Solar-induced chlorophyll fluorescence (SIF) is a direct proxy for photosynthetic activity, yet existing satellite SIF products are constrained by coarse spatial resolution, limiting their application in ecological and agricultural studies. In this work, we propose a One-Step Learned Spatial Redistribution Convolutional Neural Network (OSRNet) that downscales 0.05° TROPOMI SIF to 0.005° by learning spatially adaptive redistribution fields from high-resolution drivers, which allocate coarse-resolution satellite SIF into fine-resolution grids. Based on this framework, we generate RSIF, a global 16-day 0.005° SIF dataset for 2018–2020. Comprehensive evaluation against both satellite and tower-based SIF shows that RSIF maintains strong consistency with TROPOMI observations (R² = 0.976, RMSE = 0.036) while recovering fine-scale spatial details. OSRNet substantially outperforms established direct prediction methods such as RF and SIFNet, and, compared with post hoc corrected RF approach from prior studies, achieves the highest R² across all tower sites and generally the lowest RMSE, enabling more accurate representation of seasonal dynamics with improved spatial fidelity.

Detecting small air target is an important task in civil aviation. However, the weak characteristics of these targets make detection challenging. Hyperspectral image (HSI), provides a new approach for the small air target detection task due to its strong ability of capturing both spatial and spectral information simultaneously. In this article, we propose a spectral-spatial enhanced local contrast strategy for hyperspectral small air target detection. An unsupervised band selection step based on the local contrast strategy has been designed based on local contrast (LC-UBSM) to choose bands with better distinguish ability between the target and background in HSI. Then, we have developed an improved RX detection algorithm with combined spatial and spectral variance (CSSV-RX) to detect the target while suppressing both background and noise. Experimental results on both real GAOFEN-5 dataset and simulated dataset based on EO-1 (Earth Observing-1) satellite have validated the effectiveness and robustness of the proposed method.

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.

Due to limitations of satellite imaging systems, hyperspectral image (HSI) often suffers from incomplete coverage, with certain regions of the study area missing. Data fusion and reconstruction are effective approaches to resolve the contradiction in spatial and spectral domains, where related theories have intensively developed in recent years. However, existing fusion methods are mostly applicable to simulated data and are challenging to apply to real data. In this paper, we propose an unsupervised fusion spatial reconstruction network namely UFSRnet, which not only reconstructs the missing regions of HSI but also learns the differences between heterogeneous data adaptively. Specifically, a sensor radiation deviation correction (SRDC) module is designed to tackle the disparities between heterogeneous data adaptively. The model demonstrates commendable performance across both simulated and real data sets.

Recently, the methods based on self-attention mechanisms have gained increasing prominence in hyperspectral image classification (HSIC). However, the existing self-attention mechanism suffers the challenge of attention shift and redundancy. To address the problem, we propose the center category focusing transformer network (CCSF-Transformer) for HSIC, which is designed to resolve attention shifts and redundancy by balancing the multiple category features. Specifically, the central-category-focused attention mechanism (CFA) is presented in the proposed framework to compute the category-matched attention between the center pixel and neighbor pixels, closely matching the center-pixel style labeling strategy, and reducing the computation complexity by excluding the computation between interference pixels. Besides, the spectral-salient-focused attention module (SFA) is developed to capture the spectral correlation, which concentrates on the salient bands and suppresses the expression of redundant bands. Moreover, the hierarchical integration network (HIN) is built to rectify spatial and spectral features The experiment results on two popular HSI datasets demonstrate that the proposed method achieves robust performance compared to other state-of-the-art methods.

The most cost-effective way to obtain a high spatial resolution hyperspectral image (HrHSI) is to fuse a low spatial resolution hyperspectral image (LrHSI) and corresponding high spatial resolution multispectral image (HrMSI). This article proposes a generalizable unsupervised deep fusion method based on spectral-spatial collaborative constraint to address LrHSI and HrMSI fusion task. First, in view of the limitations of the current spectral-spatial downsampled model, the group convolution enhancement (GCE) module is designed to eliminate the radiometric difference between the images to be fused. Second, to enhance the model’s feature extraction ability, this article introduces the design of the spatial, channel, and filter 3-D attention factor dynamic convolutional kernel (SCFConv). In order to verify the proposed method, we compared and evaluated our method with traditional methods and unsupervised deep learning methods using both simulated and real onboard data, respectively. In the absence of HrHSI validation images in real scenarios, we evaluate the performance of different fusion models through classification results. The experimental results demonstrate the effectiveness of the proposed model and the practical value of the fusion results (the onboard data produced by ours are available athttps://drive.google.com/drive/folders/1JLCCB6ld5R49HDLN5SsMISx1d0fuqRjO).

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.

Oriented to adaptive recognition of the new land-cover categories, incremental classification (IC) that aims to complete adaptive classification with continuous learning is urgent and crucial for hyperspectral image classification (HSIC). Nevertheless, deep-learning-based HSIC models adopted the learning paradigm with fixed classes yield unsatisfactory inference in the situation of IC due to the catastrophic forgetting problem. To eliminate the recognition gap and maintain the old knowledge during IC, in this paper, we propose a novel approach called the distillation-constrained prototype representation network (DCPRN) for hyperspectral image incremental classification (HSIIC). The primary goal of DCPRN is to enhance the discriminative capability for recognizing the original classes in HSIIC, while effectively integrating both the original and incremental knowledge to facilitate adaptive learning. Specifically, the proposed framework incorporates a prototype representation mechanism, which serves as a bridge for knowledge transfer and integration between the initial and incremental learning phases of HSIIC. Additionally, we present a dual knowledge distillation module in incremental learning, which integrates discriminative information at both the feature and decision level. In this way, the proposed mechanism enables flexible and dynamic adaptation to new classes and overcomes the limitations of fixed-category feature learning. Extensive experimental analysis conducted on three popular data sets validates the superiority of the proposed DCPRN method compared with other typical HSIIC approaches.

Hyperspectral image (HSI) denoising is a crucial step for its subsequent applications. In this article, we propose TDSAT, a 3-D spatial-spectral attention Transformer model designed to effectively remove noise in HSI processing while preserving essential spectral and spatial information. The primary objective of this model is to utilize the 3-D Transformer to explore the global spectral-spatial features in HSI, learn the relationships among different bands, and preserve high-quality spectral and spatial information for denoising. The proposed method consists of three main components: the multihead spectral attention (MHSA) module, the gated-dconv feedforward network (GDFN) module, and the spectral enhancement (SpeE) module. The MHSA module learns the relationships among different bands and emphasizes the local spatial information. The GDFN module explores more expressive and discriminative spectral features. The SpeE module enhances the perception of subtle differences between different spectrums. Moreover, unlike the previous Transformer denoising method that can only handle fixed bands, the proposed method combines 3-D convolution and spectral-spatial attention Transformer blocks, enabling the denoising of HSI with an arbitrary number of bands. Experimental results demonstrate that TDSAT outperforms compared methods. The code is available athttps://github.com/Featherrain/TDSAT.

Mixed noise pollution in HSI severely disturbs subsequent interpretations and applications. In this technical review, we first give the noise analysis in different noisy HSIs and conclude crucial points for programming HSI denoising algorithms. Then, a general HSI restoration model is formulated for optimization. Later, we comprehensively review existing HSI denoising methods, from model-driven strategy (nonlocal mean, total variation, sparse representation, low-rank matrix approximation, and low-rank tensor factorization), data-driven strategy [2-D convolutional neural network (CNN), 3-D CNN, hybrid, and unsupervised networks], to model-data-driven strategy. The advantages and disadvantages of each strategy for HSI denoising are summarized and contrasted. Behind this, we present an evaluation of the HSI denoising methods for various noisy HSIs in simulated and real experiments. The classification results of denoised HSIs and execution efficiency are depicted through these HSI denoising methods. Finally, prospects of future HSI denoising methods are listed in this technical review to guide the ongoing road for HSI denoising. The HSI denoising dataset could be found at https://qzhang95.github.io.

Thermal infrared remote sensing has been widely used for sea surface temperature (SST) monitoring. However, traditional SST remote sensing retrieval models usually have uncertainties when applied to offshore waters with variable environmental conditions due to simple functional forms and empirical fitting of model parameters. Machine learning (ML) can theoretically avoid these problems, but its applicability and driving features have not been thoroughly investigated. Here, we proposed a high-precision ML-based SST retrieval framework for offshore waters in the eastern Liaodong Peninsula of China by optimizing the selection of input features. The results showed that random forest model achieved better accuracy than deep neural network and the improved split-window algorithm, exhibited credible spatial patterns of SST maps across four seasons, and was portable for the independent samples in 2021. This study offers references in selection of features and models for SST retrieval, and benefits the accuracy of offshore SST retrieval.

In recent years, fusion methods based on unsupervised deep learning have achieved impressive performance in the fusion of hyperspectral image (HSI) and multispectral image (MSI). However, there are still some limitations in the current research. Most existing fusion methods only apply to simulated data and need more verification on real data sets. To solve these issues, this paper designed an unsupervised dynamic convolutional neural network fusion model (UDCNN), which can adaptively learn the radiometric difference between HSI and MSI. This model achieves better performance on simulated data compared with related unsupervised deep learning methods, and achieves more accurate results on real data through classification-oriented application of the fusion results.

Multi-exposure image fusion (MEF) technique is the most widely used method to obtain high dynamic range (HDR) images. Inspired by the recent successful application of Transformer in image processing, a hybrid dense connection network based on CNN and Transformer is proposed for MEF in this paper. Considering the importance of texture details to the multi-exposure image fusion task, shallow features containing rich texture details is also added to each dense layer, which are extracted by the pre-trained RepVGG. In addition, the dynamic weight calculation module is improved, so that different source images can obtain finer weight in the calculation of the loss function. Experiments are conducted on the dataset provided by MEFB, and both qualitative and quantitative comparisons show that the proposed method can achieve better results compared with the state-of-the-art algorithms.

Fusing a low-resolution hyperspectral image (LrHSI) with an auxiliary high-resolution multispectral image (HrMSI) is a burgeoning technique to realize hyperspectral image super-resolution, in which learning-based methods have dominated the mainstream direction. However, the underutilization of degradation models and strong dependence on large-scale training triplets severely impedes their applicability and performance. Considering these issues, we reformulate the fusion task as a spectral mapping problem and hence propose an unsupervised model-guided coarse-to-fine fusion network. Specifically, degradation knowledge learning is first performed to fully excavate latent model information, which will serve as guidance for better mapping learning. Following that, a coarse-to-fine fusion network is constructed with a multi-scale attentional fusion module in the head and a coarse-to-fine structure in the tail. The former is deployed to achieve a more informative compression, and the latter is adopted to capture the spectral relationship, including a spectral degradation-guided subnetwork for group-by-group coarse reconstruction and a refinement subnetwork for inter-group correlation and dependencies. Finally, high-resolution HSI can be recovered via established spectral mapping. Extensive experiments on simulated and real datasets verify the superiority of our proposed method. The code is available at https://github.com/JiaxinLiCAS/UMC2FF_GRSL.

Due to the powerful feature information mining ability of deep learning, models such as Convolutional Neural Network (CNN) and Transformer have gained a certain progress in hyperspectral image classification (HSIC). Characteristically, the CNN is good at extracting local information, but it has the limitation of insufficient receptive field. While the Transformer has the advantage of global representation, it ignores local details to some extent. Therefore, this letter proposes an interactive Transformer and CNN with multilevel feature fusion network (ITCNet) for HSIC. Specifically, in the image-based framework, features with different perceptual fields and depths are extracted interactively by a multi-layer Transformer and CNN, then fused through a multilevel feature fusion module for class prediction. Experimental results on two real datasets verifies its efficiency, with improvements over other related methods.

Mixed noise pollution severely disturbs hyperspectral image (HSI) processing and applications. Plenty of algorithms have been developed to address this issue via two strategies: model-driven or data-driven strategy. However, model-driven methods exist in the highly time-consuming weakness of iterative optimization and unstable sensitivity of setting parameters. Data-driven methods usually perform poor due to the overfitting effects. To solve these issues, we combine both the deep denoising priors with low-rank tensor factorization (DP-LRTF) for HSI restoration. The proposed method uses Tucker tensor factorization to depict the global spectral low-rank constraint. Then the spectral orthogonal basis and spatial reduced factor are optimized by two deep denoising priors, respectively. Through this integrated strategy, we can simultaneously exploit the intrinsic low-rank property of HSI, and utilize the powerful feature extraction ability by deep learning for HSI restoration. Compared with model-driven and data-driven methods, DP-LRTF outperforms on HSI mixed noise removal and execution efficiency for various simulated/real experiments.

With the development and progress of deep learning, the use of deep learning technology for hyperspectral target detection has achieved excellent results. However, most deep-learning-based methods do not effectively suppress background. This paper presents a contrastive learning-based hyperspectral target detection (CLHTD) for this purpose. The positive and negative pairs are constructed through data augmentation, and the backbone is used to extract the representative vectors of the augmented samples. Then the representative vectors are mapped to the spectral and the cluster contrast space using their corresponding contrastive head, respectively. In the contrast space, the similarity and dissimilarity of spectra and clusters are learned by maximizing the similarity of positive pairs while minimizing the similarity of negative pairs, to increase the difference between the representative vectors of target and background. Finally, the detection result is obtained through the cosine distance. Experimental results illustrate that the proposed CLHTD algorithm can achieve superior performances for hyperspectral target detection.

Hyperspectral remote sensing image is rich in spectral information. Due to the limitations of sensors and the complexity of the scene, a large number of mixed pixels exist in the scene. Therefore, it is very necessary to develop the unmixing technology. The linear unmixing model and its derived algorithms have made some progress. The existing unmixing methods treat all pixels in the scene as mixed pixels for operation, but the real scene is often a complex scene with pure pixels and mixed pixels. Considering the unmixing of complex scenes, the robust linear unmixing model based on enhanced constraint of classification (ECRLU) is proposed in this paper. The model combines unmixing and classification. After extracting endmembers, the number of endmembers is expanded by using local similarity and spatial similarity to obtain hard classification items, so as to provide sparsity constraints for the model. In this paper, synthetic data set and real data set are used to verify the effectiveness of the model.

Detecting and counting solar panels from high-resolution aerial images timely and accurately is essential for monitoring and management of industrial solar photovoltaic (PV) systems. Due to the influence of weather and light, the detection results of traditional methods are usually unsatisfactory. For the purpose of improving detection accuracy, we propose a method that combined residual network and channel attention module to improve the Faster RCNN framework. First, the balance between the training data size and model complexity is investigated, and the residual network is utilized to deepen the feature extractor within the effective range. Then, the channel attention modules are introduced into the network to further enhance the feature representation. Experimental results, conducted on high-resolution aerial image over Guilin, China, prove that the proposed method can detect solar panels with better accuracy than other related methods.

Abstract Although hyperspectral data, especially spaceborne images, are rich in spectral information, their spatial resolution is usually low due to the limitation of sensor design and other factors. Therefore, for the application of hyperspectral images, unmixing technology is a key processing technology, such as linear mixing model and its derived algorithms have made a certain progress. However, a real scene often contains both pure and mixed pixels. The existing methods usually ignore the consideration and analysis of this situation in the process of model design and simulation experiment. In this context, this paper proposes a robust linear unmixing model with the enhanced constraint of classification for hyperspectral image. In general, it designs a framework combining unmixing and classification. In the task for real scene data, endmembers are extracted first, and then the hard classification term constructed after the expansion of endmembers (training samples) based on similarity is introduced to provide the sparsity constraint of the overall model, so as to realize relatively complete adjustment and effective image unmixing under complex conditions. Considering the scene with different distributions, the simulation experiment designs several groups of data tests, including different proportions of pure and mixing pixels. The unmixing results of three simulated datasets and two real datasets show that the unmixing results of this method are better than those of the other six comparison methods. This model improves the accuracy of unmixing and realizes effective unmixing.

This letter proposes an unsupervised band selection (BS) algorithm named residual driven BS (RDBS) to address the lack ofa prioriinformation about anomalies, obtain a band subset with high representation capability of anomalies, and finally improve the anomaly detection (AD). First, an anomaly and background modeling framework (ABMF) is developed via density peak clustering (DPC) to pre-determine the prior knowledge of the anomalies and background. Then, the DPC-based constraints are applied to R-Anomaly Detector (RAD), and three band prioritization (BP) criteria are derived to obtain the representative band subset for anomalies. Experiments on two datasets show the superiority of RDBS over other BS algorithms and verify that the obtained band subsets are strongly representative of anomalies.

Recently, convolutional neural networks (CNNs) have been widely applied to hyperspectral image (HSI) classification due to their detailed representation of features. Nevertheless, the current CNN-based HSI classification methods mainly follow a patch-based learning framework. These methods are nonglobal learning methods, which not only limit the use of global information but also require a high computational cost. In this letter, an image-based global learning framework is introduced to HSI classification. Based on this framework, we propose a dual-channel convolutional network (DCCN) for HSI classification to maximize the exploitation of the global and multiscale information of HSI. The experimental results conducted on two real hyperspectral datasets indicate that our method is superior to other related methods in terms of both efficiency and accuracy for HSI classification.

Convolutional neural networks (CNN) have been widely used in hyperspectral image classification (HSIC). Although the current CNN-based methods have achieved good performance, they still face a series of challenges. For example, the receptive field is limited, information is lost in down-sampling layer, and a lot of computing resources are consumed for deep networks. To overcome these problems, we proposed a multi-level spectral-spatial transformer network (MSTNet) for HSIC. The structure of MSTNet is an image-based classification framework, which is efficient and straightforward. Based on this framework, we designed a self-attentive encoder. Firstly, HSIs are processed into sequences. Meanwhile, a learned positional embedding is added to integrate spatial information. Then, a pure transformer encoder is employed to learn feature representations. Finally, the multi-level features are processed by decoders to generate the classification results in the original image size. The experimental results based on three real hyperspectral data sets demonstrate the efficiency of the proposed method in comparison with the other related CNN-based methods.

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.

Band selection can reduce information redundancy and improve application efficiency of hyperspectral images, such as classification. Traditional band selection methods usually weight different objectives and combine them together in a single function, making it difficult to balance conflict between various criteria. Recently, multiobjective optimization band selection techniques have got a lot of attention, which evaluate bands from different aspects separately, and search for a solution well balancing all the objectives simultaneously. However, few algorithms are focused on target detection, and most of them use just two objectives, which are not sufficient enough to select optimal band subset for detection. To alleviate these problems, this paper proposes an algorithm named target-oriented multiobjective optimization of band selection (TOMOBS). Firstly, the multiobjective optimization framework with three objective functions is modeled, involving information, noise, and correlation of the bands respectively. Secondly, in order to optimize the proposed model, the noninferior solution advantage matrix is designed based on the swarm intelligence optimization method, which can provide accurate solutions and improve the descriptiveness of multiobjective optimization problems. Thirdly, target-oriented evaluation mechanism is developed to guide selecting final result from the Pareto front, especially designed for target detection. Experiments on real hyperspectral datasets show that this algorithm can provide a subset of bands with strong representational capability for target detection, and achieve impressing results compared to the state-of-the-art methods.

High spectral dimensionality of hyperspectral image (HSI) has brought great redundancy for data processing. Band selection (BS), as one of the most commonly used dimension reduction (DR) techniques, attempts to remove the redundant spectral bands, while maintaining good classification or detection rate for later applications. Gray wolf optimizer (GWO) algorithm is a meta-heuristic algorithm, and it is used for HSI BS. However, the convergence factor of the basic GWO is linearly decreased, leading to a slower convergence speed and increasing the probability of falling into local optimality. This article proposes a new hybrid gray wolf optimizer (HGWO) algorithm for HSI BS, which uses adaptive decreasing convergence factor instead of linear convergence factor to improve GWO convergence rate and combines category separability for initialization to avoid local optimality. Five nonlinear functions are used to test the convergence of the proposed HGWO algorithm, compared with the state-of-the-art optimization algorithms. Finally, the experimentations are performed on three widely used real hyperspectral datasets for HSI classification, and the experimental results show that band subsets selected by the proposed HGWO algorithm can obtain better classification accuracy compared with other global optimization algorithms.

Model-driven methods and data-driven methods have been widely developed for hyperspectral image (HSI) denoising. However, there are pros and cons in both model-driven and data-driven methods. To address this issue, we develop a self-supervised HSI denoising method via integrating model-driven with data-driven strategy. The proposed framework simultaneously cooperates the spectral low-rankness prior and deep spatial prior (SLRP-DSP) for HSI self-supervised denoising. SLRP-DSP introduces the Tucker factorization via orthogonal basis and reduced factor, to capture the global spectral low-rankness prior in HSI. Besides, SLRP-DSP adopts a self-supervised way to learn the deep spatial prior. The proposed method doesn't need a large number of clean HSIs as the label samples. Through the self-supervised learning, SLRP-DSP can adaptively adjust the deep spatial prior from self-spatial information for reduced spatial factor denoising. An alternating iterative optimization framework is developed to exploit the internal low-rankness prior of third-order tensors and the spatial feature extraction capacity of convolutional neural network. Compared with both existing model-driven methods and data-driven methods, experimental results manifest that the proposed SLRP-DSP outperforms on mixed noise removal in different noisy HSIs.

Super-resolution reconstruction is a rapidly growing research area in hyperspectral data processing. However, there exist some problems, such as edge blur, burr in the smooth area, subjective design of iteration times, et al. This paper analyzes the causes of blur and burr, and puts forward some countermeasures according to these problems. Firstly, gradient interpolation is used instead of the traditional nearest neighbor interpolation, which alleviates the edge blur to a certain extent problem, the projection operator calculated from the gradient map is introduced into the projection formula to solve the burr phenomenon in the smooth area. Then, the mean square error of the reconstructed image of adjacent iterations is used to measure the similarity of the reconstructed image between two adjacent iterations, which is used as the stopping criterion of iterations, avoiding the subjectivity of setting the iteration times artificially. Finally, the proposed algorithm is applied to every band of hyperspectral image. Experimental results show that the proposed algorithm has better performance than the traditional POCS algorithm in visual effect and quantitative criteria.

This paper proposes a method to improve the performance of the supervised classification from two aspects. Firstly, the global spatial and local spectral similarity is used to extend the labeled sample size (GLS). Secondly, extended subspace projection (ESP) which projects the original image to a lower-dimensional subspace is used to alleviate band redundancy. Finally, the two implements are combined with the sparse representation classifier (SRC) to optimize the hyperspectral image classification (HSIC). The proposed method is named GLSESP. Experimental results on real hyperspectral data set demonstrate the practicality and effectiveness of GLSESP for HSIC tasks.

The combined use of spatial information and spectral information has been widely applied to hyperspectral image (HSI) classification. In recent years, multiscale spatial-spectral convolutional neural networks (CNN) have been introduced for hyperspectral image classification (HSIC). However, most of HSIC methods based on CNN mainly use patches as input for classifier. This may cause a lot of redundancy in the training and testing process, and reduce the efficiency of the model. In order to address this problem, we design a novel image-based classification framework. Based on this framework, we propose a multi-scale dense network for HSIs, called HyMSDN. This network merges features from different scales through a feature pyramid structure. Experimental results on real hyperspectral dataset verify the efficiency and effectiveness of the proposed framework, with superior performances compared with other related methods.

Sparse representation (SR)-based models have shown to be a powerful category of frameworks for hyperspectral image classification (HSIC). However, current residual-driven methods mainly focus on the sparsity of the coefficient, which is generally used in conjunction with the dictionary. In fact, the discriminant information hidden behind the value of sparse coefficient is not fully exploited. In this letter, we analyze the SR-based framework from the perspective of sparse coefficient, develop the participation degree (PD)-driven decision mechanism, and establish a concise model called constraint representation (CR). Based on CR, an improved version called adjacent CR (ACR) is further proposed, with consideration of spatial coherence via adjacent constraint. Experimental results using two real hyperspectral datasets verify the improvements of the proposed methods over the other related models and their spatial variants.

Wealthy spectral information provided by hyperspectral image (HSI) offers great benefits for many applications in hyperspectral data exploitation. However, processing such high-dimensional data volumes that may result in redundant bands due to its high interband correlation will be a challenge. For target detection and classification, this is particularly true since there may only need a relatively small number of bands that respond one particular target of interest well, while most of other bands do not. Band selection (BS) is a major dimensionality reduction technique to remove the redundant bands and selects a few bands to represent the entire image. However, how to eliminate the effect of uninteresting targets with similar spectra on detection of interesting targets is a severe issue arising in target detection for BS. This article develops a new approach called target-constrained interference-minimized BS (TCIMBS) which can be used to select band subset for specific target detection, while annihilating targets of no interest and suppressing interferers and background. Its idea is derived from target-constrained interference-minimized filter (TCIMF). By taking advantage of TCIMF, two band prioritization (BP) criteria called forward minimum variance BP (FMinV-BP) and backward maximum variance BP (BMaxV-BP) along with their three band search-based BS counterparts called sequential forward TCIMBS (SF-TCIMBS), sequential backward TCIMBS (SB-TCIMBS), and improved SB-TCIMBS (SB-TCIMBS*) are derived. The experimental results suggest that TCIMBS can improve the detection accuracy and also achieve better performance in comparison with several state-of-the-art methods.

Hyperspectral imagery provides wealthy spectral information to make it suitable for many applications. However, for specific applications, extracting suitable bands from high-dimensional data is a tedious and difficult task. In the past, many methods have been developed to perform band selection for specific tasks such as target detection. However, there is very little work to consider and deal with the effects of suspected interfering targets. In this paper, a new method for band selection, called target-constrained interference-minimized band selection (TCIMBS) is developed for specific target detection. It can select a band set with strong characterization capabilities for desired targets and good suppression for undesired targets and background (BKG). Experimental results demonstrate that TCIMBS can improve the detection performance, and also achieve better performances in comparison with several state-of-the-art methods.

Sparse representation (SR)-based models have been widely applied for hyperspectral image classification. However, the original residual-driven frameworks ignore the property of sparse coefficient to some extent, and their spatial variants suffer obstacles of optimization due to the strong constraint. In this paper, based on previous works on sparse coefficient and its spatial expansion, we put forward a novel classifier, called superpixel-level constraint representation (SPCR). In particular, constraint representation (CR) is first applied to interpret the process of SR from perspective of participation degree (PD). Then, a relaxed and adaptive spatial constraint via superpixel segmentation is imposed to transform the individual PD to local relative activity degree (RAD). The final classification is determined based on a concise RAD-driven mechanism. Experimental results on real data set demonstrate the efficiency of the proposed 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.

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.

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.

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.