Remote sensing change detection (RSCD) has become an essential tool in observing and analyzing geographical information. However, existing deep learning approaches dependent solely on visual modalities may encounter challenges in discerning subtle variations amidst noise interference. To overcome these issues, we propose a multiscale semantic-guided synergistic interaction network (MSSI-Net), which utilizes the advanced multimodal semantic representations for enhancing the capacity to perceive hierarchical changes. Specifically, we first devise a multiscale interaction module (MIM) which leverages multiscale attention mechanism to guide the interaction between the coarse and fine stages of different visual features. The fine-grained visual features subsequently complement the semantic features through scale weight reassignment to enhance the discriminative capability of vision-language features. Furthermore, driven by the semantic-guided synergistic interaction mechanism, our developed cross-modal feature fusion module (CFFM) exploits both homogeneous and heterogeneous features among modalities. This ensures that the generated vision-language features are semantically representative. Finally, we formulate a manifold differential perception head (MDPH) to optimize the detection of changes by efficiently fusing diverse differential feature representations, achieving comprehensive performance enhancement. Extensive experiments conducted on four benchmark datasets (LEVIR-CD, CDD, SYSU-CD and WHU-CD) indicate that the designed MSSI-Net achieves state-of-the-art performance compared to existing methods.

UAV remote sensing image registration has a wide range of applications in the fields of fine geographic information extraction, environmental change monitoring, agriculture and forestry, serving as a fundamental and critical step in supporting various applications. However, existing registration methods often extract fewer feature points, uneven distribution and poor stability when faced with significant changes in land features. Accordingly, in this paper, we propose a UAV remote sensing image registration method based on an improved SuperPoint+SuperGlue deep learning network. We add a feature point extraction branch to the shallow feature map in the SuperPoint network, and add the newly extracted feature points to the existing feature points, and then perform non-maximum suppression (NMS) for further refinement. This enhances its capability to extract image feature points, resulting in more accurate and evenly distributed positions of these points. The experiments carried on two sets of real UAV datasets indicate that our method outperforms several typical registration approaches in terms of registration accuracy and detection efficiency.

Radar jamming recognition is a fundamental step for anti-jamming techniques. However, the recognition performance is impeded in insufficient samples situation. Ensemble learning provides an effective way to address this issue. In this paper, first, a novel ensemble learning-based radar Transformer (i.e., RadarTR-E) is proposed to improve recognition performance with insufficient samples. Specifically, it votes on the predictions among sub-recognizers to increase recognition accuracy, where RadarTR is employed to effectively capture long-range dependencies. Then, a dynamic label smoothing method (i.e., RadarTR-E-DLS) is further proposed to mitigate overfitting. In detail, dynamic soft labels are designed to prevent overconfidence towards certain radar jamming types. Therefore, the proposed RadarTR-E-DLS achieves better recognition accuracy. Compared with other advanced methods, the experimental results show the superior recognition performance of the proposed methods.

In the field of remote sensing, the detection of tiny objects has always been an interesting and highly regarded issue. Although many researchers have dedicated their efforts to studying this problem, it still presents numerous challenges due to the complexity of the environment in which tiny objects are presented in remote sensing images. To this end, we propose a remote sensing image tiny objects detection method based on explicit semantic guidance, with a specific focus on regions containing tiny objects. Specifically, we incorporate supervision of the tiny object regions during the training process. This supervision allowed us to extract tiny object regions, thereby forming an explicit attention map. This explicit attention map is employed to semantically modulate the feature map for detecting tiny objects, thus enhancing the regions containing tiny objects while suppressing the background. Extensive experiments are conducted on the AI-TODv2 dataset and the proposed method can achieve an AP of 24.6%. The experimental results demonstrate the effectiveness of the proposed tiny object detection method based on explicit semantic guidance. The code will be released soon on the site of https://github.com/dyl96/ESG_TODNet.

In practical applications, due to the high cost and difficulty of hyperspectral image (HSI) annotation, labels for the target domain (TD) may be either unavailable or insufficient in quantity. To address this issue, we propose a multi-source domain generalization two-branch network (MDGTnet) and train the model only using source domain (SD) HSIs with contrastive learning to classify an unknown TD image. MDGTnet consists of a classifier and two branches, which are intra-domain uniqueness extraction branch (intra-DUEB) and inter-domain commonality extraction branch (inter-DCEB). The intra-DUEB is responsible for mining internal attributes of each SD, which can be seen as imaging environmental characteristics. And the inter-DCEB is applied to extract generic features among different SDs. The features extracted by two branches are fused at different levels respectively to remove the influence of different imaging environments for discriminative class features. We have conducted extensive experiments on four public HSI datasets. The results show that the proposed method outperforms state-of-the-art methods. It can learn robust models and extract highly discriminative features, leading to excellent performance in HSI cross-domain classification. Especially on the Pavia Center dataset, the overall accuracy (OA) is 2.47% higher and kappa coefficient is 2.92% higher than the best results of the other methods. The code will be released soon on the site of https://github.com/Cherrieqi/MDGTnet.

The majority of existing object detection models struggle to fully exploit the intimate relationship between scene context and objects, and the feature fusion and proposal generation strategies tend to be relatively basic, resulting in poor model performance. To address these issues, we propose an object detection model based on adaptive multilevel fusion refinement network. Firstly, we propose an adaptive gated fusion network that dynamically assesses correlations between objects and scene information, generating a gated feature map to guide feature fusion and extract discriminative joint object-context features. Next, a proposal refinement model is proposed. By utilizing a learnable correlation-weighted coefficient, this model effectively merges low-level features with joint features, thereby mitigating spatial information deficits. We also propose an adaptive multidimensional offset strategy, which minimizes the impact of regression deviations on proposal quality by combining information offsets and spatial offsets. To optimize all subtasks, a novel multi-task loss function is proposed. Evaluated on the DOTA and HRSC2016 datasets shows that our method is superior to compared methods in object detection and harvests 77.26% and 90.68% mean average precision, respectively.

Tiny object detection in the field of remote sensing has always been a challenging and interesting topic. Despite many researchers have been working on this problem, it has not been well solved due to its complexity. In this paper, we analyze the reasons for the poor performance of deep learning-based object detection methods for tiny objects in remote sensing images. Moreover, we propose a new remote sensing image tiny object detection network based on object reconstruction and multiple receptive field adaptive feature enhancement module (MRFAFEM), called ORFENet. Detailedly, object reconstruction aims to reduce the information loss of tiny objects within deep neural networks, which is only used in the training phase and can be discarded in the inference phase. MRFAFEM is designed to enhance the features for detecting tiny objects by dynamically adjusting the multiple receptive field features. We have conducted several experiments on the AI-TODv2 and LEVIR-Ship datasets, both of which are proposed for tiny object detection in remote sensing images. The experimental results indicate the effectiveness of the proposed method. Specifically, the proposed ORFENet can achieve the AP of 24.8% on the AI-TODv2 dataset and 83.3% AP50 on the LEVIR-Ship dataset. The code will be released at https://github.com/dyl96/ORFENet.

Infrared small target detection has significant applications in airspace surveillance, warning systems and so on. Detection of infrared small targets on a single image frame is a challenging work. First of all, compared to generic object detection, infrared small targets have the characteristics of low signal-to-clutter ratio, various sizes, and shapes. In addition, false alarm sources in the complex environment also impede precise detection. In the past years, scholars have performed many studies on infrared small target detection. The majority of traditional single-frame-based methods rely on the gray-scale discontinuity between the target and the neighborhood to detect infrared small targets. However, these traditional methods rely on prior assumptions. And when the real scenarios change dramatically, it is difficult to use fixed hyperparameters to handle such variations. As we all know, the deep convolutional neural network (CNN) can automatically learn the hierarchical features of images. However, CNN-based methods could not be directly applied for infrared small targets which are even small to several pixels because the pooling layer in the networks may result in the loss of targets.

The primary task of hyperspectral anomaly detection (HAD) is to distinguish targets with noticeable spectral variances from their surroundings. Background purification for dictionary construction is vital for representation based HAD. In this letter, we present a novel HAD method based on background purification via deep autoencoding gaussian mixture Model. First, the low-rank representation (LRR) model is applied to separate the sparse anomalies from the low-rank background component. Secondly, we innovatively apply the deep autoencoding gaussian mixture model (DAGMM) for dimensionality reduction and background purification, which combines the feature mapping and Gaussian density estimation for joint training in the deep latent space. In addition, we propose a dictionary construction strategy based on the gaussian mixture model, achieving the exclusion of possible anomalies and inclusion of background features. Experiments on two real datasets illustrated the superior performance for HAD task of the proposed method.

We proposed a learned masked robust principal component analysis (LMRPCA) algorithm for single-frame infrared small target detection. Firstly, the original images are constructed into patch images, which are separated into low-rank and sparse components corresponding to the backgrounds and foreground masks. The optimization function is solved by alternating directions of multipliers method (ADMM), which is mapped to trainable convolutional layers. We use elements of convolutional sparse coding to improve representation learning for foreground masks and side information in the auxiliary transform domain. By doing so, we assign learnable weights to different feature maps by using a reweighted−l1− l1minimization. Numerical experiments show that our proposed LMRPCA can segment and locate the targets precisely.

Lightweight object detection and recognition models are extremely crucial for in-orbit applications, which is the most critical factor for whether deep learning-based object detection and recognition algorithms can be applied to remote sensing satellites for real-time or near real-time processing. Global information is extremely important for object detection and recognition of remote sensing images. However, due to the high computational cost, the existing CNN-based lightweight models over-emphasize on the extraction of local information, while ignoring the global information. For this reason, we propose a lightweight object detection and recognition model (Lightweight Global-Local Detection, LGLDet) based on the especially light global modeling structure. In LGLDet, light global-local module (LGLM) is proposed to extract the global and local information. The LGLM consists of Point2Patch Non-Local (P2PNL), local branch and skip connection. Specifically, P2PNL is proposed to reduce the computation of global long-range dependency modeling. In addition, the feature fusion part and detection head are also designed in a lightweight way. In the experiments, the proposed method can achieve optimal performance with fewer parameters and lower computational complexity than existing CNN-based lightweight models and transformer-based lightweight models with similar parameters or computational complexity. The code will be released on the site of https://github.com/dyl96/LGLDet.

Automatic road detection from remote sensing images has always been a significant research topic. It is of great value to many practical applications. However, there are still some problems need to be solved. First of all, most of existing road detection methods are inefficient because of the sequential processing of the decoder head. Secondly, some existing methods are unable to detect occluded road areas effectively. For this reason, we focus on the speed and occlusion problems in road detection network, and propose a new lightweight road detection method based on multi-scale convolution attention network (MSCAN) and coupled decoder head, LRDNet. In particular, LRDNet adopt multi-scale convolution attention network with large receptive field for feature extraction to solve the occlusion problem, and decode the road surface, road edge and road centerline in a coupled way to improve the speed of road detection and ensure that the road surface detection results have fewer burrs at the road edge. We have performed several experiments on the RNBD dataset. Compared with some state-of-the-art methods, the experimental results prove the validity of the proposed LRDNet. The code will be released soon on the site of https://github.com/dyl96/LRDNet.

With the rapid development of earth observation technology, the fusion of multisource remote sensing (RS) data, has become an important research field in land cover classification. Particularly, the fusion of hyperspectral image (HSI) and light detection and ranging (LiDAR) data, which can provide complementary information to each other, has attracted an increasing attention for land cover classification tasks. However, most of the existing methods focus on multi-source information fusion on feature level and ignore the discrepancy of the land covers with the same label among different kinds of viewpoints, which limit the further improvement of classification performance. So, this paper proposes a novel HSI-LiDAR classification method based on multi-view feature learning and multi-level information fusion, which consists of a multi-view data representation (MVDR) strategy, a multi-branch dual-channel graph convolutional networks (MB-DCGCNs) model and a progressively high-confidence label assignment (PHCLA) scheme. MVDR is designed by jointly utilizing multiple attributes of spatial information and multi-source RS data to re-express multi-source land covers with diversity and complementarity. The MB-DCGCNs model which aims at integrating spectral-spatial-elevation information on feature level is employed on the above multi-view re-expressed HSI-LiDAR data to explore land cover feature representations from different views. Furthermore, a PHRLA scheme is proposed to classify the land covers with high-reliability by a combination of decision-level label prediction and pixel-level label assignment. Comparative experiments on two benchmark datasets with several state-of-the-art classification methods validate the effectiveness and superior performance of the proposed method.

Detection of infrared dim and small targets with diverse and cluttered background plays a significant role in many applications. In this paper, we propose a deep low-rank and sparse patch-image network, termed as Deep-LSP-Net, to effectively detect small targets in a single infrared image. Specifically, by using the local patch construction scheme, we first transform the original infrared image into a patch-image, which can be decomposed as a superposition of the low-rank background component and the sparse target component. The target detection is thus formulated as an optimization problem with low-rank and sparse regularizations, which can be solved by the alternating direction method of multipliers (ADMM). We unroll the iterative algorithm into deep neural networks, where a generalized sparsifying transform and a singular value thresholding operator are learned by the convolutional neural networks (CNNs) to avoid tedious parameter tuning and improve the interpretability of the neural networks. We conduct comprehensive experiments on two public datasets. Both qualitative and quantitative experimental results demonstrate that the proposed algorithm can obtain improved performance in small infrared target detection compared with state-of-the-art algorithms.

Long-wave infrared (LWIR) bands in multispectral datasets are extremely useful in many applications. However, the LWIR bands usually suffer from undesirable stripe noise, which impedes their further application. Compared with emission-dominated LWIR, the mid-wave infrared (MWIR) bands containing both emitted and reflected radiation usually exhibit higher image quality. In this article, we propose a novel two-stage MWIR energy separation and image guidance (MES-IG) algorithm to destripe the LWIR images with the assistance of the MWIR bands. In the first stage, we decompose the MWIR image into the emitted and reflected components by solving a constrained optimization problem. Specifically, we impose the low-rank penalty to enforce the similarities between MWIR and LWIR, and we use the total variation (TV) regularization to exploit the similarities between MWIR and visible and near-infrared (VNIR) images. In the second stage, the obtained emitted component of MWIR is considered as the guidance image to remove the stripes in the LWIR images by adopting the 1-D guided filter algorithm. Numerical experiments on the Chinese Gaofen-5 satellite and the Moderate Resolution Imaging Spectroradiometer (MODIS) data demonstrate the utility of the proposed method in providing improved LWIR image destriping performance over the state-of-the-art algorithms.

Small infrared target detection is a significant technique in both civil and military applications. Regularized optimization methods that exploit both the sparsity and the low-rank prop-erties of the infrared image have achieved good performance. In this paper, we propose to unroll the sparse and low-rank regularized model to a deep neural network to effectively sep-arate the infrared target and the background. Specifically, we adopt the infrared patch-image (IPI) model to transform the original infrared image into a patch-image using local patch construction. A deep network flow graph is proposed by si-multaneously exploiting a learned low-rank prior and a spar-sity prior to promote the target detection performance. Exper-imental results demonstrate that the proposed IPI-net is able to provide improved performance in small infrared target de-tection compared with the state-of-the-art algorithms.

Hyperspectral images (HSIs) can provide abundant and diverse features which are helpful for classification, such as spectral, texture, and shape features. Combining these features can enhance the ability to describe the characteristics of different classes of land covers. However, most of the existing methods usually stack features from multiple views to construct high-dimensional data and then learn information from it which may waste information inherent in different feature spaces. In this letter, we proposed a multiview spectral–spatial feature extraction (FE) and fusion framework for the analysis and classification of the HSIs. First, different and complementary spatial features extracted by extended multiattribute profiles (EMAPs), gray-level cooccurrence matrix (GLCM), and Gabor from the original HSI are, respectively, stacked with the spectral bands to construct multiview data set for one single scene of HSI. Thus, each sample can be represented in different spectral–spatial domains. Then, a semisupervised FE method, which combines local fisher discriminant analysis (LFDA) that explores discriminative information from limited labeled samples and the improved neighborhood preserving embedding (NPE) that aims at maintaining the local neighborhood structure from a global perspective, is applied on the multiview data set to eliminate redundant information and obtain multiview spectral–spatial features. Note that the improved NPE which adds spatial interpixel correlations to similarity measure between samples is applied on all the samples rather than unlabeled samples, and hence, the best spatial nearby neighbors for each sample could be found from the whole data. Finally, we integrate these multiview features with diversity and complementarity to construct the intact feature representation for each sample. The experimental results show that the proposed method outperforms the state-of-the-art multiview FE methods for HSI classification.

Hyperspectral images (HSIs) have been utilized in various fields due to abundant information, whose application is to a great extent limited by the number of labeled samples. Hence, how to exploit the diverse and complementary characteristics of multiple information from different views inherent in the HSIs is very critical for improving the classification performance under the condition of small-sized training set. This letter presents a novel method to tackle the small labeled sample size problem with semisupervised self-learning (S3L) and multiview information fusion. First, a sample augmentation scheme based on S3L and high-reliable neighborhood structure is designed for realizing training set enlargement. Thus, the pseudo-labeled samples with high-quality would be automatically picked out from the unlabeled data by exploiting complementary information from multiple views, i.e., semantic information, spectral bands, texture and geospatial information. Then, we retrain the classifier by the enlarged training set and generate an intermediate classification map. Finally, we simultaneously utilize the location and gradient information of the samples to adaptively realize the refined landcover classification. Experimental results on three widely-used data sets compared with several representative methods for small-sized HSI classification validate the effectiveness of the proposed method.

Due to the difficulty and time-consuming of labeling ground truth map in practical situations, unsupervised multiple change detection (MCD) for multispectral images (MSIs) have attracted much attention in recent years. One possible strategy to obtain multiple changes is to assign labels to the binary change result. However, some methods are difficult to obtain the accurate binary result because of the complexity of backgrounds; moreover, assigning labels is also a challenge owing to the limitation of the number of spectral channels in MSIs. Therefore, we propose a novel unsupervised MCD framework based on auto-updating multitemporal matrix factorization (AMMF) and spatiospectral channel augmentation (SSCA). In AMMF, the accurate binary change result can be detected based on joint matrix factorization, during which the distribution and subspace information of each temporal image are regularized to encode the spatiotemporal correlation. In SSCA, some novel augmentation strategies are introduced to increase the number of channels in MSIs to form the normalized high-dimensional maps for each temporal image based on nonlinear operations and convolutional sparse analysis, respectively. MCD can be achieved by integrating the binary change result and directional information that can be calculated by high-dimensional maps of different temporal images. Experiments are conducted on two real MSIs, indicating that the proposed framework performs well in detecting multiple changes.

Automatic road detection has always been an important research problem in the field of remote sensing image processing, which is of great significance for many applications. However, many road areas cannot be effectively detected and the existing road detection methods suffer from unsmooth edges due to shadow phenomena and the occlusion of objects such as trees. For this reason, we propose a cascaded automatic road detection network based on edge sensing module and attention module, called CasEANet. CasEANet consists of three tasks including road surface detection, road edge detection and road centerline extraction. An encoder-decoder structure integrating edge sensing module and attention module is applied to detect the road surface. In order to obtain smoother road edges, the edge sensing module is designed to enhance the perception of road edges. The attention module is employed to guide the network to reinforce the perception of global information, aiming to solve the problem of discontinuity in the detection of road surfaces that are obscured by trees. The centerline extraction is adopted to assist the training of road surface detection. Experiments performed on the RNBD dataset prove the effectiveness of CasEANet. Specially, the F1 score, overall accuracy and balanced error rates of the CasEANet are 0.946, 0.986 and 0.0219 respectively, outperform the other state-of-the-art methods. The code will release soon on https://github.com/HITLDY/CasEANet.

Automated shadow detection is an important research problem in the field of remote sensing image processing. The shadow regions seriously affect the interpretation of the remote sensing images. However, the existing methods have poor detection effect for small shadow regions, and the ability to distinguish between weakly illuminated regions and shadow regions is insufficient. For this reason, we propose a shadow detection network based on multiscale spatial attention mechanism for aerial remote sensing images, called MSASDNet. First, the backbone based on residual block is employed to extract the preliminary features of the input image. Then, we design a multiscale feature extraction module based on the spatial attention mechanism to extract multiscale features with spatial attention information, which can suppress the influence of complex nonshadow regions on the detection and improve the detection ability of small shadow regions. Finally, the decoder structure based on deconvolution is used to predict the shadow mask from the combined feature. Experiments performed on the Aerial Imagery dataset for Shadow Detection (AISD) dataset demonstrate the superiority of MSASDNet in terms of quantitative and qualitative comparison with several state-of-the-art methods. The code will release soon inhttps://github.com/HITLDY/MSASDNet.

Compared with visible and near-infrared images, the long-wave infrared region hyperspectral image (LWIR HSI) is more vulnerable to noise pollution in the acquisition process due to its specific imaging mode. In this letter, a new restoration method is proposed using total variation based on bidirectional estimation and brightness temperature smoothing (BBSTV), which can remove dead lines and restore junk bands effectively. The proposed method introduces the linear relation between brightness temperature and emissivity derived from radiative transfer model (RTM) to restoration processing. Besides, bilateral estimation is used to complete the loss information of noise-polluted bands to achieve a faster convergence speed of total variation (TV) method. Both simulated and real LWIR HSI experiments were conducted to verify the improvements of the BBSTV method in quantitative and qualitative ways.

Cloud contamination is a common phenomenon in the optical remote sensing field, which limits their application in land surface studies and causes the waste of satellite images. This letter presents a new framework for removing thin clouds from visible images based on multiscale dark channel prior (MDCP). The cloud removal of cloudy images (target images) is carried out with the assistance of a different temporal cloudless image (reference image) from the perspective view of multiscale transform (MST). In order to make it more suitable for the application of thin cloud removal, two improvements are made to this traditional fusion method. For one thing, a dark channel prior module is integrated into the low-frequency component of the target image in the framework of MST. For another, we choose the weighted average for high-frequency components and sparse representation (SR) for low-frequency components as fusion rules. After the fusion process, the modified Laplacian sharpening whose model is optimized is carried out. The performance of MDCP was evaluated with both simulated and real cloudy images. Experimental results show that the proposed MDCP has a good performance.

Most of the existing saliency detection methods are affected by the complex background and weak contrast in remote sensing images (RSIs), which easily leads to confusion between salient object and background. To solve this problem, we present a general space–frequency joint saliency detection method based on spatial contrast analysis (SCA) and adaptive spectrum analysis (ASA). The proposed SCA constructs a spatial distribution function to give higher saliency to bright elements with similar appearance and compact distribution, which can avoid the interference of similar elements in the background. In addition, for the weak contrast-level salient object, an adaptive spectral energy function is proposed in ASA by combining regional dispersion and frequency spectrum characteristic, which can make full use of frequency spectrum and obtains the complete information of salient object. Finally, the SCA and ASA information are fused by a joint optimization module, which is proposed to integrate the saliency of different contrast levels objects; thus, the final saliency maps are obtained. Evaluated on the extended optical remote sensing saliency detection (EORSSD) dataset and our dataset, the proposed method is superior to other five classical methods in RSI saliency detection.

This letter presents a novel method for hyperspectral image (HSI) restoration, which aims to improve the removal effectiveness of the sparse noise. In contrast to the existing approaches that employ the$L_{1}$-norm for tractable optimization, we apply the non-convex non-smooth$L_{0}$-norm to measure the sparsity of the impulse noise, stripes, deadlines, and other outliers accurately. By combining the low-rank and total variation (TV) priors to exploit the intrinsic properties of the clean HSI and using the patch scheme to preserve local features, the$L_{0}$-PLRTV restoration model is established. In order to deal with the optimization problem, we introduce an equivalent primal-dual formulation to reformulate the$L_{0}$-norm term, and develop a minimization approach for the objective function based on the alternating iterative method. The simulated and real data experiments confirm that the proposed algorithm can effectively reduce the sparse noise in HSI.

The degradation of spaceborne hyperspectral images (HSIs) usually results from various types of noise. In this letter, we propose a 3D hybrid higher degree total variation regularized nonconvex local low-rank tensor recovery (H2DTV-NLRTR) model to restore the HSIs. Inspired by the good performance of the higher degree total variation penalty in image denoising, we first develop a 3D hybrid higher degree total variation penalty term, which is able to capture the fine image details and edges along the spatial dimensions and spectral dimension. The tensor multi-Schatten-pnorm is chosen as the relaxation of the low-rank tensor constraint, which can not only separate the low-rank clean HSI patches from noisy images effectively but also improve the computational efficiency. The proposed H2DTV-NLRTR model can simultaneously characterize the spectral correlation and the spatial structure of the HSI dataset by incorporating the H2DTV penalty in the nonconvex local low-rank tensor recovery problem. In addition, we adopt a fast iterative majorize-minimize algorithm to efficiently solve the corresponding optimization problem. The numerical experiments on both simulated and real HSI datasets demonstrate that the proposed algorithm provides consistently improved restoration results compared with the state-of-the-art algorithms.

When it comes to multisource collaboration issues, previous registration-based studies always attempt to build reliable connections between two sources. However, these pixel-oriented algorithms often highly rely on mapping functions or require other auxiliary data. In this letter, a target-oriented multisource association model (ToMsAM) is proposed. It is a new perspective of multiinformation integration driven by practical applications in remote sensing. The two main parts in ToMsAM gradually use the similarity information in pixel and feature level. First, to cover the comprehensive prior information, a triple-unit-graph is built. Then, a feature-constraint deep neural networks for graph representations (FC_DNGRs) model is adopted to automatically learn the compressed representation. So far, the heterogeneous samples are unified in a new feature space. These new abstractions associated with the source domain can solve the problem of insufficient samples in the target domain. Real remote sensing images acquired by synthetic aperture radar (SAR) and optical satellites are utilized to conduct experiments on airplane and vessel detection tasks. Experimental results show that the representation obtained by ToMsAM outperformed the baseline representations. The support vector machine (SVM) trained by associated features can complete the detection tasks even in the case of limited quantity of prior samples in the target domain.

With the wide application of deep learning (DL), change detection (CD) for remote-sensing images (RSIs) has realized the leap from the traditional to the intelligent methods. However, many existing methods still need further improvement in practical applications, especially in increasing the effectiveness of feature extraction and reducing the model computational cost. In this article, we propose a novel deep multiscale Siamese network with parallel convolutional structure (PCS) and self-attention (SA) (MSPSNet), which has excellent capabilities of feature extraction and feature integration under an acceptable consumption. It mainly contains three subnetworks: deep multiscale feature extraction, feature integration by the PCS, and feature refinement based on the SA. In the first subnetwork, a deep multiscale Siamese network based on convolutional block is designed to depict the image features at different scales for different temporal images. In the subsequent subnetworks, a PCS model is proposed to integrate multiscale features of different temporal images, and then, an SA model is constructed to further enhance the representation of image information. Experiments are conducted on two public RSI datasets, indicating that the proposed framework performs well in detecting changes.

Anomaly detection in a hyperspectral image (HSI) has been actively researched in the field of remote sensing due to its significant application requirements. Traditional methods were based on the spatial models for the background to detect the anomaly targets. However, in detecting the spectral anomaly targets, they led to two problems: 1) the spatial characteristics of spectral anomaly targets are not obvious, which causes many false alarms in detection and 2) spectral anomaly usually occurs in the local band of targets, while the rest of the spectrum is similar to the ones of surrounding backgrounds, which leads to missed detection. This article proposes a novel hyperspectral anomaly detection method for spectral anomaly targets based on spatial and spectral constraints (SASCs). This model finds suspected anomaly target part as spatial anomaly results through SASCs. Then, the feedback process determines the spectral anomaly through the spectral difference between the tested pixel and the surrounding background. It is fed back to the spatial anomaly results to obtain final detection results. Furthermore, in order to enlarge the spectral difference between anomaly and background while suppressing the background, the optimal order of fractional Fourier transform (FrFT) is determined by combining spatial anomaly results with the uncertainty principle, which is used in FrFT of HSI. Experimental results show that the proposed method suppresses the background and reduces the false alarm rate. The feedback mechanism effectively reduces the missing detection rate, achieving a promising detection accuracy.

Anomaly detection is a hot topic in the field of hyperspectral image (HSI) processing, which aims to find anomalous targets through spatial and spectral differences from a complex background. However, there still remains two unsolved problems in anomaly detection methods: 1) since the global image covers more complex scenes, it inevitably suffers a lot of false alarms in the anomaly detection and 2) the sensitivity of the target to the global mode or the local mode detector is different. A detector that only considers one mode usually misses some targets, which makes the detection rate low. This article proposes an anomaly detection method for HSIs with potential target region extraction. The potential target region is extracted through the combination of the tensor robust principal component analysis (RPCA) and the curvature circle model. The obtained subregions are used in the region traversing method to filter out the areas not containing the target. In addition, in order to adapt to the different targets contained in the region, the proposed method combines the isolated forest of the global model and the statistical correlation of the local model, thereby enhancing the separability of the target and the background. Experimental results show that the proposed method can effectively extract potential target regions and greatly reduce the false alarm rate. Furthermore, the proposed method can highlight the target for a higher detection rate and accuracy.

Anomaly detection is an active topic in hyperspectral image processing. Recently, low-rank representation (LRR)-based approaches have shown satisfactory results in wide anomaly detection applications. However, the existing LRR methods still have the following two problems: i) Setting a fixed value as a termination condition of the iterative constraint often results in the loss of target information, leading to a low detection rate with some missing targets. ii) Noise after LRR still remains in the sparse part, which increases false alarms. This paper proposes the tensor approximation with LRR and the kurtosis correlation constraint method for anomaly detection. The hyperspectral image is regarded as a third-order tensor for the LRR process. In the optimization process, the background suppression degree is obtained through the background dictionary to determine the iteration termination condition. After the iterative optimization is completed, the low-rank tensor that can fully represent the background is obtained. Also, the difference between the original hyperspectral image tensor and the low-rank tensor is used as the input of the kurtosis correlation constraint. The kurtosis correlation constraint compares the similarity between the current pixel and its surrounding pixels to detect the anomaly, where the kurtosis in the high-order statistical feature is introduced to avoid the interference of noise. The experimental results illustrate that the proposed method can retain the complete target information to highlight targets while suppressing background.

In hyperspectral image classification, deep learning (DL) based on abundant training samples has demonstrated its significance in classification performance. However, due to the limitation of available samples and the imbalance/similarity of classes in small-sized datasets, data-driven DL algorithms can hardly extract representative and effective features for interclass classification, and the subtle diagnostic spectral features for intraclass classification are easily covered or lost in the iterative feature extraction (FE). The restricted FE of interclass/intraclass results in the accuracy reduction and performance limitation of refined classification. To mitigate these issues, an attention network with multiscale receptive fields (MRFs) is proposed, embedding an inversion subnet for relative water content retrieval (RWCR). In classification, the three critical parts in the proposed network, namely, MRFs, embedded subnet, and multiple-attention mechanism, are responsible for multiscale feature merging, relative water content (RWC) feature enhancement, and paying attention to bands, channels, and multiscale features, respectively. The ablation studies on small-sized datasets show the accuracy improvements of interclass and intraclass in refined classification, which verifies the effectiveness of critical parts for extracting representative features and taking RWC features as the diagnostic biochemical signature from unbalanced and similar classes. The comparison results with typical DL models demonstrate the superiority of the proposed network. Moreover, the competitive advantage of the proposed network is demonstrated in comparison with traditional and state-of-the-art HSI classification methods.

Multiclass geospatial object detection in high spatial resolution remote sensing imagery (HSRI) is still a challenging task. The main reason is that the objects in HRSI are location-variable and semantic-confusable, which results in the difficulties in differentiating the complicated spatial patterns and deriving the implicitly semantic labels among different categories of objects. In this article, we propose a relation-augmented embedded graph attention network (EGAT), which enables the full exploitation of the underlying spatial and semantic relations among objects for improving the detection performance. Specifically, we first construct two sets of spatial and semantic graphs of objects–objects for object relations modeling. Second, a Siamese architecture-based embedding spatial and semantic graph attention network is designed for relations reasoning, which is implemented by introducing the long short-term memory (LSTM) mechanism into the EGAT, for learning the relations among different categories of intraobjects and interobjects. Driven by the spatial and semantic LSTM, the EGAT-LSTM can adaptively focus on the critical information of reason graphs for spatial–semantic correlation discrimination in the embedding non-Euclidean feature space. By this way, the EGAT-LSTM can effectively capture the global and local spatial–semantic relationships of objects–objects, and then produce relations-augmented features for improving the performance of object detection. We conduct comprehensive experiments on three public datasets for multiclass geospatial object detection. Our method achieves state-of-the-art performance, which demonstrates the superiority and effectiveness of the proposed method.

We present a deep sensor fusion method based on frustum point single shot multibox detector (PointSSD) for autonomous driving scenarios. The proposed method solves the problem of precision degradation in frustum PointNets (F-PointNet) caused by relying heavily on 2D detection and making insufficient use of RGB information. The method mainly consists of two subnetworks: pyramid segmentation network (PSNet) and PointSSD. The proposed PSNet uses a novel architecture capable of performing semantic segmentation on RGB information to generate high quality image semantic information. Using these image semantic information, point cloud semantic information is obtained through projection and is then fused with raw 3D spatial features by deep fusion. The fusion results are processed by PointSSD, which is proposed for classification and bounding box regression. Evaluated on the KITTI dataset, our method is superior to other methods in 3D classification and 3D localization. In addition, our method guarantees robustness to 2D false detections.

Long-wave infrared (LWIR) images have important applications in retrieving land surface temperature. However, LWIR images are often inevitably suffered from stripe noise, a special type of spatial domain fixed pattern noise. This paper proposes a novel spectral separation algorithm for LWIR image destriping. Specifically, since the mid-wave infrared (MWIR) bands contain both radiant and reflective energy, we use MWIR as reference images to remove the stripe noise in the LWIR bands. We formulate the spectral separation problem as a convex optimization problem, where the difference between LWIR and the radiant component of MWIR, and the difference between the visible and near infrared (VNIR) image and the reflective component of MWIR are regularized to exploit the similarities between the corresponding bands. The obtained radiant component is then utilized to recover the LWIR band. Experimental results using Gaofen-5 datasets demonstrate that the proposed algorithm has good performance in removing the stripe noise.

Remote sensing images contaminated by clouds cannot be used for target recognition, image classification, and other applications, which leads to a lot of remote sensing data being wasted. We propose a low-rank and sparse constrained dark channel prior for cloud removal in remote sensing image sequence (LRSC-DCP). The sparse and low-rank constraints are used to find the position of thick clouds and remove thick clouds in cloud-contaminated images respectively. The remaining thin clouds can be eliminated by the dark channel prior. We compare the algorithm proposed in this article with the dark channel prior. Experimental results prove that the proposed method has better performance.

Hyperspectral image (HSI) classification methods based on deep learning (DL) algorithms have achieved significant improvements on abundant samples. However, due to the limitation of practically available samples, the difficulty of representative feature extraction from small-sized samples and the loss of subtle diagnostic features in DL iteration results in the accuracy reduction of interclass and intraclass in refined classification, respectively. To address these issues, a water retrieval embedded deep network is proposed in this paper. The relative water content retrieval (RWCR) of the proposed network is embedded as a subnet, which is responsible for extracting subtle diagnostic features of relative water content (RWC) to enhance the representation of features in classification. The experimental results verify the effectiveness of RWCR for improving the interclass and intraclass accuracy in refined classification. Moreover, the superiority of the proposed network is also demonstrated in comparison with state-of-the-art methods.

In hyperspectral image (HSI) classification, the distinction of similar classes has always been a focus of research. In this paper, a new classification module named class confusion merging (CCM) is proposed to improve the classification accuracy, especially for classes with the similar spectral feature. In CCM processing, the merging matrix is firstly constructed based on the confusion matrix to measure the similarity between different classes. Then similar classes are merged as big categories. Finally, for each big category, soft band selection is implemented based on the spectral difference of contained classes for reclassification. To evaluate the performance of CCM, real image experiments are conducted in comparison with no CCM module hyperspectral classification methods. The experiment results demonstrate that the CCM module can improve the classifier performance by providing higher classification accuracy.

The cloud-contaminated phenomenon in the field of remote sensing has a serious impact on image processing so that a large number of images are unusable. To achieve cloud removal for single visible image, we propose a novel method based on modified dark channel prior with multiple scale (MDCPMS). In the structure of multiple scale, the cloudy image is firstly decomposed into high-frequency and low-frequency components. The former is uniformly amplified to enhance its weak contour, and the latter is processed by modified dark channel prior (DCP), whose estimation of atmospheric light is optimized for better cloud removal. Finally, the cloud-removed image is obtained through multi-scale reconstruction. Experimental results show that the proposed MDCPMS obtains a significant performance with slightest color distortion and is closest to the corresponding real image, compared with DCP and nonlocal method.

Multiclass geospatial object detection is a vital fundamental task for many remote sensing applications. However, it still faces several challenges in very high-resolution (VHR) images in remote sensing, such as the ambiguity of object appearance and the complexity of spatial distribution. In this letter, we propose a novel Siamese graph embedding network (SGEN) that leverages the spatial and semantic information to jointly extract the high-level feature representation for object detection. The main purpose of our SGEN is to learn an embedding discriminative feature space that strengthens the interclass compactness while alleviating the intraclass separability. Specifically, we first design a novel contrastive loss in terms of spatial dependence and semantic correspondence for graph similarity metric learning (ML). Then, the SGEN architecture is adopted for spatial and semantic similarity learning by training the novel contrastive loss function. The SGEN model contains two-stream graph convolutional networks (GCNs) for ML, which is helpful to capture the discriminative features. At last, these extracted features with high spatial and semantic discrimination are served to improve the performance of object detection. The comprehensive evaluations on a combined data set consisting of two public object detection data sets demonstrate the effectiveness of the proposed method.

Acquiring training samples in remote sensing images is always expensive and time-consuming. As a consequence, it would be preferable if one domain without training samples (the target domain) could be classified givena prioriknowledge from another domain (the source domain). In this letter, an iterative training sample updating (ITSU) approach is proposed based ona posteriorispatial feature extraction. First, the classifier is trained with initial training samples from the source domain and applied to the target domain, producing a preclassification map. Then, as an invariant feature, thea posteriorispatial features are extracted with a guided filter. Based on the spectral features and thea posteriorispatial features, a criterion measuring the similarity of the cross-domain samples is defined. New training samples from the target domain are assigned with pseudo-labels, and the original samples in the source domain are removed. Furthermore, thea posteriorispatial feature maps are fed back to the input images, and new classifiers are trained with an updated training sample set in the updated feature space. This procedure is repeated until the stopping rule is satisfied. Finally, the adapted classifier is obtained based on the updated training samples. The experimental results on three hyperspectral data sets indicated that ITSU achieved the best performance compared with the other two state-of-the-art methods.

The disadvantage of low resolution and low signal-to-noise ratio (SNR) of thermal infrared (TIR) data makes it difficult to be applied in practice, although it has been studied for decades. In contrast, visible and near infrared (VNIR) and shortwave infrared (SWIR) data have higher resolution and SNR. In this letter, an ensemble extreme learning machine (EELM) is proposed, which is based on the extreme learning machine (ELM), to fuse together VNIR, SWIR, and TIR to improve TIR resolution and SNR. The associated ELM nets are trained with correlated training data which are selected from the random forest method. The temperature estimation cube can be obtained after putting SWIR data and VNIR data into these networks. Finally, the cube structure is adjusted by an ensemble rule to obtain the final temperature estimation results. We test the EELM algorithm on the Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) L1B data set and compare it with other scholars' algorithms. The experimental results show that the EELM algorithm can not only improve the resolution of TIR data, but also estimate the subpixel temperature of TIR more accurately.

Change detection (CD) for multitemporal remote sensing images can find change trends and reveal the development patterns. However, the typical methods based on algebraic operation, image transformation, or segmentation may not yield satisfactory results due to the spectral variability and noise complexity. In a sense, it can be considered that multitemporal images are composed of unchanged and changed regions, as well as noise. In the light of this, a stepwise subtraction method for CD is proposed, based on auto-updating multitemporal matrix factorization (AMMF) and spectral constraint, to remove the unchanged regions and noise from the original images step by step. The unchanged regions are first identified by AMMF, during which the distribution and subspace information of each temporal image are regularized to encode the spatio-temporal correlation. Then, mean shift smoothness is adopted as a spectral constraint so as to remove the noise. In this way, the changed regions have been highlighted so that the change map can be obtained by a postsegmentation method. Experiments have been conducted on three multitemporal data sets, including images from Quick Bird, aerial, and GF-1, indicating that the proposed method is effective and robust, which is superior to some state-of-the-art methods.

The richness of spectral information in multitemporal hyperspectral images (MHSIs) offers the possibility to effectively detect subtle changes and properties of grounds. However, severe spectral variabilities and inadequate spatial co-exploitation capabilities limit the performance of existing methods due to differences in acquisition times and conditions. Therefore, this article proposes a strategy of joint unmixing and multitemporal spatial information coguidance (JUC) to fully exploit the spatio-temporal-spectral features. First, a multitemporal joint unmixing method is used to achieve endmembers’ extraction and abundance estimation. Wherein the method adds spectral perturbed regularization when compared to the traditional unmixing strategy, making it robust to spectral variability. Second, we propose a multitemporal coguidance method that highlights the contrast between changed and unchanged regions and removes the noise by transferring the common structure information between the multitemporal first principal component map and the abundance difference maps. It will obtain an enhanced abundance difference maps and achieve effective combination of multitemporal spatial information. The final change result can be obtained by combining and thresholding these enhanced abundance difference maps. Experiments on some data sets demonstrate that the proposed algorithm is sufficiently valid and robust for multitemporal images, especially for data containing spectral variabilities and obvious structures.

Anomaly detection is a key problem in hyperspectral image (HSI) analysis with important remote sensing applications. Traditional methods for hyperspectral anomaly detection are mostly based on the distinctive statistical features of the HSIs. However, the anomaly-detection performance of these methods has been negatively impacted by two major limitations: 1) failure to consider the spatial pixel correlation and the ground-object correlation and 2) the existence of the mixing pixels caused by both lower spatial resolution and higher spectral resolution, which leads to higher false-alarm rates. In this article, these two problems are largely solved through a novel hyperspectral anomaly-detection method based on image super-resolution (SR) and spatial correlation. The proposed method encompasses two innovative ideas. First, based on the spectral variability in the anomaly targets, an extended linear mixing model can be obtained with more accurate ground-object information. Then, image SR is used to improve the spatial resolution of the HSIs by injecting the ground-object information from the mixing model. This alleviates the effect of mixed pixels on anomaly detection. Second, spatial correlation is exploited jointly with the global Reed-Xiaoli (GRX) method and the ground-object correlation detection for anomaly detection. Experimental results show that the proposed method not only effectively improves the hyperspectral spatial resolution and reduces the false-alarm rate but also increases the detectability with the spatial correlation information. Furthermore, the results for the real HSIs demonstrate that the proposed method achieves higher rates of anomaly detection with lower false-alarm rates.

Hyperspectral image (HSI) classification appro- aches achieve significant improvements with the proposal and application of deep learning algorithms. However, due to the end-to-end structure of the deep learning model, the exploration of intrinsic physical-chemical properties in HSI data is insufficient, which restricts the extraction of diagnostic features and impedes the improvement of intraclass classification performance. Moreover, the synergetic spectral-spatial feature extraction in deep learning model is limited owing to the difference between HSI spectral and spatial dimensions, which also hinders the refinement of performance. In order to mitigate these issues, an attention symbiotic neural network (ASNN) based on relative water content (RWC) retrieval (RWCR) is proposed for HSI refined classification in this article. ASNN is a multisupervised deep learning model that is able to extract spectral-spatial and biochemical features from the multilabel input data simultaneously. The augmented multilabel data, consisting of original spectral-spatial labels and RWC labels, are generated in the RWCR inversion model, which contains the proposed spectral index [red edge slope (RES)] calculation and the proposed adaptive grading algorithm. There are two critical parts in ASNN, soft band selection (SBS) module and dimensionality-varied feature extraction (DVFE) module, which are responsible for attention assignment and synergistic spectral-spatial feature extraction, respectively. The experimental results on real HSI data verify the effectiveness of RES, SBS, and DVFE in ablation studies. It is also demonstrated that ASNN has the capacity for improving intraclass and interclass accuracy in refined classification and providing a competitive advantage in comparison with several state-of-the-art methods.

A spectral-spatial (SS) hyperspectral classifier generally implements a spectral classifier (SC) followed by a spatial filter (SF) for classification. This article develops a new approach to fusing multiple SC-SF classifiers for hyperspectral image classification (HSIC) as to improve classification performance. To accomplish this goal an iterative process is particularly designed to fuse the spatial-filtered classification maps (SFMaps) produced by each of SC-SF classifiers into one single SFMap via maximum a posteriori (MAP) criterion. Such fused SFMaps are then fed back and added to the current data cube to create a new data set for next round SC-SF classifier fusion. The same process is repeated iteratively until it satisfies an automatic stopping rule. To further fuse more than two SS methods, two approaches are also developed, called simultaneous multiple SC-SF fusion (SMSSF) method and progressive multiple SC-SF fusion (PMSSF) method. Experimental results demonstrate that fusing multiple SC-SF classifiers can indeed perform better than using an individual single SC-SF classifier alone without fusion.

High resolution and large field of view in large scene images ( ) provide rich detail information and wide viewing angle. However, the computational complexity is also drastically increased. Small object detection in large scene remote sensing images is always one of the nontrivial problems. Generally, the body length of aircraft in large scene images is only 30~80 pixels at 0.5m or 1m resolution. While convolutional neural networks (CNN) have made great breakthroughs in natural images, the fast and accurate identification of small objects has not been effectively tackled. In order to improve accuracy, this paper proposes a two-stage Fusion-oriented aircraft detection model (FOADM) and uses an adjusted detection network model Tiny Darknet based on Darknet53 to adapt for the detection of small aircraft. In the first stage, we combine Line Segment Detection (LSD) with Graph-Based Visual Saliency (GBVS) to acquire the region of interest (ROI) in downsampled images, which can reduce the worthless search to some extent. Then, in original high resolution image, the ROI is located and partitioned. In the second stage, each block is fed into the detection network Tiny Darknet for aircraft detection. Experiments demonstrate the proposed method can effectively improve the recall of detection result in high resolution.

Hyperspectral anomaly detection is a hot topic in remote sensing applications. Most of the conventional detectors are based on the Reed-Xiaoli (RX) method and assumedly targets and backgrounds follow a Gaussian distribution in which two problems exist: the outliers in the Gaussian distribution statistics limit the detection accuracy of RX method, and the larger proportions between the backgrounds and anomaly targets account for the higher false alarm rate. In this letter, a new hyperspectral anomaly detection method is proposed, which can solve the two problems mentioned above. The new method includes two improved ideas. First, third- and fourth-order moments are used as statistical features to improve the outlier peak values and highlight the targets. Second, the adaptive cosine estimation as the structural assumption for the RX method is used to suppress the backgrounds for anomalous targets. Experiments on real hyperspectral data sets suggest that our proposed method could not only effectively decrease the impact of background statistics but also improve the detection ability of such outlier values. Furthermore, comparative experimental results revealed that the proposed method achieves higher detection rates with lower false alarm rates.

LIDAR point cloud and RGB images are often used for object detection in autonomous driving scenarios. This paper develops a multi-view version of Frustum PointNet (F-PointNet), to be called MVFP to reduce the rate of missed detection in F-PointNet by adding auxiliary bird's eye view (BEV) detection part. In processing MVFP, initial object detection results are obtained from F-PointNet by combining the RGB image and raw LIDAR point cloud. Simultaneously, raw LIDAR point cloud is encoded into BEV feature maps, from which 2D bounding boxes are predicted. In missed detection judgement, the intersection over union (IoU) is used as a criteria for the matching of preliminary object detection results from F-PointNet and BEV maps prediction results. 2D boxes belonging to missed-detected objects from BEV maps are projected to the pipeline of F-PointNet until all the objects in BEV maps find a matching detection result in the set of F-PointNet detection results. To evaluate the performance of MVFP, 3D object detection experiments are conducted on KITTI benchmark. The experiment results demonstrate that MVFP outperforms the original F-PointNet by 5% and 4% higher recall on the hard mode of pedestrian and cyclist.

Hierarchical detection from parking lot to vehicle based on visual saliency and angle estimation is proposed for the large-area remote sensing image (RSI). According to the brightness characteristics of parking lot, an accelerated bright-based saliency map (BBSM) is presented to locate the parking lot, which is also achieved by two-step location from rough to accurate. The suspected vehicle queues are then detected using the spectral residual saliency map and rotated to the horizontal direction by angle estimation of vehicle queue. Each vehicle in the suspected vehicle queues is identified by HOG features extraction and SVM classification. Using several RSIs at a spatial resolution of 0.5 meter with the size of 24000×24000 pixels, experimental results show that the proposed method outperforms two traditional methods and achieves the precision ratio of 87.1% and recall ratio of 90.2%.

Hyperspectral anomaly detection aims to separate the abnormal pixels from the background, and plays an important role in remote sensing image processing. Most traditional detectors are based on the RX method but in these detection methods, the detection peak value of outliers is low, which leads to the unobvious detection results. In the small target and sub-pixel target areas, the detection of outliers is difficult because of the complicated background. In this paper, a hyperspectral anomaly detection based on improved RX with CNN framework is proposed. The method firstly estimates the degree of similarity between the pixel to be detected and the target or background by training the CNN, thereby effectively suppressing the background and highlighting the targets. Then the RX algorithm is improved by using higher moments to improve the peak of the targets, and the score is sent to the improved RX algorithm to obtain the detection results. Experimental results on real hyperspectral images show that the method can effectively highlight the target, suppress the background, and have better performance for the detection of small targets.

This letter presents a study of vehicle detection in high-resolution images using superpixel segmentation and iterative convolutional neural network strategy. First, a novel superpixel segmentation integrated with multiple local information constraints method is proposed to improve the segmentation results with a low breakage rate. To make training and detection more efficient, we extract meaningful and nonredundant patches based on the centers of the segmented superpixels. For reducing the instability in detection performance because of manual or random selection of samples, a training sample iterative selection strategy based on convolutional neural network is proposed. After a compact training sample subset is obtained from the original entire training set, a representative feature set with high discrimination ability between vehicle and background is extracted from these selected samples for detection. To further avoid overfitting the training and promote the detection efficiency, data augment and a main direction estimation method are used. Comparative experimental results on Toronto data indicated the effectiveness of our proposed method.

This letter extends one of popular spectral-spatial classification methods for hyperspectral images, called edge preserving filtering (EPF)-based method to an iterative version of EPF method, referred to as iterative EPF (IEPF). Instead of finding maximum of the final soft probability maps obtained from the initial binary probability maps by EPF, the proposed IEPF feeds back the soft probability maps and combines them with the currently being processed image cube to create a new image cube as the next input to IEPF to reimplement support vector machine (SVM) for classification. The process is carried out iteratively by repeatedly feeding back the spatial information provided by EPF-obtained soft probability maps and terminated by a Tanimoto index (TI)-based automatic stopping rule. The experimental results demonstrate that IEPF performed better than EPF by providing higher classification accuracy.

Inshore ship detection becomes challenging in high-resolution optical remote sensing image (RSI) because inshore ships are often incomplete and deformed due to the poor imaging condition and shadow of ship superstructure, and there are various interferences in harbor. A contour refinement and the improved generalized Hough transform (GHT)-based inshore ship detection scheme is proposed for RSI with complex harbor scenes. First, the suspected region of ships (SRS) is located in the entire RSI according to the line segments of ship body and docks. The contours in each SRS are then refined to repair the damaged ship head contour (SHC) using the convex set characteristics of ship head and subsequently reduce non-SHC by curvature filtering. In each refined SRS, equal frequency quantification instead of equal width quantification for R-Table construction and Gini coefficient-based decision criterion combining the number and distribution of votes are proposed to improve GHT (i.e., EG-GHT) and to extract SHCs as candidate targets. The false candidates are removed according to pixel proportion described by the structured binarization feature. Applying the border scoring strategy, the best candidates with the largest score among all the overlapped bounding boxes are selected as the final detection targets. Using the public RSIs with various cases, including turbid water, cloud occlusion, ships moored together, and ships with the different sizes, experimental results demonstrate the proposed scheme outperforms state-of-the-art contour-based methods and deep learning-based methods in terms of precision-recall rate and average precision, respectively.

This paper presents a new spectral-spatial (SS) approach to hyperspectral image classification (HSIC), called SS feedback close network system (SSFCNS), which has not been explored in the past. Unlike commonly used SS-based methods SSFCNS includes a feedback close network system (FCNS) to obtain spatial information via a selective spatial filter in an iterative manner. More specifically, SSFCNS takes advantage of FCNS which utilizes a particularly selected spatial filter to capture a posteriori spatial information directly from spectral-classified data samples and then feeds back such obtained spatial-filtered image to be combined with the current image cube to create a new image cube that can be used as a new input to re-implement SSFCNS. The process is carried out in such a way that the spatial information obtained from spectral classification results is updated by FCNS iteratively and terminated by a Tanimoto index (TI)-derived automatic stopping rule. To evaluate the performance of SSFCNS several spatial filters (i.e., Gaussian, bilateral, guided, and Gabor filters) are explored for real image experiments. The experimental results demonstrate that SSFCNS performs significantly better in classification accuracy compared to SS-based methods which do not use FCNS.

In hyperspectral image classification spectral information and spatial information are always integrated to improve the classification accuracy. This paper develops an iterative version of support vector machine, to be called iterative SVM (ISVM) to perform hyperspectral image classification by extracting spatial information iteratively via feedback loops. In processing ISVM an initial hyperspectral data cube is obtained by combining the original image and its first principal component. SVM is then implemented to the resulting data cube to produce an initial classification map. In each feedback loop, a Gaussian filter is applied to obtain the spatial information of the SVM-classification map so that the Gaussian-filtered map is further fed back to combine with the currently processed hyperspectral cube for the next round of iteration. As for terminating the iterative process an automatic stopping rule is also developed. To evaluate the performance of ISVM real image experiments are conducted in comparison with state-of-the-art spectral-spatial hyperspectral classification methods. The experiment results demonstrate that ISVM performed better by providing higher classification accuracy.

Region proposals are very important for several perfections of remote sensing applications such as vehicle detection, traffic surveillance and intelligent transport system. In this paper, an efficient region proposal approach has been proposed. The framework is organized into two key steps. The first step is based on extracting region proposals using Cascade system. The second step is based on the classification of extracted region proposals which is performed by transfer learning using Convolutional Neural Networks (CNN) and AlexNet architecture is utilized for transfer learning. The aim of this investigation is to evaluate the proposed method for vehicle detection. The selective search (SS) method is also briefly discussed for comparison. The results regarding vehicle detection are very promising.

With the rapid development of sensor technology, we pay more attention to object detection for high-resolution SAR images. Besides, the traditional object detection methods which only use one SAR image to accomplish detection aren't enough appreciate for some cases that the background around the object is complex. In the paper, we propose an object detection method for high-resolution SAR images under the spatial constraints of optical images. It consists of three main steps: Establishment of the spatial relation between optical and SAR images, spatial constraints projection from optical images and detection under the spatial constraints in high-resolution SAR images. At the end of the paper, we take the inshore ship detection as an example to show that the proposed method can greatly improve the accuracy and efficiency of object detection against the traditional SAR object detection methods in conditions that background around the object is complex.

Recently, the popularity of using hyperspectral image to study and monitor plant characteristics and conditions has been increased. The use of hyperspectral image improves the breeding process and increases profits. In the case of hyperspectral data with high spectral resolution characteristics suitable for intraclass classification, this paper focuses on the application of hyperspectral image analysis in distinguishing among different plant species. Plant intraclass classification is sophisticated due to its small spectral differences. Hence, a refined hyperspectral image classification method for plant, referred as SI-GCK which uses Spectral Index (SI) to represent plant spectral, and take advantage of semi-supervised graph-based composite kernel (GCK) method to combine spectral information and spatial location of pixels for classification is presented in this paper. As a comparison, sequential floating forward selection (SFFS) is used to select spectral bands for SVM learning. Its accuracy of plant classification is nearly equal to result by means of SI, and the proposed method in this paper is better than aforementioned.

With the development of airborne Lidar, a large number of digital surface models(DSMs) are now available, which has greatly contributed to the rapid development of the applications for building reconstruction. Similar to two-dimensional Zernike moments(2D-ZMs), the three-dimensional Zernike moments(3D-ZMs) consist of two components, amplitude component and phase component, respectively. Benefiting from rotation invariance of the amplitude characteristic and orientation difference of the phase characteristic, the 3D-ZMs have excellent performance for building recognition. Image reconstruction using 2D-ZMs has been achieved in early research. However, few studies have referred to three-dimensional object reconstruction based on 3D-ZMs. This paper proposes a method using 3D-ZMs to approximately reconstruct the shape of a general 3D building. Firstly, we study the amplitude and phase characteristic of 3D-ZMs to distinguish buildings, and conversely, the 3D-ZMs are used to reconstruct 3D buildings. Experimental results illustrated that this proposed method could be used to approximately reconstruct the shape of a general 3D building from a small number of moments.

In remote sensing images, it is usually hard to extract narrow roads with only several pixels width. To address this problem, the original remote sensing images are processed with super-resolution to enlarge the details of the narrow roads by a convolutional neural network method. Then the One-Class Support Vector Machine (OCSVM) classifier is applied after super-resolution for exact extraction of narrow roads. Experiments are conducted on an open dataset of remote sensing images to verify the performance of the new method and the results are compared with the method without image super-resolution. The experimental results demonstrate the validity and superiority of the new method.

In the field of target detection in remote sensing images, lots of learning algorithms have been presented, among which support vector machine was widely utilized. However, this kind of vector represents only one pixel of a remote sensing image that ignores the spatial relationship of neighbors. Besides, with the increase of spatial resolution of remote sensing images, detail detection of targets become possible so that we gain more detailed information. Higher resolution leads to larger data volume, nevertheless, which makes processing efficiency decrease. In order to improve the situation, we present a Hierarchical Support Tensor Machine (H-STM) method, which deal images with feature tensors that remains much spatial structural information, and according to requirement, we detect if targets exist in low-resolution images with low-level STM first. While got desired result, we make use of a higher level to find out more detail information.

An efficient vehicle detection method is proposed for remote sensing images provided by Chinese GF-2 satellite with the 1-meter spatial resolution in this paper. Considering the characteristics of the vehicle on the road in GF-2 image, dark and light vehicles are firstly detected on the masked road using the semi-automatic dual-threshold technique. The residual disturbance (e.g. shadows, lane line and noise) is removed by the adjacent relation and double area filtering. Furthermore, to avoid the detected broken vehicle, an integrity processing is proposed to locate the detected broken vehicle and eliminate the repetition detection. Experimental results on several GF-2 images present the lower miss rate and false rate in vehicle detection.

Multi-resolution analysis (MRA) is a useful technique for multispectral (MS) image pan-sharpening. To overcome the limitation of the conventional wavelet-based method, multi-directional MRA approaches have been proposed to provide an efficient directional information representation. In this paper, we present a new hybrid method for MS image pan-sharpening that uses non-subsampled contourlet transform (NSCT) as the MRA tool, and followed by a high-pass detail-injection model. Particularly, to further enhance the spatial resolution of the MS image, and in the meantime, produce a high spectral quality, we take account of the dissimilarity between the spatial details of MS image and decomposed panchromatic image of NSCT, and introduce a fast and effective means to deal with the problem. Experiments on four remote sensing data sets show the superiority of the presented approach over other typical pan-sharpening methods.

In very high resolution (VHR) SAR images, traditional method failed to accurately and completely extract vessels because of the holes and fractures in the target body in addition to the interference of adjacent objectives. In this paper, a saliency method based on SLIC (simple linear iteration clustering) segmentation is adopted to detect the targets, and the salient results are further post-processing to remove the false alarms and fill the blanks in the target body. Experimental results on Terra-SAR images demonstrate that the proposed approach can maintain the integrity of vessel and decrease the false alarm rate.

Region-of-interest (ROI) detection techniques are of great importance in the analysis of remote sensing images, especially in target detection, since the size of the image to be dealt with grows substantially with the improvement of spatial resolution. Most of current studies are not aiming at the specific type of object area detection, and the processed images are rather small compared to the size of the raw data acquired by high-resolution satellite. In this letter, a hierarchical task-driven ROI detection method, based on saliency and density, is proposed to address the detection of the potential object areas in large-scale remote sensing images. The proposed saliency and density-based detection method (SDBD) integrates bottom-up and top-down strategies, where the saliency-based multilevel histogram contrast is presented in the bottom-up phase to obtain the preliminary regions, while the centroid density distribution index (CDDI) is defined in the top-down scheme to refine the previous results. Specifically, superpixel segmentation is introduced in this letter to narrow down the ROI candidates. SDBD is capable of extracting ROI of different objects by adjusting the threshold of CDDI. The experiments are conducted on two data sets to extract ROIs of storage tanks and residence. Experimental results demonstrate that the proposed method is effective in identifying ROI in large-scale data.

In the past decades, with the development of polarized hyperspectral imaging system, target detection and recognition for polarized hyperspectral images (PHSIs) have attracted more and more attention. Most conventional target detection algorithms of PHSI are based on the Stokes vector, which mainly take advantage of the spectral information, and ignore the continuous variability of polarized dimension, being similar to spectrum. In fact, the PHSI include multidimensional features of polarization, spectrum, space, and radiation, and these provide more discriminable information about target and background than traditional spectrum or intensity ones. Hence, tensor, which can keep the complete information of PHSI, is introduced to represent such high-dimensional data. In this letter, the tensor canonical polyadic (CP) decomposition is adopted to extract the spectral and polarized features. There are two ways to realize the target detection through CP decomposition. One is to construct a fourth-order tensor matched filtering (FTMF), and FTMF is applied to the original data directly without extracting the Stokes vector. The other is to reconstruct the PHSI into a new 3-D data, then matched filter algorithm of hyperspectral image is applied to this data to detect the targets, for short CPMF. The experimental results show that the proposed methods achieve the joint utilization of spectrum and polarization and are more suitable and effective for the target detection of the PHSI.

Building shape, as a key structured element, plays a significant role in various urban remote sensing applications. However, because of high complexity and intraclass variations between building structures, the capability of building shape description and recognition becomes limited or even impoverished. In this letter, a novel deep embedding network is proposed for building shape recognition, which combines the strength of the unsupervised feature learning of convolutional neural networks (CNNs) and a novel triplet loss. Specifically, we take advantage of the strong discriminative power of CNNs to learn an efficient building shape representation for shape recognition. With this deep embedding network, the high-dimensional image space can be mapped into a low-dimensional feature space, and the deep features can effectively reduce the intraclass variations while increasing the interclass variation between different building shape images. Afterward, the derived deep features are exploited for the process of building shape recognition. This method consists of two stages. In the first stage, for standard building shape image queries stored in the shape primitives library and the building shape data set, two sets of deep features are extracted with the deep embedding network. In the second stage, we formulate the shape recognition task into a feature matching problem and the final building shape recognition results can be achieved by set-to-set feature matching method. Experiments on the VHR-10 and UCML data sets demonstrate the effectiveness and precision of the proposed method.

Polarized hyperspectral images (PHSIs) possess multidimensional information, including space, spectrum, and polarization, and in the past decades, target detection and recognition for PHSIs have attracted more and more attention. However, most target detection methods of PHSIs are based on the Stokes vector, and derived from the target detection of HSIs, which mainly take advantage of the spectral information and ignore the continuous variability of polarized dimension, being similar to spectrum. Hence, in order to take full advantage of the multidimensional information of PHSIs, we combine tensor decomposition and joint sparse representation, and propose a joint sparse tensor representation (JSTR) method for the target detection of PHSI, which can remove the redundancy and noise, and also realize the joint utilization of spectral, polarized, and spatial information. And the experiments on the PHSI data have validated the practicability and effectiveness of JSTR for the target detection of PHSIs.

Simultaneously recovering hyperspectral images (HSIs) from mixed degradations is a classical inverse problem, which has attracted major research efforts. Low-rank matrix recovery (LRMR) has been proved to be an effective method. This paper proposes a multi-scale recovering model based on 3D Gaussian pyramid decomposition and residual reconstitution to improve the LRMR on its adaptability of local correlative noises (including stripes, dead lines and impulse noise) removal. By compressing the HSI cube to lower-resolution layers in spatial domain, the non-local low rank property of clean HSI can be better utilized. LRMR algorithm is applied from the top. The following layers are reconstituted with the upper recovery result and their original decomposition residual, and then executed LRMR until the bottom of the pyramid. In the proposed procedure, mixed noises are removed progressively in terms of frequency, besides the details of clean HSI are well preserved. Experimental results on simulated and real data in terms of qualitative and quantitative assessments show significant improvements over conventional methods.

When dealing with the enormous remote sensing image, JPEG XR offers similar compression rate compared with JPEG2000, while consumes nearly the same resource as JPEG. Taking the limitation of power and computational resources onboard into consideration, FPGA-based hardware solution stands out with advantages of less resource requirement and higher speed. And the operation of JPEG XR is all in integer, so the image compression algorithm is feasible to implement. To realize high-throughput pipeline architecture for onboard image compression with low clock frequency, FPGA is adopted to perform the parallel architecture for JPEG XR lossy compression. The parallel architecture is summed up into five modules: pre-filter module, photo core transform (PCT) module, quantification module, predictive coding module and entropy coding module. Experimental results demonstrate the coding speed is 0.437 pixel per clock, speed of code stream is 41.7Mbyte/s at 100MHz clock frequency.

This paper introduces a novel multi-layer line grouping method for perceptually building extraction from stereo aerial images. Nowadays, perceptual grouping algorithm for line features obtained from images has been widely investigated, but there are little attentions to be paid to building height information of the line segments applied in existing literature of edge grouping field. In order to enhance accuracy of edge grouping, line segments are grouped into multi-layer with the extracted height information of neighbor matching points as constraint in this paper. In each height layer, line segments are grouped under the guidance of prior knowledges about the boundary style of polygonal buildings, and iteratively verified by the aforementioned group rules or prior knowledges for correctness of the connection and optimal building extraction. Experimental results illustrate a precise building extraction which can be accomplished by the proposed method.

An algorithm for automatic recognition of overwater bridge target based on “joint feather and knowledge rule-based” is presented for the problem concerning automatic recognition of overwater bridge target in optical remote sensing images. Firstly, based on knowledge feathers of overwater bridge target, waters in an optical remote sensing image are extracted to narrow down bridge detection range. After preliminary segmentation of waters, mathematical morphological algorithms are used to remove small noise points. Secondly, binary image connected regions are labeled based on pixels to achieve regional features of waters effectively. After the determination of river areas, the area tracing algorithm is adopted to extract outer boundaries of river areas. Candidate areas with possible existing bridges can be prejudged according to bridge knowledge rule. Straight line fitting is applied on points of two boundaries of possible bridge within candidate areas to achieve two bridge boundary lines. It is indicated by analysis that the algorithm raised in this paper shows favorable recognition speed and accuracy.

Rational function model (RFM), which is composed of 80 rational polynomial coefficients (RPCs), has been widely used to establish a functional relationship between the image space and the object space in photogrammetry and remote sensing. In order to gain precise RPCs, a set of ground control points (GCPs) need to be selected. And in all most applications, many GCPs selected are located in the center of one object in order to increase the measurement precision. Note that, for a special area, such as urban areas which consist of many buildings, have many feature points which are usually located in the corner. This paper proposes an improved method using feature points instead of non-feature points to solve RPCs. Evaluation of aerial data shows that the RPCs can reach a high fitting accuracy by means of these feature points as GCPs, more than those using non-feature points. An important advantage is that this method can enhance edge protection of buildings, so that it can applied in subsequent applications, such as shadow removing, target recognition and so on. Moreover, this method can remain computation accuracy of buildings even if the number of GCPs decreases.

In hyperspectral image processing technologies, anomaly detection is a valuable and practical way of searching small unknown targets based on spectral characteristics. For the lack of prior knowledge of targets, background modeling on hyperspectral images is the key process that affects the outcome of anomaly detection operator. In this paper, a novel method of anomaly detection based on quadratic modeling is proposed. The innovation of the proposed algorithm is that it divides the detection process into two main steps: one is initial detection, which provides a preliminary judgment of background pixels; the other is the quadratic background modeling to reduce the contamination of outliers, consisting both anomaly pixels and abnormal background pixels. In the part of experiments, a semisimulated hyperspectral image and a real hyperspectral image are both used to evaluate the performance of our proposed method. Visual analysis and quantative analysis of receiver operating characteristic (ROC) curves both show that our algorithm performs better when compared with other classic approaches and state-of-the-art approaches.

Pan-sharpening is designed to estimate multi-/hyperspectral (MS/HS) images that would have been observed with a sensor at higher resolution. It is a very important issue for many remote sensing and mapping applications. This letter proposes an improved pan-sharpening algorithm based on the ARSIS concept under the assumption that missing information of a low-resolution MS/HS image is linked to the high frequencies of MS/HS and panchromatic (PAN) images. The main object of this letter is to exhibit a multilevel interband structure model that better considers the inherent relationship between the hierarchical structures of MS/HS and PAN images. Several groups of data sets are used to demonstrate the performance of the proposed method. The results show that the proposed method outperforms the existing ARSIS-based and some other fusion techniques and can be extended to HS image sharpening as well.

In this letter, we proposed a phase analysis of the 3-D Zernike moment (3D-ZM), to estimate the orientation difference between buildings in a digital surface model (DSM). A 3-D analysis using the DSM is an important way for building reconstruction and many further remote sensing applications. By using the 3D-ZM, we could decompose the 3-D structure of an object in a complex domain. Benefiting from rotation invariance of the amplitude component, the 3D-ZM has excellent performance for object classification. However, the phase component of 3D-ZM is ignored in early research, by which orientation of different objects could be analyzed, and similar buildings (within one class) could be distinguished meticulously, whereas other traditional geometric features may fail to do so. Therefore, we studied the phase analysis of 3D-ZM and introduced a flow frame of orientation-difference estimation. Experimental results illustrated that our method could robustly find the orientation difference between similar buildings, and improvement on accuracy was achieved for building classification and orientation.

In this paper, we propose a self-learning approach for remote sensing image classification. The main work of this paper aims at providing a new framework of semisupervised learning technique for multiple-source synergetic classification, thereby improving the classification accuracy under the condition of small samples. Considering the high spectral resolution of a hyperspectral (HS) image and the high spatial resolution of a panchromatic (PAN) image, the proposed approach combines image segmentation with an active learning algorithm and adopts a standard active learning method for a self-learning strategy, in which the learning algorithm automatically selects informative unlabeled samples by itself according to their collaborative spatial-spectral features and the predicted information of a spectral-based classifier. This way, no extra cost of human expertise is required for labeling the selected pixels when compared with conventional active learning methods. Experiments on three data sets, including HS and PAN images, indicate that our proposed approach has a great enhancement on overall classification accuracy compared with classical supervised algorithms and turns out to be a promising strategy in synergetic classification of HS and PAN images.

Most of the compression methods for remote sensing images are often designed under the guidance of mean square error. However, for the vision-related applications, high peak-signal-to-noise ratio (PSNR) does not mean good visual quality. On the other hand, existing compression methods that considering the human visual system (HVS) are usually designed for natural images, without taking the unique characteristics of remote sensing images into account. Focusing on this problem, we present a novel HVS-based adaptive scanning (HAS) scheme for the compression of remote sensing images. First, after the wavelet transform, a retina-based visual sensitivity model is established, and then, the visual weighting mask is generated. Second, for the weighted transformed image, an adaptive scanning method is proposed, which provides different scanning orders among subbands and within a subband, respectively. The former focuses on organizing the codestream according to the importance of weighted subbands, and the latter aims at preserving the direction information of an image as much as possible. Finally, the binary tree codec is utilized. Experimental results show that, as compared with other scan-based compression methods, the proposed HAS-based compression method can provide better visual quality, which makes it more desirable in vision-related applications for remote sensing images.

Image fusion is one of the most important image processing methods in the field of remote sensing. Multispectral (MS) or hyperspectral (HS) images are often fused with panchromatic (PAN) images to enhance their spatial resolution while preserving the spectral information, which will lead to a better interpretation in subsequent applications. In order to achieve this goal, an improved method of image fusion, which is based on the amélioration de la résolution spatiale par injection de structures (ARSIS) Concept, is proposed in this paper. In the new method, the degree of diversity between each pixel and its surroundings is measured utilizing Center-Surround Spectral Angle (CSSA) model, and the more different a pixel is, the more detailed information is injected into the MS image. In order to verify the advantages of our proposed fusion method, experiments are processed on two data sets. Several assessment criteria are used to demonstrate the effectiveness of our proposed algorithm. Moreover, from the view of application, accuracy of classification on fused images is also evaluated to further show the superiority of our method.

This paper presents a ℓ2,0-norm regularization based feature selection method to analyze very high resolution remote sensing imagery. The method tackles the feature selection problem based on a ℓ2,1-norm based objective function and a ℓ2, 0-norm equality constraint. The constrained optimization problem is solved by an efficient algorithm based on augmented Lagrangian method to figure out a stable local solution. Though the ℓ2, 0-norm regularization based feature selection method should handle a non-convex and non-smooth problem, it outperforms the ℓ2,1-norm regularization based approximate convex counterparts and state-of-art feature selection methods in light of classification accuracies by 1-NN and SVM classifiers. The experimental results demonstrate the effectiveness of the presented method in selecting features with great generalization capabilities.

Texture segmentation is a critical step in building-based analysis in urban remote sensing images to obtain more detail information for further applications. Most existing segmentation algorithms rely on region or edge information to segment, which failed to segment building surfaces with almost same texture and unclear edge between the surfaces. Therefore, in order to solve this challenging task, based on the ORTSEG algorithm in Michael T. McCann's paper, an improved ORTSEG algorithm is proposed, in which, a sparse non-negative matrix factorization (SNMF) is used for the optimization. The final segmentation results show the superiority of this improved ORTSEG algorithm.

This paper presents a feature guided multi-window area-based matching method for urban remote sensing stereo pairs. The method achieves the goal that producing dense disparity maps for urban remote sensing stereo pairs. The proposed method can be divided into four stages: feature-based matching, edge support region extraction, area-based matching and post-processing. The point feature matching is applied firstly as it provides precise matching results of few points, which can be used to restrict the searching range of area-based matching process. Then, building edges are extracted by an efficient line segment detector. In order to enhance the accuracy of the area-based matching, edge support regions are derived from these edges and multi-windows are applied during the area-based matching to preserve details of edges. Finally the post-processing including interpolation and filtering is applied to heighten the completeness and accuracy of the disparity map.

Hyperspectral images (HSIs) are often contaminated by noise, in order to remove the image noise efficiently and acquire excellent results. We propose a new denoising method based on 3D sparse coding. Firstly, to make full use of spectral information of hyperspectral data, we extract patches from HSIs and each patch contains the same area of different band. Secondly, we use aforementioned method to extract all patches and train these patches, the dictionary can be obtained, further calculate sparse coefficients. Finally, we can restore the HISs through the dictionary and the sparse coefficients. Experiments are implemented using the HSIs collected by AVIRIS and ROSIS. Results indicate that compared with common 2D sparse coding method, 3D sparse method can effectively improve the restoration performance for both subjective visual and objective evaluation criterion.

In this paper, we proposed a novel texture-mapping method for buildings using remote sensing images and digital surface model. For generating better 3D map, boring manually or semi-automatic texture-mapping of buildings is always needed. However, only with remote sensing images and digital surface model, it is difficult to generate `sides' of buildings, and corresponding relation between triangular mesh and texture image is also hard to be found. Inspired by building extraction result, we found that roof-contour could guide interpolation of `sides' of building, and generate triangular mesh, and an interactive frame of texture mapping is introduced for processing the generated multi-sides and corresponding texture-images of buildings. Experiments show that texture-mapping of buildings using remote sensing resource is easily realized with our frame, and excellent results could be obtained.

Image registration technology is getting more and more important in nowadays. The accuracy of the registration resolution plays an important. In this passage, we present an image registration algorithm based on point feature of sub-pixel, which can improve the accuracy. Firstly we use Harris corner point algorithm to get point features, then we use our method to refine the Harris points, after that we use these points as GCPs and register the two images. Finally we find that our image registration algorithm has a better accuracy than the image registration.

Hyperspectral images (HSI) contain hundreds of bands, which brings huge amount of data. In this paper, we propose a novel compression method for HSI with Tucker3 decomposition. The hyperspectral images are firstly decomposed into core tensor, and then the number of components is selected according to the Fast particle swarm optimization (FPSO). Compared to the traditional methods, the new method has excellent reconstruction quality and less computing time.

Generally, dimensionality reduction methods, such as Principle Component Analysis (PCA) and Negative Matrix Factorization (NMF), are always applied as the preprocessing part in hyperspectral image classification so as to classify the constituent elements of every pixel in the scene efficiently. The results, however, would suffer the loss of detailed information inevitably. In this paper, deep learning frameworks, restricted Boltzmann machine (RBM) model and its deep structure deep belief networks (DBN), are introduced in hyperspectral image processing as the feature extraction and classification approach. The experiments are conducted on an airborne hyperspectral image. Further in the experiments, spatial-spectral classification is also practiced. Meanwhile, SVM with and without some classical feature extraction methods adopting before classification are employed as comparison. The results show the superior performance of the proposed approach.

In recent years, the specialized destriping methods for remote-sensing image emphasize efficiency and flexibility but lose the particulars in wide stripes. Though many excellent inpainting algorithms have been proposed, most of them are too complex and inefficient for hyperspectral image (HSI). In this paper, we propose a novel automatic completing method which is appropriate for the feature of HSI and easy to be implemented in parallel. The boundary information in broken region is restored primarily based on SVM with the input of the surrounding detected edges. Then we introduce an adaptive morphological filling operator restrained by the boundaries to estimate the pixels in the same position of all bands synchronously. Experimental results show satisfactory performance of the proposed system and its significance on HSI completion.

The image registration is an important technology in remote sensing image processing and applications. However, in recent years it is yet a challenging task especially to highresolution remote sensing images which contain more similar objects such as smooth areas, repetitive structures. In order to solve this problem, a novel registration method is proposed using multi-feature and multi-stage strategy in this paper. Firstly local features, the local density distribution and spatial relation, are employed to deal with the ambiguity in the similar objects and avoid mismatches, which are described by the DAISY and the RPCP (relative polar coordinates of point) respectively. Secondly the multi-stage strategy is used to avoid exhaustive search process and also improves the matching performance. Finally experimental results have shown the effectiveness of the proposed method.

In this paper, a new high-precision electromagnetic scattering computing model, which is based on the parallel finite-difference time-domain (FDTD) method, is proposed to compute the SAR echo. Since the FDTD method can only compute radar return at a fixed azimuth angle once, several FDTD simulations should be combined so that a flight path can be simulated. The FDTD method suffers from low computation speed and large computation cost, thus a parallel FDTD model based on MPI library is built to overcome these shortcomings in this paper. The purpose of the computing model is how to use the parallel FDTD to get high-resolution SAR echoes rather than imaging techniques or electromagnetic propagation and scattering effects. Then the SAR echoes of some typical objects including tank and car are computing. To validate the correctness of the proposed model, SAR images derived from the computed radar echoes are given in this paper. To evaluate the performance of the proposed method, experiments are done with different number of threads and PCs. The results show that big improvement has been made in speedup and computational scale by the proposed model.

Hyperspectral images (HSIs) are often contaminated by noise, some spectral bands are highly corrupted that they are usually discarded before processing. To make full use of hyperspectral data, a new bidirectional gradient (BG)-prediction-based HSI junk bands restoration algorithm is proposed. Firstly, according to the field spectral reflectance curves continuity and high spectral resolution instruments, both sides of the junk bands reflectance relative to wavelength gradients can be estimated respectively. Thus, calculate the two estimates of each junk band. Finally, followed by introducing the weighting factor which is inversely proportion to the square of wavelength difference and weighting the two estimates, the results of BG-prediction can be obtained. Experiments are implemented using the HIS collected by airborne visible/infrared imaging spectrometer (AVIRIS). Results indicate that compared with linear prediction, bidirectional gradient prediction can effectively improve the restoration performance, meanwhile the ground classification accuracy of the restored HSIs are improved.

Digital Surface Models (DSMs) generated from airborne laser-scanning or stereo satellite images provide a very useful source of information for building orientation estimation. However, due to the high complexity of the building structure, it is hardly to get the details of the building boundary information. In this paper, a new orientation estimation method is proposed, which merge the edge information extracted from optical images into DSM, and take advantage of the ZM phase information in the orientation estimation process. The classical way of extracting Zernike features only takes into account the magnitude of the moments and loses the phase information. The novelty of our approach is to take advantage of the phase information of Zernike moments to capture these variabilities in a way that makes it robust in the context of rotation angle estimation.

In hyperspectral images, there is abundant spectral information for classification. In most cases, spectral information based methods yield good classification results. However, different objects may have similar spectrums due to similar physical property. Spectral information based classification methods can't give accurate results for the similar physical property among objects belonging to the same main category. On the other hand, as the resolutions of sensors increase in recent years, more spatial information, such as shape and texture information can be extracted and described more precisely. In this paper, we proposed a spatial information aided similar spectral classification. In our method, spatial features, including the pixel shape index (PSI), and the gray-level co-occurrence matrix (GLCM), are extracted for accurate classification. We compared the Bhattachary Distance before and after spatial information being aided and we found that the B Distance was amplified sharply, which indicated that the separability among classes increased. Classification is practiced on two hyperspectral data sets, Kennedy Space Center and Pavia City, and the proposed method is compared with classification based on different features. It is found that each feature makes contribution to classification and the accuracy of the proposed method is the highest among all methods, which certifies the effectiveness of our algorithm.

In this paper, we address a problem of 3-D reconstruction with generalized stereo data from multiple platforms of remote sensing. Nowadays, rational function model (RFM)-based 3-D reconstruction with stereo images obtained from a single platform of remote sensing like a satellite or an airborne platform has been widely investigated, but there are little attentions to be paid to the problem of 3-D reconstruction with stereo images from multiple platforms in the existing literature. In order to make full use of the generalized stereo images from different platforms with different rigorous sensor models for 3-D reconstruction, we need to form the least squares estimation model of the corresponding RFM-based forward-intersection task after collecting observations from different platforms. However, resolutions of the stereo images from different platforms are greatly different so that the observations in the corresponding least squares problem are mathematically seriously unbalanced. To solve this problem for achieving precise reconstruction, we first model how the spatial resolution of the observation images of different platforms changes pixel by pixel and then embed the variance-component-estimation technique into the RFM-based 3-D reconstruction procedure to adaptively adjust weights for different observations. Experiments are conducted on simulated and real data sets. Experimental results show that the proposed algorithm can efficiently fulfill the 3-D reconstruction task for multiplatform stereo images with noticeable improvement over the classical RFM-based 3-D reconstruction method in terms of precision.

Spatial and spectral decor relations are necessary for hyper spectral data compression. The two dimensional wavelet transform based spatial transform and the Karhunen-Loève transform (KLT) based spectral transform have been employed successfully for hyper spectral data compression. In this paper a hyper spectral asymmetrical data compression is proposed as an improvement of the low complexity version of the Karhunen-Loève transform following the energy distribution in the wavelet transform domain. In the improved low complexity KLT, the computation processing of the covariance matrix is carried out on a spectral data which is extracted from the region of high energy distribution. The new method highlights the physical difference between the spatial and spectral characteristics of hyper spectral data. Experimental results show that the new method has improved significantly, not only the computation time but also has a good performance for the compressed data.

Summary form only given. Grid-based model is used to describe 3D objects in many circumstances. It can represent fine structure of objects by using small grid. However, small grid causes problem that data of grid-based model occupies much space, which leads to difficulties of transmission and storage. This paper presents an effective compression method for 3D data. In this method, 8-byte float coordinates of each grid are transferred to 1-bit binary codes. Then the binary data is coded by octree further. The experiment result shows that the 3D data can be efficiently compressed. The method is lossless. The complete raw data can be obtained by decoding.

Due to the huge amount of hyperspectral image (HSI), the compression of HSI is an important topic in remote sensing. The state of art methods use principal component analysis ( PCA ) as spectral decorrelatior and wavelet transformation as spatial decorrelator. How to determine the number of principal component and how to allocate storage of every principal component are two problems not solved. In this paper, we use hyperspectral signal subspace identification by minimum error ( HySime ) algorithm to estimate the the number of principal component and eigenvalue as the metric to allocate the storage. The experimental results demonstrate that the proposed algorithms can get better results than traditional PCA based methods.

Most lossy compression methods for hyperspectral image (HSI) usually compress the data in this way that focus on preserving low frequency information. However, for some applications such as edge detection, the information which belongs to high frequency is more useful. Thus, a new pixel of interest (POI)-preserving-based HSI compression scheme is proposed. The concept of POI is proposed because some pixels are significant in preserving the main high frequency. Firstly, the POI extraction is performed by unmixing and the mixed pixels are viewed as POI, then the mask of the pixel of interest (MPI) is generated. Secondly, the compression scheme based on the POI preserving is conducted. The spatial and spectral redundancies are reduced, respectively, then a POI-lifting strategy is adopted for preserving the main high frequency information. Finally, bit allocation and encoding to the transformed HSI is performed by SPIHT_TCIRA algorithm, followed by the contextual adaptive arithmetic coder (CAAC). Experiments are implemented using the HSI acquired by the ROSIS Sensor. Results indicate that compared with the common compression method, the POI-preserving-based compression method can keep the key high-frequency information more effectively.

It is an important problem in remote sensing that using limited observing points acquire the maximum quantity of building information. In this paper, a building information acquisition (BIA) model based on Support Vector Machine (SVM) is proposed for quantitative description of the mathematical relationship between the information quantity acquisition and the observing angles, which is optimized to obtain the maximum information quantity in the multi-temporal remote sensing observation. The main idea of the BIA model is that, to calculate information quantity at different observing angles, the target is decomposed into multiple faces whose information is described by the combined vector. Further, the modified bee colony algorithm is utilized to optimize the model to achieve the ideal maximum information quantity. The corresponding combined vector is optimal observing angles combination. The proposed model method performs well in our imaging simulation system data. Experiment results demonstrate that the proposed BIA model optimized will provide much more information quantity than observing randomly.

Hyperspectral remote sensing is a technique based on the spectroscopy, which contains abundant spectral information besides the spatial information of the images, and overcomes the limitations of the wide-band remote sensing detection. When classifying hyperspectral and multispectral images with the existing algorithms, we use only the spectral information more often. This paper presents an one-class classification techniques, which is based spatial-contextual term, this study modifies the decision function and constraints of support vector data description. Experimental results show that the proposed method achieves good classification performance on hyperspectral image.

In this paper, a rapid compression technology for remote sensing image based on different ground scenes is proposed. According to the different textures and the corresponding information contained different ground types, compression parameter is set for JPEG2000, firstly. And then considering the weight of the information amount of the image, the proportion of the information amount of the image and the proportion of the weight of the image, the bit rate of the image are allocated and the compression of the image is realized. Finally, an algorithm based on the same pass truncation is proposed. Experimental results demonstrate the proposed method speeds up the compression algorithm with little loss of reconstruction quality.

Polarimetric SAR (POLSAR) can offer more information than single-polarized SAR that has the capability to image in all weather and day-night conditions. The multi-polarization mode and wide swath requirements result in a huge amount of data, which may exceed the on-board storage and downlink bandwidth. Effective compression of POLSAR raw data is clearly one of the best solutions. This paper presents a compression method for POLSAR raw data with the relative phase between co-polarized and cross-polarized channel being reserved. In this method, the amplitude is quantized for Rayleigh distribution with the phase of HH and VV channel quantized for uniform distribution. In order to reserve relative phase information, the phase difference between co-polarized (HH and VV) and cross-polarized (HV and VH) channel is optimally quantized for triangular distribution. Results show that by quantizing the phase difference, the relative phase information between HH (VV) and HV (VH) channel can be well preserved.

3D city models typically consist of thousands of buildings in different types. We usually reconstruct these buildings automatically from high-resolution satellite or airborne imagery. However, for detailed roof reconstruction, 2D information offered by imagery data is not enough while DSM data is necessary. In this paper, we propose a novel level set framework for 3D building models in LOD2 with geometry structure of typical roofs. Local information is introduced towards multiphase and multichannel level set method. Its energy function is minimized when each part of roof data corresponds to the same normal vector as feature values for level set segmentation. The advantage of this method is that for complex building models, roof primitives as well as roof topology graph can be extracted from high-resolution DSM data with high accuracy, evaluated by completeness of segmentation and RMSE of 3D reconstruction. Thus, LOD2 building models can be reconstructed automatically with good performance. The very promising experimental results demonstrate the potentials of our method for large-scale building reconstruction in LOD2.

To broaden the future application of CHANG'E-1 imagery, including hyperspectral imagery (low spatial resolution of 200m) and CCD imagery (relatively high spatial resolution of 120m), an ARSIS-based method for spatial-spectral fusion is proposed in this paper, which aims at combine high spatial and high spectral resolution. Firstly, ARSIS concept is employed, in which Àtrous wavelet is used to describe images at different resolutions for multiresolution analysis. Secondly, Pulse Coupled Neural Network (PCNN) is employed to search and model a relationship between the high frequencies of the images to be fused for missing information. The ARSIS method preserves the spectral content of the original image for its very definition, and Àtrous wavelet and PCNN prove to be effective means to implement it on CHANG'E-1 Imagery. The experimental results demonstrate that the visual improvement and spectral fidelity of the proposed method outperform many conventional methods of image fusion.

Hyperspectral images (HSI) contain hundreds of bands, which brings huge amount of data. In this paper, a novel compression method based on optimal-truncation tucker decomposition for HSI is proposed. HSI tensor is firstly decomposed into complete core tensor. And then core tensor and factor matrices are truncated according to the optimal number of components of core tensor along each mode (NCCTEM), which is determined by the proposed criterion for the optimal NCCTEM and searching strategy. Experimental results show that the proposed method has the excellent reconstruction comparable to the traditional compression methods. Furthermore, it significantly reduces the compression and decompression time.

Polarimetric SAR (POLSAR) can offer more information than single-polarized SAR. At the same time dual-channel POLSAR results in much more data than the single-polarized SAR which is difficult to process on board. This paper presents a method for dual channel POLSAR raw data compression with the relative phase between HH and HV channel being reserved. In this method, the amplitude is quantized for Rayleigh distribution with the phase of HH and VV channel quantized for uniform distribution. The phase difference between HH and HV channel is optimally quantized for triangular distribution. Results show that by quantizing the phase difference, the relative phase information between HH and HV channel can be well preserved. Also the method can be used in full-polarimetric mode.

In this paper, a remote sensing building detection method is proposed, based on knowledge of environment. Digital surface model (DSM) and optical image are utilized for analyzing intricate environment of urban area. Partitioned terrain adjustment (PTA) method is proposed for alleviating terrain interference. Furthermore, vegetation interference is suppressed by optical image based reconfirming. Experiments results indicate that high accuracy detection could be obtained by our method.

Linear mixture model (LMM) has been widely used in hyperspectral image unmixing under the assumption that the mixed spectrum is performed in a linear manner. In order to obtain accurate amounts of material abundance, two constrains are usually imposed on LMM, which are abundance non-negative constraint (ANC) and abundance sum-to-one constraint (ASC). Although LMM with full constraint shows bunches of advantages in application, it is not so effective in complicated ground scene, for it couldn't simulate nonlinear factors and might distort the unmixed abundances under nonlinear interferences. In this paper, we propose a generalized constraint model by slacking the sum to one constraint of fractional abundances, which can tolerate spectral-amplitude variation caused by undulated terrain. The experiment results indicate that the proposed method outperforms LMM with full constraint significantly in terms of unmixing accuracy of specific land-covers, such as shadows caused by sheltering.

Unmixing is an important technique to extract sub-pixel information contained in hyperspectral image. Many spectrum mixture models and unmixing algorithms have been proposed, but little of them consider unmixing as an inverse problem, which is usually ill-posedness, i.e. the uniqueness, existence and stability of solution may not be satisfied simultaneously. Traditional algorithms pay more attention to the former two conditions and neglect the last one. However, actual hyperspectral data is usually noise contaminated, that means the stability of unmixing algorithm is also crucial. Motivated by this, we propose a novel linear spectrum unmixing method based on regularizing operator. By modifying the original form of cost function with respect to linear mixture model, proposed unmixing algorithm reduces the condition number as well as sensitivity to noise of image. Taking semi-simulation hyperspectral image containing noise as test data, we proved thee performance on preserving unmixing effect of our method when unmixing image is noise contaminated.

To improve the classification accuracy of image in which many classes have the similar spectrum, this paper presents a new hierarchical classification scheme for hyperspectral images (HSI). The Spectral Angle Mapping (SAM) is firstly used to combine the similar classes into large classes. Next the hierarchical classifier classifies the image with large classes and then divides every large class into normal classes further. For every large class, the most suitable feature extraction method and classifier are chosen empirically. Meanwhile, a new band selection is proposed to help every large class find the bands which can better reflect the differences of classes according to the characteristic of spectrum. Experiments are conducted on a 103-band ROSIS image of University of Pavia. The experimental results show that the hierarchical classifier is better than the single classifier used only once. Especially when the spectra of the given classes are so similar that the traditional classifiers couldn't divide them thoroughly, the proposed classifier can make it. Moreover, the hierarchical classifier can do more efficiently because it excludes some redundant bands and concentrates on the bands with slight differences.

Recently, multiple kernel learning (MKL) methods have been developed to improve the flexibility of kernel-based learning machine. The MKL methods generally focus on determining key kernels to be preserved and their significance in optimal kernel combination. Unfortunately, computational demand of finding the optimal combination is prohibitive when the number of training samples and kernels increase rapidly, particularly for hyperspectral remote sensing data. In this paper, we address the MKL for classification in hyperspectral images by extracting the most variation from the space spanned by multiple kernels and propose a representative MKL (RMKL) algorithm. The core idea embedded in the algorithm is to determine the kernels to be preserved and their weights according to statistical significance instead of time-consuming search for optimal kernel combination. The noticeable merits of RMKL consist that it greatly reduces the computational load for searching optimal combination of basis kernels and has no limitation from strict selection of basis kernels like most MKL algorithms do; meanwhile, RMKL keeps excellent properties of MKL in terms of both good classification accuracy and interpretability. Experiments are conducted on different real hyperspectral data, and the corresponding experimental results show that RMKL algorithm provides the best performances to date among several the state-of-the-art algorithms while demonstrating satisfactory computational efficiency.

Polarimetric hyperspectral images can provide spectral, spatial, and polarimetric information of a scene, which are unique and comprehensive for remote sensing applications such as growth monitoring of crops, analysis of water quality, and geology mapping, etc. The researches on polarimetric hyperspectral imaging mechanism and on image characteristics are of great importance for further information extraction and utilization of the images. The purposes of this paper are to analyze the mechanism of polarimetric hyperspectral imaging and to model such a process. The outcome of the paper will help designers and users of a polarimetric hyperspectral imaging system to further understand the system and take full advantages of it. In this paper, a polarimetric hyperspectral imaging model is proposed, in which the influence of skylight on polarization is considered, and subpixel model, polarized reflectance models, and the classical fast canopy reflectance model are combined to model the vegetation canopy. Then, a simulated scene that includes a woodland area with low shrubbery and a road is obtained by using the imaging model. Experiments analyze and discuss the simulation condition and parameters of the imaging models, the uniqueness, and usefulness of the integration of polarimetric and spectral information.

In this paper, the bandwidth of channels is finite in a practical video compression and transmission system, down-sampling techniques are usually adopted to reduce the rate of bit stream in the transmitter before video compression. Thus the reconstructed frames need to be inserted into the video sequences as the missing frames in the receiver after video decompression. Based on traditional temporal frame interpolation method using bidirectional motion vectors, an improved algorithm is proposed to classify the motional relationship to determine the weighting ratio between the adjacent frames, which is used to reconstruct the missing frame by interpolation.

Vector Quantization (VQ) is widely used for Hyper Spectral Image (HSI) compression and VQ based algorithms yield good results for reducing the amount of the data. However, the VQ based algorithms have the shortcoming of computing expensive. Many fast VQ algorithms have been proposed to reduce the computing complexity, while the algorithms consider the HSI feature rarely. We present a new framework of fast vector quantization for HSI compression, which uses the spectra characteristics of HSI adequately. The breakthrough codebook training method is calculated at the HSI feature domain, which is a low dimension structure without losing significant information, to get much lower complexity. The experimental results demonstrate that the proposed algorithms can reduce the computing time dramatically while keep the comparable reconstruction fidelity.

Polarimetric SAR Interferometry (PolInSAR) provides a useful tool for forestry parameters retrieval at L-band. Three-stage inversion process is a traditional way to retrieve these parameters, but it has several shortcomings while ground phase estimation is processed. In order to overcome these shortcomings, an algorithm of ground topography estimation using PolInSAR image by means of coherence set is proposed in this paper. The coherence region derived from numerical range is combined with RVoG model to obtain accurate estimation of ground topography. Simulated image and SIR-C image of forestry area are used to validate the proposed algorithm.

Achieving high target recognition accuracy is a pursuing and challenging issue for hyperspectral data analysis. The complicated imaging environment and noise interference lead to heterogeneous spectra within the homogeneous object, which makes the current spectral target recognition methods be lack of robustness. In this paper, a robust spectral target recognition method is proposed based on the combined spectral signatures, in which two key techniques are concerned. One is support vector data description (SVDD), which can tolerate the spectral variations of different pixels in the same object. Another is an effective spectral signature combined of spectral reflectance and spectral derivative, which can be robust to data characteristics with different spectral-amplitude variation. The proposed method outperforms the classical methods with only spectral reflective information in term of target recognition accuracy and robustness.

Ground Control Points (GCPs) are one of the most important data used in many fields of Remote Sensing. The number and distribution of GCPs are always the key factors for the success of some researches. A GCPs selection method by integrating the three dimensional spatial information (i.e. the earth coordinates (X, Y, Z) ) and the corresponding feature information underlying the data itself was proposed. To testify the performance of this method, a Rational Function Model Resolving experiment is conducted. Experiment results show that the accuracy and time-consuming performance are both improved using GCPs selected by the proposed method.

In absence of prior knowledge of the pure signatures (endmembers) existing in a remotely sensed image which is often the case, the mean spectra of the pixel vectors directly extracted from the image scene are usually used in unmixing problems. This approach ignores some important statistical properties of the extracted samples, thus, leads to suboptimal solutions. This paper proposes a novel method for unmixing of hyperspectral imagery through a classification model. It first transforms the unmixing problem into a classification task where the abundances of endmembers can be estimated with the help of a set of artificially made classes using known endmember compositions. Support vector machine, as an efficient classifier, is used to realize this model. The proposed method exploits the statistical nature of the extracted endmember representatives. Experiments on hyperspectral images validate the high performance of the proposed method in unmixing which is a key subpixel information detection technique.

In this paper, a new method for improving the classification performance of hyperspectral images with the aid of derivative information is investigated. First, spectral features are filtered and derivatives of different orders at different sampling intervals are computed. Then, the suitable spectral magnitude features and different derivative features are chosen by using segmented principle component analysis feature extraction method with optimal parameters, and are stacked to constitute a new feature cube. Finally, the efficacy of the spectral derivatives in improving the classification performance of the hyperspectral data is testified using support vector machine for AVIRIS hyperspectral data. The experimental results show that the proposed method can improve the classification accuracy compared to the traditional classification techniques with spectral magnitude features even on very small training samples.

The projection errors caused by curvature of the earth and relief are two important problems in geometric correction, especially in the case of imaging with large view angles. General polynomial correction model is only effective to flat area and ineffective to correct projection errors caused by both curvature of the earth and relief. According to the generated characteristic of the projection errors, this paper proposes a self-adjustive polynomial model which adds an adjustive factor in the large view angle direction to make effective correction on distorted images with both kinds of projection errors in the absence of precise attitude parameters. This paper first analyzes the principle of projection errors caused by curvature of the earth and relief, and then proposes the improved polynomial model. Experiments show that the proposed model has greatly improved accuracy for correcting the projection errors in the large angle direction compared with general polynomial models.

In recent years, remote sensing images with high resolution are increasingly applied in change detection and disaster assessment. Compared with the traditional pixel-based methods, object-oriented image processing techniques have attracted more attention for high resolution images. In this paper, we aim to research the object-oriented change detection for urban area. A new multi-scale segmentation algorithm is proposed so as to obtain accurate image objects, and a pre-processing step is adopted to improve the computation efficiency. In order to testify the performance of proposed method, experiments are conducted on QuickBird images. The experimental results show that accurate image objects and changed area can be acquired in appropriate scales.

An efficient superresolution technique through spatial-spectral data fusion for hyperspectral (HS) imagery is proposed in this letter. The spatial and spectral contents of an HS image are extracted using a linear mixture model and a fully constrained least squares unmixing technique. These data are then combined using a spatial correlation model through a learning-based superresolution mapping (SRM) algorithm. The proposed spatial correlation model realistically simulates a mapping model between the low-resolution (LR) HS image and its subsampled version ( LR2HS image) to train the designed SRM algorithm for mapping from the LR to high resolution. The experiments on real HS images validate the accuracy and low complexity of the proposed autonomous technique for key information detection in HS imagery.

The curse of dimensionality is the main reason for the computational complexity and the Hughes phenomenon in supervised hyperspectral classification. Previous studies seldom consider in a simultaneous fashion the real situation of insufficiency of available training samples, particularly for small land covers that often contain the key information of the scene, and the problem of complexity. In this paper, the capabilities of a feature reduction technique used for discrimination are combined with the advantages of a Bayesian learning-based probabilistic sparse kernel model, the relevance vector machine (RVM), to develop a new supervised classification method. In the proposed method, the hyperdimensional data are first transformed to a lower dimensionality feature space using the feature reduction technique to maximize separability between classes. The transformed data are then processed by a multiclass RVM classifier based on the parallel architecture and one-against-one strategy. To verify the effectiveness of the method, experiments were carried out on real hyperspectral data. The results are compared with the most efficient supervised classification techniques such as the support vector machine using appropriate performance indicators. The results show that the proposed method performs better than the other approaches particularly for small and scattered landcover classes which are harder to be precisely classified. In addition, this method has the advantages of low computational complexity and robustness to the Hughes phenomenon.

Need for a priori knowledge of the components comprising each pixel in a scene has set the endmember determination, rather than the endmember abundance quantification, as the primary focus of many unmixing approaches. In the absence of the information about the pure signatures present in an image scene, which is often the case, the mean spectra of the pixel vectors, directly extracted from the scene, are usually used as the pure signatures' spectra. This approach which is mathematically optimized for unmixing problems with a priori known information ignores some statistical properties of the extracted samples and leads to a suboptimal solution for real situations. This paper proposes a novel learning-based unmixing-to-classification conversion model to treat the abundance quantification task as a classification problem. Support vector machine, as an efficient classifier, is used to realize this model. It exploits the statistical nature (endmember spectral variability) of the extracted endmember representatives from the hyperspectral scene, rather than solving the problem according to the ideal model in which only the mean spectra of each training sample set is used. Several experiments are carried out on simulated and real hyperspectral images. The obtained results validate the high performance of the proposed technique in abundance quantification which is a key subpixel information detection capability.

In land-cover analysis of hyperspectral remotely sensed images through supervised classification methods, a frequent problem is that the available training samples corresponding to different land-covers are not sufficient. This problem is especially severe for small land-covers and targets which often include the key information of the scene. Furthermore, degrading due to “boundary effect” is more serious in classification of small and scattered patches of land-covers. In this paper, a new supervised hyperspectral classification method through application of a discriminant data transformation in joint with a Bayesian learning-based probabilistic sparse kernel model, i.e., relevance vector machine (RVM), is proposed. The proposed method outperforms other efficient approaches in terms of classification accuracy, robustness to Hughes phenomenon (lack of accuracy due to too small ratio of training sample number to feature number), and computational complexity in particular for small and scattered land-cover classes which are harder to be precisely classified.

Target detection is a hot topic and key technique of SAR image interpretation. There are many detection methods, such as CFAR detector and Extended Fractal (EF) feature detector. In order to overcome their shortcomings and combine their merits at the same time, the combination of some different detection methods need be implemented. Granularity computing is just an approach that solves the problem at different granularity space due to different principles. Therefore, SAR image target detection based on granularity synthetic algorithm of quotient space theory is proposed in this paper. Firstly, CFAR detector and EF feature detection method are performed to generate different detection results as coarse granularity spaces. Then combine the different quotient spaces and construct the fine granularity space by using granularity synthesis algorithm. Finally, obtain the final target detection result. The experimental result of RADARSAT-I C band SAR image proves that the proposed algorithm is effective.

This paper proposes a two-stage registration method for SAR and optical images based on multi-features and multi-constraints. In the first stage, closed regions are extracted automatically to achieve the coarse mapping parameters as geometrical restriction. In the second stage, Harris corner points and cross-road features are extracted, and then correlation analysis and mutual information are utilized to match the corresponding control points. After that, multi-constraints are used to delete the false matched points. The retained ones are served as ground control points for registration. The experimental results show that the method can reduce the possibility of false matching effectively and the registration error is within one pixel.

Hyperspectral image provides rich information of ground covers, which has been brought great attention. Combining hyperspectral spatial and spectral constraint, an image segmentation method based on region active contour is proposed in this paper. The energy function in Chan-Vese's method is improved and both spatial and spectral information are employed. Spatial term of the function is restricted by global spatial information and intensity consistency in homogeneous region, while spectral term is restricted by spectral similarity of the target. Finally the image is segmented by minimizing the energy function. In order to verify the effectiveness of the proposed method, experiments are conducted on AVIRIS data. Results show that the method can extract indistinct contours of interested target in hyperspectral image, and reduce the influence caused by mixed pixels and the shadows around the target, and also adapts to complex scene in some degree.

Small-target detection in infrared imagery with a complex background is always an important task in remote-sensing fields. Complex clutter background usually results in serious false alarm in target detection for low contrast of infrared imagery. In this letter, a kernel-based nonparametric regression method is proposed for background prediction and clutter removal, furthermore applied in target detection. First, a linear mixture model is used to represent each pixel of the observed infrared imagery. Second, adaptive detection is performed on local regions in the infrared image by means of kernel-based nonparametric regression and two-parameter constant false alarm rate (CFAR) detector. Kernel regression, which is one of the nonparametric regression approaches, is adopted to estimate complex clutter background. Then, CFAR detection is performed on “pure” target-like region after estimation and removal of clutter background. Experimental results prove that the proposed algorithm is effective and adaptable to small-target detection under a complex background.

Hyperspectral images (HSI) regularly contain hundreds of bands, which are of different importance in the application. Most HSI compression methods usually deal with most bands in the same way, and they do not take the difference of different bands into consideration, which may cause the loss of important spectral information. In order to preserve the spectral information of interest for applications, a new band-of-interest (BOI)-preserving-based HSI compression method is proposed. The conception of BOI is proposed because some bands are significant in the specific applications, and BOI selection methods are chosen according to application requirements. BOI selection is first performed according to application measurements. Then, BOI information is fed into recursive bidirection prediction (RBP) and set partition in hierarchical trees (SPIHT) compression scheme which uses RBP for spectral decorrelation followed by SPIHT algorithm for coding the resulting decorrelated residual images. More bits are allocated to BOI to preserve BOI by two approaches, respectively. Compress BOI and non-BOI bands directly with low distortion and high distortion, respectively, and compress all bands with low distortion and perform a postcompression truncation. Experiments are implemented with different settings using AVIRIS images. Results indicate that the proposed two methods both can achieve excellent compression efficiency and reconstructed quality. In addition, they can improve the application effect in both material classification and target recognition. Compared with non-BOI compression algorithm, at the compression ratio of 80, the proposed methods improve the classification accuracy by 2% and target recognition accuracy by 9%.

Target detection with SAR image is one of important research topics in remote sensing. In this paper, a kernel regression-based predicting method is proposed for target detection in SAR image. Badly speckle noise and background clutter are two main factors which make the target detection with SAR image difficult. In the proposed method, the kernel regression on local image is used to exactly predict the background interferences and make Gaussian assumption in conventional detector better followed after kernel regression-based prediction and suppression of background clutter. Thus, final CFAR detection is performed on the background clutter-removed SAR image. Experiments conducted on real SAR image show that the proposed algorithm can effectively predict and suppress background clutters, and greatly improve the performance of the conventional CFAR detector.

A fast and efficient spatial-spectral fusion method for resolution enhancement of hyperspectral imagery is proposed in this paper. A linear mixture model and fully constrained least squares based unmixing algorithm are applied for spectral unmixing of the hyperspectral imagery and the resulted fractional images are processed using a spatial-spectral information correlation model through a learning-based super-resolution mapping technique. To validate the performance of the method, experiments are carried out on real images. The obtained results validate the reliability of the technique. The main advantages of the proposed method include its autonomous nature so that it doesn't need any high resolution secondary source of data, its acceptable performance, and its low computational cost which makes it favorable for realtime target recognition and tracking applications.

A new spatial-spectral data fusion technique based on spectral mixture analysis and super-resolution mapping for spatial resolution enhancement of hyperspectral imagery is proposed in this paper. To this end, a linear mixture model and a constrained least squares based unmixing algorithm are applied for spectral unmixing of the hyperspectral imagery and the resulted fractional images are processed based on a spatial-spectral information correlation model through a super-resolution mapping technique. The obtained results validate the effectiveness of the method. It doesn't need any a priori information of the scene or secondary high resolution source of data, and is fast.

The crucial problem of multisensor image registration is how to establish the correspondences between the features extracted from reference and input images. Generally, most existing methods only consider how to extract features, the quality of the features is ignored. In this paper, we combine scale invariant feature transform (SIFT) and maximally stable extremal region (MSER) to initialize the process of extracting plenty of control points(CPs) pairs. A concept of distribution quality(DQ) is introduced to quantify the distribution of CPs pairs, experimental analysis is illustrated to analyze the effects of CPs pairs number and DQ on the registration root mean square error(RMSE). An automatic feature matching and selection algorithm is then proposed, extensive experiments demonstrate the effectiveness of the proposed algorithm by aligning real images.

With much richer information than multispectral image, hyperspectral image has been applied in many aspects such as agriculture, environment, military etc. But higher spectral resolution is accompanied by a huge volume of image data, which will result in excessive computing time and data complexity for transmission and storage, so it is necessary to compress hyperspectral image. Because of limit of spatial resolution, some targets that we are interested in are usually in small size and belong to high frequency. In order to preserve such information as much as possible, a hierarchical compression method with protection strategy for hyperspectral image is proposed in this paper, which can protect information of interest (IOI) to some extent, including spatial and spectral IOI. The experimental results show that under the same compression rate, the proposed method can achieve better performance in target detection application than typical SPIHT method.

In order to support spaceborne hyperspectral sensor system design, an end-to-end simulation model for spaceborne hyperspectral image generation starting from the airborne image has been developed in this paper. Airborne image after being resampled both in the space and spectrum performs as the at-sensor radiance that is the input of the sensor model. Sensor model is the main part of proposed model. According to the sensor's imaging process, the simulation is divided into four sub-modules, which are optics, detector, electronics parts and system noise. Based on the theory of optical transfer function (OTF), each sub-module can be treated as a spatial filter and thus its simulation can be realized in the spatial frequency domain. Using parameters of spaceborne sensor Hyperion as well as the image acquired by Airborne Visible and Infrared Imaging Spectrometer (AVIRIS), the validity of the proposed model for sensor design and operation are also demonstrated in the paper.

In this letter, a selective kernel principal component analysis (KPCA) algorithm based on high-order statistics is proposed for anomaly detection in hyperspectral imagery. First, KPCA is performed on the original hyperspectral data to fully mine the high-order correlation between spectral bands. Then, the average local singularity (LS) is defined based on the high-order statistics in the local sliding window, which is used as a measure for selecting the most informative nonlinear component for anomaly detection. By the selective KPCA, information on anomalous targets is extracted to maximum extent, and background clutters are well suppressed in the selected component. Finally, the selected component with maximum average LS is used as input for anomaly detectors. Numerical experiments are conducted on real hyperspectral images collected by the airborne visible/infrared imaging spectrometer. The results strongly prove the effectiveness of the proposed algorithm.

A multiple-component scattering model (MCSM) is proposed to decompose polarimetric synthetic aperture radar (PolSAR) images. The MCSM extends a three-component scattering model, which describes single-bounce, double-bounce, volume, helix, and wire scattering as elementary scattering mechanisms in the analysis of PolSAR images. It can be found that double-bounce, helix, and wire scattering are predominant in urban areas. These elementary scattering mechanisms correspond to the asymmetric reflection condition that the copolar and cross-polar correlations are not close to zero. The MCSM is demonstrated with a German Aerospace Center (DLR) Experimental Synthetic Aperture Radar (ESAR) L-band full-polarized image of the Oberpfaffenhofen Test Site Area (DE), Germany, which was obtained on September 30, 2000. The result of this decomposition confirmed that the proposed model is effective for analysis of buildings in urban areas.

In this paper, a new algorithm is proposed for resolution enhancement in hyperspectral images (HSIs). The key techniques are included: spectral unmixing and superresolution mapping, by which spatial and spectral information of HSIs is substantially fused. The proposed algorithm first represents each pixel in scene as a linear combination of landcover spectra and noise. Then, a fully constrained least squares algorithm is used to obtain the proportion of each landcover in each pixel, i.e., abundance, subjecting to two constraints: nonnegativity and sum-to-one. After that, superresolution mapping is performed on high-resolution grids according to spectral unmixing abundances of each landcover and following spatial correlation of clutters. Thus, by reasonably integrating spatial and spectral information of landcovers in HSIs, the proposed algorithm realizes resolution enhancement of the HSIs based on a back-propagation neural network. The proposed algorithm is independent from thea prioriinformation associated with original HSIs, i.e., a main merit of the algorithm. In order to evaluate the performance of the new algorithm, numerical experiments are conducted on both simulated images and real HSIs collected by the Airborne Visible/Infrared Imaging Spectrometer. The proposed algorithm is compared with the traditional method in the experiments. The experimental results prove that the proposed algorithm effectively enhances the resolution of HSIs and indicate its applicability.

In this letter, a geometry-based feature-selection method is proposed for efficient analysis of hyperspectral imagery. It searches the vertices that form the largest simplex iteratively in pixel space. These vertices are representative subsets of spectral bands. A distance measure is introduced in the simplex volume comparison for fast implementation of the proposed method. Fast principal component analysis and spectral band indexing are suggested for data preprocessing. This method can be implemented in supervised or unsupervised manner. It is automatic, fast, and distribution-free. Experimental results show the superiority of the proposed method in terms of quality and speed

In this paper, a selective kernel principal component analysis algorithm is proposed for anomaly detection in hyperspectral imagery. The proposed algorithm tries to solve the problem brought by high dimensionality of hyperspectral images in anomaly detection. This algorithm firstly performs kernel principal component analysis (KPCA) on the original data to fully mine high-order correlation between spectral bands. Then, high-order statistics in local scene are exploited to define local average singularity (LAS), which is used to measure the singularity of each nonlinear principal component transformed. Based on LAS, one component transformed with maximum singularity is selected after KPCA. Finally, with RX detector, anomaly detection is performed on the component selected. Numerical experiments are conducted on real hyperspectral images collected by AVIRIS. The results prove that the proposed algorithm outperforms the conventional RX algorithm

Anomaly detection is one of the most important applications for hyperspectral images. In this paper, a new algorithm called unmixing component analysis (UCA) is proposed for anomaly detection in hyperspectral imagery. The proposed algorithm firstly performs spectral unmixing only with background endmembers on original hyperspectral images, and the unmixing error data are retained. Secondly, kernel principal analysis (KPCA) is performed on the error data to concentrate and extract useful information about anormalous targets. After that, non-linear principal component that includes the most information about anomalous targets is selected based on non-gaussianity measures. Finally, anomaly detection is conducted on the selected non-linear principal component using RX detector. Numerical experiments are performed on AVIRIS data with 126 bands. The experimental results show the proposed algorithm greatly modifies performance of the conventional RX algorithm and has good detection performance with low false alarms.

Based on the basic principle of PolInSAR and the coherent scattering model of random volume over ground, the inversion of forest parameters of PolInSAR can be characterized by a six-dimensional non-linear parameter optimization problem. However, the global optimal can't be obtained using the traditional gradient-based optimization algorithms. Therefore, a global optimization inversion scheme of forest parameters of PolInSAR based on genetic algorithm is presented. We generate a validity test using SIR-C L-band repeat-pass PolInSAR data of the area of Tien Shan, China. The preliminary results accord with the range of the parameters of the fact. Performances of different GAs and effects of different parameters are compared. SGA is influenced by the mutation rate strongly, but GA with tournament of two generations is independent of the mutation rate.

In this paper, change detection for urban area based on multiple sensor information fusion is studied. The images acquired at different times are used to identify the differences during the process of city construction and reconstruction. The proposed method in this paper consists of three steps: image pre-processing and registration, information fusion for multiple sensor images and image change detection. Wavelet packet transform is used in the fusion stage. More detailed features can be extracted by high frequency components as well as low frequency components decomposition. The experiments are carried on optical and SAR images taken at different periods. The results show that the method based on multi-source information fusion can effectively detect changed regions.

In this paper, a kernel-based invariant subspace detection method is proposed for small target detection of hyperspectral images. The method combines kernel principal component analysis (KPCA) and the linear mixture model (LMM). The LMM is used to describe each pixel in the hyper-spectral image as a mixture of target, background and noise. The KPCA is used to build subspaces of the target and background. A generalized likelihood ratio test is used to detect whether each pixel in the hyperspectral image includes the target. Numerical experiments are performed on AVIRIS hyperspectral data with 126 bands. The experimental results show the effectiveness of the proposed method and prove that this method can commendably overcome spectral variability in hyperspectral target detection, and it has good ability to separate target from background.

In this paper, an unsupervised subspace linear spectral unmixing algorithm for hyperspectral data is investigated, which includes two key techniques: subspace minimum noise fraction transformation (SMNFT) and independent component analysis (ICA). The SMNFT is used to reduce noise, remove correlation between neighboring bands and determine intrinsic dimensionality of hyperspectral data. Then the ICA is applied to unmix hyperspectral images and obtain independent endmembers. The main merits of the proposed algorithm are that it can fast unsupervisedly separate useful and independent endmembers resident in hyperspectral images. The experimental results demonstrate that this algorithm can effectively identify independent endmembers. Meanwhile, the results show high computational efficiency of the algorithm. The time consumed by the SMNFT is merely one fifth of the traditional minimum noise fraction transformation.

A kernel based nonlinear subspace projection (KNSP) method is proposed for reduction of hyperspectral image dimensionality. This method involves three steps: subspace partition of full data space, feature extraction based on kernel principal component analysis (KPCA) in subspace and feature selection based on class separability criterion. The main merit of the proposed method is that it is more suitable for feature extraction than linear principal component analysis (PCA) and segmented principal component: transformation (SPCT), in particular, when hyperspectral data have nonlinear characteristics. In order to testify the effectiveness of the KNSP method for reduction of hyperspectral image dimensionality, hyperspectral image classification is performed on AVIRIS data. Experimental results show that when the hyperspectral dimensionality is reduced to a few features, the average classification accuracy of the new method is higher than those of PCA and SPCT methods.

Classification is one of the most important tasks for remote sensing image processing. Most of the existing supervised classification methods are based on traditional statistics, which can provide ideal results when sample size is tending to infinity. However, only finite samples can be acquired in practice. In addition, many methods are constrained by high data dimension of hyperspectral images. In this paper, a novel learning method, the support vector machine (SVM), is applied to hyperspectral data classification. This method does not suffer the limitations of data dimensionality and limited samples. The foundations of the SVM have been developed by Vapnik (1995) and are gaining popularity in field of machine learning due to many attractive features and promising empirical performance. In our experiment, the support vectors, which are critical for classification, are obtained by learning from the training samples. Choosing appropriate kernel function and suitable parameters, better classification results are obtained.

Data fusion is widely used in many fields in the last two decades. With the development of the hyperspectral sensor technique, the concept of data fusion is introduced into the classification investigation of hyperspectral data recently. Consensus theory is one of the data fusion methods, in which how to properly choose and assign the weights is very important for the improvement of fusion classification accuracy. In this paper, a new method of hyperspectral image classification is studied, which is realized by two key steps: division of data sources based on adaptive subspace decomposition (ASD) and fusion classification based on consensus theory. In order to testify the effectiveness of the proposed method, computer simulations are conducted on AVIRIS data. The experiment investigation shows that the classification result in our new method is improved compared with both the equal weights and conventional approach in the full data space.

This paper proposed a novel adaptive subspace decomposition (ASD) method for hyperspectral data dimensionality reduction. The new method is mainly based on the criterions of the correlation matrix and the variability ratio of eigenvalues and it can overcome the disadvantages of the conventional Principal Component Analysis (PCA) method. To evaluate the effectiveness of the new method, experiments are conducted on AVIRIS data. The data dimensionality is reduced from 100 to 5 bands. When applied to classification, the results show that the new method keeps more detail information than the conventional PCA method and can get higher classification accuracy.