSM), transparency and turbidity data. Regression analyzing with 27 sampling stations of water quality parameter data and the water remote sensing reflectance obtained in Lake Taihu, we established the empirical retrieval models of concentrations of TSM, transparency and turbidity. Based on these models we obtained the TSM, transparency and turbidity distribution maps in Lake Taihu using the HJ-CCD image. Finally testing retrieval results with the reserved three sampling stations of the water surface quality parameters, the average relative error is less than 0.2. This result indicates the retrieval accuracy of inland water quality parameters from HJ-CCD data satisfied basically the application requirements.

This paper proposes a method on detecting specific type of collapsed built-up structures using only post-event images. Its essence lies in fusing morphological texture and spectral information through a nonlinear function to characterize debris of collapsed built-up structures. Experiments are carried out on an image after the 2010 Yushu earthquake. Results show that the method can well extract collapsed brick built-up structures and it has an advantage of handling complex scenes in urban areas compared to state-of-the-art methods.

Measuring light absorption of suspended matter in water is essential for water color remote sensing. The `transmittance' method, which is based on the Quantitative Filter Technology, is one of the most widely used methods to determine absorption of suspended matters in water. This method measures optical density of suspended matters that concentrated on the filter and then calculate absorption by applying light pathlength amplification correction to the optical density. Either a pair of filter holders or an integrating sphere is the necessary accessory for the measurement of the optical density. However, according to our research, we discovered that the results obtained with different accessories have some differences. By comparing the optical density values that measured with different accessories, we analyzed the difference between different accessories and proposed a revised model for light pathlength amplification correction.

Rapid landscape pattern change has taken place in many arid and semi-arid regions of China such as Yellow River Basin over the past decade. In this article, the physical suitability of cropland and its change were evaluated and analyzed by the combined use of satellite remote sensing, geographical information system, and landscape modeling technologies. The aim was to improve our understanding of cropland change so that sustainable cropland utilization could be established. First, the spatial pattern change of cropland was analyzed using the 1-km2 area percentage model; second, the numerical model for cropland suitability assessment was explored and developed using analytical hierarchy process analysis method. Using this model, cropland suitability index was computed for the whole of the basin from 1990 to 2005. The cropland suitability index was classified into five levels: better, good, middle, bad, and worse, following the natural breaks classification. The spatial distribution of cropland suitability level and its changes over the 15 years from 1990 to 2005 were analyzed and the driving factors of cropland change were investigated. The results showed that the cropland suitability in the study area was at good level, and the cropland quality had been gradually improved on the whole. However, the cropland quality had become worse over the 15 years in some regions. In the study area, governmental policies for eco-environmental protection and population growth were found to be the major factors that caused the cropland change over the past 15 years.

Endmember extraction (EE) is the first step in hyperspectral data unmixing. N-FINDR is one of the most commonly used EE algorithms. Nevertheless, its computational complexity is high, particularly, for a large data set. Following a parallel version of N-FINDR, i.e., P-FINDR, further improvements are presented in this paper. First, generic endmember re-extraction operation (GERO) and multiple search paths are introduced such that multiple endmembers are extracted in parallel. Second, by making full use of the advantages of the proposed algorithms, two extended schemes, i.e., extended mapping rule and multiple-stage GERO are presented, which can reduce synchronous cost and provide steady parallel performance. In experiments, the proposed algorithms have been quantitatively evaluated. The results demonstrate that they can outperform the conventional parallel computing and do not degrade the quality of EE.

The shift of snow lines and their responding to climate warming change were investigated for the studying area of Nianqingtanglha mountainous in the Tibet plateau based on the yearly minimum snow cover from 2000 to 2008 using MODIS and digital elevation data. The results indicated that the elevations of snow lines were shifting toward higher from 2000 to 2008 following to the ablation of snow cover because of the affects of inclining temperature. From investigating results, it was assessed that the elevation of snow line for yearly minimum snow cover will generally uplift 57m per year if the yearly mean temperature increase one centigrade in the Nianqingtanglha mountainous of Tibet plateau.

Rapid detection of collapsed built-up structures is crucial for disaster mitigation in earthquake-affected areas. This paper proposes a method on detecting collapsed built-up structures using only post-event images. Its essence is to track and detect debris of collapsed built-up structures using features obtained through the derivative morphological profile. Experiments are carried out on images of the 2008 Wenchuan earthquake. Results show that the method can extract the debris of collapsed built-up structures in an effective and efficient way and is useful for rapid damage assessment.

This study presents a comparison of FPAR derived from GIMMS NDVI and MODIS product, as the preparation research for generating the global FPAR from 1981 to present. Eurasia was selected as the study area. First, we estimated FPAR in 2006 by the NDVI-based approach, and then we compared the spatial and seasonal patterns of estimating FPAR with the MODIS standard product. The results showed that: the GIMMS NDVI SR FPAR show the consistent dynamics spatial and seasonal dynamics with MODIS FPAR, and two datasets capture the seasonal variation well. MODIS FPAR values are larger than GIMMS NDVI SR FPAR, especially for the forest vegetation. The differences among of two datasets can also be partly attributed to the biome specific MODIS algorithm and NDVI-based approach in this study.

The Three Gorges Reservoir is the largest water resource project in west China. With water environment change greatly, water quality of the Three Gorges Reservoir needs monitoring urgently. With the properties of high spatial resolution, multi-angle observation and hyperspectral imagery, CHRIS offers a precious data resource for monitoring water quality. We apply CHRIS imagery to detect total suspended substance concentration of the Three Gorges. The method is simplified bio-optic model. The results showed the distribution total suspended substance concentration in the Three Gorges at 17thApril of 2007, which agree with the actual situation. The total suspended substance concentrations retrieved by the near-infrared method are quite close to the measured data. This study could be helpful to monitor water quality with hyperspectral remote sensing imagery just having near-infrared channels.

HJ-1A is one member of the Environment and Disaster Monitoring Microsatellite Constellation, which carries a HyperSpectral Imager (HSI) with the spectral resolution about 5nm from 450nm to 950nm. Retrieving columnar water vapor content is essential to the quantitative applications of hypespectral imagery. The ideal best band (940nm) for water vapor retrieval has lower signal-to-noise(S/N) value. In this paper, we choose another weak water absorption band (820nm) to retrieval the columnar water vapor content. Two common water vapor retrieval algorithms, called the Continuum Interpolated Band Ratio (CIBR) and the Atmospheric Precorrected Differential Absorption (APDA), are implemented and compared with each other. Simulation results show that these two algorithms have less difference in the accuracy of water vapor retrieval because the weak water vapor absorption effect in 820nm The water vapor contents derived from HJ-1A HSI by CIBR algorithm are compared with MODIS products and a systematic error may exist in the radiometric calibration of HSI.

Using the MODIS datasets, we assessed the spatial-temporal variations of land surface albedo driven by the changes of land cover such as snow, vegetation in the Qinghai-Tibetan plateau. The Qinghai-Tibetan plateau, called “the roof of the world”, is located in E74° – E104°′, N25° – N40° with an average elevation of over 4500 meter, where the main land cover types are grasslands and unused barren lands. Our results showed that the inter-annual trend of albedo was spatially correlated to snow cover variation, and its coefficient of determination with snow cover is greater than 0.5 over areas around northern meteorological stations from 2000 to 2009. The inter-annual variation of summer NDVI largely induced albedo change over the alpine meadow m the eastern region.

An adaptive Markov random field (MRF) approach is proposed for classification of hyperspectral imagery in this letter. The main feature of the proposed method is the introduction of a relative homogeneity index for each pixel and the use of this index to determine an appropriate weighting coefficient for the spatial contribution in the MRF classification. In this way, overcorrection of spatially high variation areas can be avoided. Support vector machines are implemented for improved class modeling and better estimate of spectral contribution to this approach. Experimental results of a synthetic hyperspectral data set and a real hyperspectral image demonstrate that the proposed method works better on both homogeneous regions and class boundaries with improved classification accuracy.

Spectral mixture analysis has been an important research topic in remote sensing applications, particularly for hyperspectral remote sensing data processing. On the basis of linear spectral mixture models, this paper applied directed and weighted graphs to describe the relationship between pixels. In particular, we transformed the endmember extraction problem in the decomposition of mixed pixels into an issue of optimization and built feasible solution space to evaluate the practical significance of the objective function, thereby establishing two ant colony optimization algorithms for endmember extraction. In addition to the detailed process of calculation, we also addressed the effects of different operating parameters on algorithm performance. Finally we designed two sets of simulation data experiments and one set of actual data experiments, and the results of those experiments prove that endmember extraction based on ant colony algorithms can avoid some defects of N-FINDR, VCA and other algorithms, improve the representation of endmembers for all image pixels, decrease the average value of root-mean-square error, and therefore achieve better endmember extraction results than the N-FINDR and VCA algorithms.

This paper described endmember extraction as a combinatorial optimization problem (COP). By defining particles' position and velocity, discrete particle swarm optimization (D-PSO) was proposed based on particle swarm optimization to resolve COP. The algorithm was tested and evaluated by hyperspectral remote sensing data. Experimental results showed that, while extracting the same number of endmembers, D-PSO could get a smaller root-mean-square error between an original image and its remixed image on the precondition of correct extraction results compared to the algorithms of vertex component analysis (VCA) and N-FINDR, which meant that D-PSO could acquire higher extraction precision.

HJ-1A and HJ-1B, the first micro-satellite constellation for Environment and Disaster Monitoring of China, was successfully launched in China on September 6, 2008. The same multispectral imagers named HJ-1/CCD with four bands (R, G, B, Nir) and large swath are installed on both HJ-1A and HJ-1B. The HJ-1/CCD is the main sensor of the constellation. In this paper, data sets includes six image pairs of HJ-1A/CCD and Terra/Modis and field reflectance spectra of Dunhuang Calibration Site are acquired. Cross calibration is taken to get the calibration results of HJ-1A/CCD relative to Terra/Modis. Based on the calibration results, the radiometric performance of HJ-1A/CCD is evaluated. Taking into that the good radiometric performance of Terra/Modis, it is obvious that HJ-1A/CCD has a radiometric attenuation during its second half of the first year. The max attenuation occurred on the near infrared band is about 18%. The min attenuation occurred on the blue band is about 8%. There maybe some inevitable errors about the data sets and produced during the processing. More images should be acquired and more attention should be paid to get the true radiometric attenuation.

This paper describes a 3D visualization computing methodology to aid the design of tremendous civil engineering in exploiting DEM and RS images. The methodology has been applied to the design and construction of astronomical telescope project, the FAST. Attempting to meet scientific and technological challenges in the process of the project, this paper has developed an innovational 3D computing platform. To simulate the virtual environment of the spot, 3D terrain model has been created based on QuickBird images and DEM, meanwhile, subtle model of massive main active reflector is loaded on the terrain. The algorithm of optimizing telescope antenna location in depressions is presented. In the virtual environment, considering the slope of the terrain, the distribution of feed supporting towers on the telescope has been optimized. It has been proved that the proposed methodology is of high efficiency in the practice of the application.

It is not completely clear that the spatial change of the green house gases such as CO2concentration, CH4concentration and their changes with the land ecological variation because there are not enough observational data available. A preliminary result investigating the spatial distributions variation of CO2and CH4concentrations in China using observed data by The Greenhouse Gases Observing SATellite (GOSAT), were demonstrated. The 1-km grid landuse data and the CO2dry air mixing ratios (XCO2) and CH4dry air mixing ratios (XCH4) inversed from GOSAT FTS/SWIR data were used. The results showed that the total average of XCO2 is 371ppmv, XCH4 is 1.72ppmv based on statistics of the entire GOSAT observing points from April 2009 to March 2010 in China. XCO2 over the urban and built-up areas and farmlands showed larger concentrations than that over the forest and grasslands.

Albedo is one of the most essential parameters for the radiation energy budget of land surface from analysis of the land-surface process which has influence on the regional climate and even on the global climate. This paper discussed the variation of the albedo from 2000 to 2008 on two administrative areas in China with very different humanistic and natural characteristics, one is Maduo County in Qinghai-Tibet Plateau, and the other is Beijing. The results showed that the annual albedo during 9 years presented increased trend in Maduo, while slightly decreased trend in Beijing. However, the albedo during the growing season showed decreased trends in both of the two regions. It is inferred that the changes of vegetation are the main factors causing albedo alteration in Beijing, while both vegetation and snow cover are main factors in Maduo.

To fulfill the objectives of Beijing-1 micro-satellite on-orbit calibration experiment, two in-flight calibration experiments were carried out on September 3 and 13, 2008 at Dunhuang Calibration Site. Two simultaneous datasets including Beijing-1 data and the in-situ surface reflectance and atmospheric measurements, were acquired at the calibration area. During the period of the calibration experiments, some dark sea images were captured to calculate the dark current of Biejing-1. With the reflectance of calibration targets, the atmospheric optical depths, and the water vapor constraints, the 6S radiative transfer code was used to calculate the equivalent radiance of Beijing-1 to the top of the atmosphere (TOA). The reflectance calibration algorithm was taken to calculate the absolute radiometric calibration coefficients of Beijing-1 multi-spectral cameras. The calibration results of Sep. 3 and that of Sep. 13 are very similar. The biggest relative error between the two results is only 3.77%. This proves the calibration results are reasonable.

Compression has become a must for efficient storing and transmission of data acquired by satellites with increasing resolution and swath. However, for compression of raw data satellite images, impact of striping noise is inevitable. Variances of Digital Number (DN) values introduced by striping noise will surely impair continuity and smoothness of satellite image and reduce the efficiency of onboard compression. In this paper, using Beijing-1 small satellite images, origin and characteristics of striping noise caused by double channel linear CCD and its impacts on the compression process are analyzed. Then, based on properties of striping noise, an improved method for compression of raw data satellite images is proposed. The new compression method is applied to Beijing-1 small satellite raw data images and yields significant boost in compression performance. Ideas of the proposed algorithm can be easily realized with circuit modification and no adaptation is needed for post processing of the compressed images.

Lunar minerals mapping is one of basic aims of China's Lunar Exploration Program. The goal of this paper was to use multiple mineral mapping techniques including classification and spectral matching for lunar surface minerals mapping and choose the effective methods based on the image data which was simulated by 76 lunar samples spectra supplied by LSCC. The results indicated that Mahalanobis Distance and support vector machine performs best of the supervised classification methods. SAM is more effective than SID of the spectral matching methods. The classification capability was different for the different size samples of the same materials. The samples with obvious diagnosed spectral characteristic can be identified effectively. Those without diagnosed spectral characteristic are sensitive to the mapping method. Besides the mapping methods, there are other factors which may affect the mapping results, such as the lunar soil component, the lunar soil maturity, the particle size and the data preprocessing procedure.

The coastal zone is a complex space where terrestrial environments and marine environments influence each other, including various coast flats and many artificial objects. There were many mixed pixels in hyperspectral image of coastal zone. In this paper, we applied decision tree to classify coastal zone, and adopted pure pixel index (PPI) to extract endmember as training samples during choosing various samples, which can reduce effect of mixed pixels on feature learning, at last using C4.5 decision tree algorithm to classify. We chose hyperspectral image acquired by Operational Modular Imaging Spectrometer (OMIS) in China, Classifying hyperspectral image using the method proposed in this paper, experiment result and classification precision proved efficiency and robustness of our method.

When calculating water leaving radiance or remote sensing reflectance from water surface measured spectra, the results are affected by the reflected skylight, which are the product of skylight radiance and the air-water surface reflectance of skylight. The skylight radiance can be measured over water surface by spectrometer. But the air-water surface reflectance is affected by multi factors, and is hard to be determined. Presently, there are some methods to estimate the value of air-water surface reflectance of skylight over ocean waters. However, when calculating the air-water surface reflectance of skylight over turbid inland waters, these methods all have some problems. In this paper, we develop an improved method to calculate air-water surface reflectance of skylight over turbid inland waters. This method is based on the spectral characteristics of turbid inland waters that water leaving radiance in shortwave infrared wavelength region can be assumed zero, which is verified by the data acquired in Taihu Lake on April 25 to 27, 2007. In this method, two atmospheric windows (1190 ~ 1330 nm and 1500 ~ 1700 nm) in shortwave infrared wavelength region are used. The main strategy of this method is to use the data in 1190 ~ 1330 nm wavelength region to calculate air-water surface reflectance of skylight first. When no reasonable result is obtained, the data in 1500 ~ 1700 nm wavelength region is used. With this method, the air-water surface reflectances of skylight on the 31 sampling stations are calculated. Then, water leaving radiance and remote sensing reflectance are calculated. The results of air-water surface reflectance of skylight and remote sensing reflectance on the 31 sampling stations are reasonable. Then, the advantages and limitations of the improved method are analyzed.

Many image fusion techniques have been proposed so as to achieve optimal resolution in the spatial and spectral domains. The Beijing-1 Micro-Satellite images have their own unique characteristics. The resolution ratio of its multi-spectral image to panchromatic image exceeds 4:1. It is often a challenge to pan-sharpen images with such a large spatial resolution ratio. In this paper, we develop an improved fusion method based on IHS, wavelet transform and regional features to merge the panchromatic and multi-spectral images of Beijing-1 Micro-Satellite. In addition, a comparative analysis from both visual effect and quantization parameters is carried out against other existing strategies. The results show that our proposed method can achieve better performance in combining and preserving spectral-spatial information for the Beijing-1 Micro-Satellite test images.

In this article, based on the theory of function series approaching, we change the spectral dimension of the hyperspectral data by using the Discrete Fourier transformation, and get a new feature space which could show the shape point of the spectrum curve. The coefficient, which hyperspectral data's component in the new feature space has against the Fourier series, could tell us the effect of different spectral function to the shape of spectrum curve. The paper especially analyzes the possible effect of this feature space in image shadow recognition and precision improvement of unsupervised classification based on the Euclid distance, and verify via experiments.

In late June 2008, Enteromorpha prolifera (E.P) bloomed in Qingdao marine, including Qingdao Olympic Sailing Center. The large scale and the fast extending speed of the E.P bloom were rare in history. The E.P bloomed just before Beijing 2008 Olympics, so it attracted the most attention around the world. Monitoring E.P from remote sensing data has the advantages of rapidness, wide coverage, low cost. But commonly used optical remote sensing is easily affected by cloud, which limits the monitoring timelines. In this paper, the theory of E.P monitoring from optical remote sensing and SAR remote sensing were analyzed. Then, the technical routes of E.P monitoring by exploiting the synergy of active and passive remote sensing data were presented. Because the SAR images are not affected by cloud, the timelines can be increased exploiting the by synergy of active and passive remote sensing data. MODIS and RADARSAT were used to monitor E.P. The monitoring results were used to analyze the beginning and spread of E.P. The monitoring results from MODIS and RADARSAT were compared.

This paper creates an operational swift solution for automatic analyzing water quality in case II waters. The HJ-1 satellites of China was successfully launched, this provides a good opportunity for case II water (inland and coastal water) environment monitoring. However, there is no operational monitoring system in China and abroad. The traditional processing methods were developed for expert users, which including many complex operations and user interaction, not suitable for business operation. To overcome this problem, an automatic monitoring procedure was developed by us. With this approach, one can get monitoring reports from original HJ-1 satellites images or MODIS images with ¿one-click¿. That means, you do not have to concern the complex data processing procedure, and what you need to do is specify the water quality monitoring area, the specific space-borne sensor and the remote sensing images. According to the study area, sensor type and image file, the operational procedure will automatically get parameters from the integrated XML files and database indexed by area and sensor type. The processing procedure does not need any user intervention, which greatly improve the processing efficiency. This paper gives a complete flow chart of data processing in the automatic monitoring mode using XML files and databases. Moreover, in order to verify the ability of the operational monitoring approach, experiments were conducted in Tai'hu, Chao'hu, and Dian'chi lakes using MODIS QKM images and the HJ-1 multi-spectral images. Tests show both the efficiency and accuracy of this approach is relatively high.

Karst rocky desertification is a special kind of land desertification developed under violent human impacts on the vulnerable eco-geo-environment of karst ecosystem. The fractional cover of photosynthetic vegetation (PV), non-photosynthetic vegetation (NPV), bare soil and exposed bedrock are key indicators of the extent and degree of land degradation in karst region. The vegetation fractional cover can be estimated approximately from remote sensing with vegetation indices. However, the vegetation indices cannot be easily applicable to all land cover types. In this study, we developed new spectral indices, karst rocky desertification synthesis indices (KRDSI), were then designed based on tied-spectrum permutation and unique spectral characteristics of main land cover types. Comparing with the use of traditional vegetation indices and LSU, the KRDSI was more consistent with the field measurement of main land cover fractions. Our study indicates that KRDSI is a useful tool for karst rocky desertification monitoring with remotely sensed data.

A Micro-satellite Constellation for Environment and Disaster Monitoring was successfully launched in China on September 6, 2008, which includes two small satellites, Satellite-A (HJ-1A) and Satellite-B (HJ-1B). The interferometric imaging spectrometer (IFIS) installed on HJ-1A is the first hyperspectral earth observation sensor in China. To assess the data quality of IFIS, a calibration experiment was carried out at the Dunhuang Calibration Site on October 20, 2008. With the simultaneous measurements acquired from the Dunhuang calibration field, the 6s radiative transfer code was used to retrieve the ground surface reflectance. By comparing the in-situ reflectance and 6S reflectance of the Dunhuang calibration target, the radiometric and spectral performance of the IFIS was evaluated. From the homogeneous image of the calibration target, the Signal-to-Noise Ratio (SNR) of IFIS data was estimated based on the high correlation between bands. This noise estimation results was used to estimate noise covariance matrix needed for hyperspectral data dimension reduction, such as Maximum Noise Fractions (MNF). The assessment results indicated that the IFIS has good performance and will be promising in the applications of environment and disaster monitoring.

An extended Bragg scattering model, for fully polarimetric SAR data, is here proposed for describing sea surface scattering. Moreover, the model is considered to examine the scattering contributions from sea surface and detected dark areas due to the presence of anthropogenic and biogenic slicks. Experiments are conducted on fully polarimetric C- and L-band SAR data.

The aerosol optical depth (AOD) measured by sun photometer is obtained after subtracting the Rayleigh optical depth, ozone optical depth and other absorption gas optical depth from total optical depth. Wherein, it was according to Beer's attenuation law. However, the band filter function of sun photometers should be considered when retrieving AODs. In this paper, it was systemically analyzed the influence of sun photometer filter function on retrieving aerosol optical depth. Numerous study showed that the band filter function has a significant impact on retrieving AODs: 1)The uncertainty of AODs may become large when the filter function is not well desgined; 2) Under large zenith observation condition, it may introduce non-neglected errors if Rayleigh scattering optical depth is calculated directly at central wavelength without filter function considered; 3) The band weighted absorption coefficients of O3and NO2almost hold constant when gas amounts increase, except for questionable designed band filter; 4) These weak absorption optical depths can not be ignored such as H2O absorption optical depths in 1020nm &1640nm band and CH4, CO2absorption optical depths in 1640nm band.

As a key parameter representing the outgoing solar flux fractions reflected by earth surface, the albedo of land surface has been strongly altered by the change of land covers, especially the increase of the impervious surface caused by the urbanization. This paper discussed and demonstrated the albedo changed with the impervious increases around Beijing-Tianjin urban region, where land cover type has been strongly changed since the 1980s, especially a large scale of buildings and roads increased in Beijing 2008 Olympic Games. We extracted the variation information of albedo from MODIS data as well as the impervious changes by using two scenes Landsat Thematic Mapper images. The relationship between the change pattern of albedo and the impervious surface was discussed and especially the regions within the five rim of Beijing urban, and the surrounding areas along two Jing-Jin highways were paid more attention to. It was found that the variation of the near infrared albedo albedo in 2008 shows an obvious change with the increase of impervious surface, while the change is not apparent in the visible band.

A new method for estimating noise in hyperspectral images is described in this letter. Our method is based on the general internal regularity of Earth objects and the strong spectral correlation of hyperspectral images. It can be used to automatically estimate noise for both radiance and reflectance images. Unlike other methods discussed in this letter, our method is more reliable and adaptable, which we demonstrate using simulated images with different scene contents. Finally, we successfully applied this new method in estimating noise for Pushbroom Hyperspectral Imager (PHI) data.

Spectral data , composed of spectra and related attributes, such as environmental parameters, attribute parameters about measured objects and others, are usually stored in spectral database. Spectral database is an important basis of the hyperspectral remote sensing development. Therefore, it is very important to utilize sufficiently, manage effectively, and collect spectral data extensively. The fast development of computer infrastructure and internet technology makes it possible to upload, manage and analyze spectral data in a real-time, long-distance, and online way. This paper takes agriculture spectral database as an example to show the details of the implementation. Using JSP + JavaBeans based on Oracle fulfills the following functions: data browse and query, upload and examination, regression analysis, parameter extraction, etc. Keywords-Spectral Database; Online;Data Analysis and Management

A new architecture for REMS (Remote-sensing Environmental Monitoring System V1.0) is introduced in this paper. REMS is the first integrated system in China developed to meet the multi-resource, multi-temporal and multi-thematic data processing, analyzing and products distributing, especially to process and monitor inland water resource pollution. The most important components of REMS are presented in this paper including tools for multi-resource data input/output, preprocessing, data visualization and mapping, environment information extraction, conventional image analysis, advanced tools for eco-environment modeling, and integrated interface to connect with general spatial and spectral database and water quality monitoring database. REMS provide professional ability to extract the major characters of water resource such as Chlorophyll content, Total Suspended Matter (TSM), Yellow Substance or CDOM etc. In order to retrieve and predict the blue algae distribution and water quality evolvement, a group of statistical algorithms are also realized to analyses the result and at the same time data assurance measures are also given respectively. Finally, we select the Taihu Lake, JiangShu Province, South China, as the representative research area and some field applications constructed based on REMS are discussed