Detection In Hyperspectral Imagery Research Articles

Hyperspectral Anomaly Detection With Robust Graph Autoencoders

Anomaly detection of hyperspectral data has been gaining particular attention for its ability in detecting targets in an unsupervised manner. Autoencoder (AE), together with its variants can not only extract intrinsic features automatically but also detect anomalies that differ dramatically from others. Many AE-driven algorithms are, thus, proposed for anomaly detection in hyperspectral imagery (HSI), but they suffer from two problems: 1) when there exist anomalies in the training set, AE can generalize so well that it can also learn the abnormal patterns well, thereby reducing the ability to distinguish anomalies from the background and 2) geometric structure among samples are lost in latent space of AE, which is vital in hyperspectral anomaly detection. To tackle these problems, we propose a robust anomaly detector based on the AE framework, named robust graph AE (RGAE) detector, in this article. To be specific, we propose a robust AE framework with <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\ell _{2,1}$ </tex-math></inline-formula> -norm that is robust to noise and anomalies during training. Meanwhile, we embed a superpixel segmentation-based graph regularization term (SuperGraph) into AE. This strategy can preserve the geometric structure and the local spatial consistency of HSI simultaneously and also effectively reduce the searching space and execution time for each pixel. Extensive experiments are conducted on five datasets, and the results demonstrate that our method has a better detection performance, after comparing with other state-of-the-art hyperspectral anomaly detectors.

Discriminative Multiple-Instance Hyperspectral Subpixel Target Characterization

Subpixel target detection in hyperspectral imagery is challenging since subpixel targets are smaller in size than the resolution of a single pixel and accurate pixel-level labels on subpixel targets are often unavailable. In particular, this article addresses the problem of learning a prime prototype target signature from imprecisely labeled highly mixed hyperspectral data. Two algorithms, multiple-instance subpixel adaptive cosine estimator (MI-SPACE) and multiple-instance subpixel spectral matched filter (MI-SPSMF), based on multiple-instance learning framework are presented. The proposed methods aim to learn a discriminative prime target signature by maximizing the posterior detection statistics of subpixel hyperspectral targets for the correspondingly proposed subpixel adaptive cosine estimator (SPACE) and subpixel spectral matched filter (SPSMF) detectors, which are also developed in this article. Experimental results demonstrate the effectiveness of the proposed methods on both simulated and real-field hyperspectral subpixel target detection tasks.

Target Detection In Hyperspectral Imagery Based on Improved Osp Algorithm

Target Detection In Hyperspectral Imagery Based on Improved Osp Algorithm

Matrix Autoregressive Model for Hyperspectral Anomaly Detection

For anomaly detection in hyperspectral imagery, the scene can be treated as a combination of the background and the anomalies. Once a pure background hyperspectral image (HSI) is obtained, the anomalies can be easily located. This paper detects the anomalies via a matrix autoregressive model (MARM) to reconstruct the background HSI. Specifically, some informative and discriminative bands are firstly selected and come into a new HSI with less bands. Secondly, the new HSI can be treated as a collection of profiles in the row direction. Based on this, the background can be regularly reconstructed via the MARM. The regressive model not only respects the original matrix structure in the row profiles, but also utilizes both the spatial and spectral correlation for the detection process. Finally, the classical Reed Xiaoli detector is applied to the difference cube between the band selected HSI and the HSI reconstructed by MARM, achieving a final detection map with higher accuracy. Experimental results and data analysis on four different sensors captured datasets with different resolutions have validated the effectiveness of the proposed method.

Target Detection in Hyperspectral Imagery Using Atmospheric-Spectral Modeling and Deep Learning

Target detection (TD) in spectral imagery is an evolving analytical perspective with broader application potential. The perceived distinctness of the spectral signatures of the materials of interest is exploited for detecting targets in hyperspectral imagery. Space-time varying atmospheric perturbances on the radiation reaching a remote sensor are major limitations for designing a successful TD framework. Incorporating atmospheric components into a target detection framework is vital for practical applicability. Considered a general approach for flexibility, scalability, and optimal prediction, deep learning (DL) methods are increasingly used in various remote sensing applications. However, their potential for TD is relatively unexplored. Especially, the ability to provide training data sufficient for DL models and maintaining the functional relevance of the sparsely distributed targets in hyperspectral imagery are crucial for TD frameworks. This letter presents a novel method for training of DL architecture, called Deep Spectral Target Detector (DSTD). The proposed method includes a semi-supervised multi-scenario forward radiative transfer modelling (RTM) for the simulation of spectral signatures of various targets as training data suitable for the functional requirements of a typical DL architecture. We implemented the DSTD on a TD application-specific benchmark AVIRIS-NG airborne hyperspectral imagery acquired over a study site near Ooty, India. Compared to state-of-art statistical target detectors, the detection performance of the DSTD is superior to equivalent. Further, RTM-based training yields a robust model, impervious to the atmospheric mismatches between target collection and TD environments, indicating the potential for a similar approach to developing efficient DL-based methods for TD in the future.

Symmetric Information–Theoretic Metric Learning for Target Detection in Hyperspectral Imagery

Metric learning-based methods, which yield great performance and show considerable potential to improve the performance of hyperspectral image processing, aim to calculate the Mahalanobis distance metric matrix. In this article, we proposed a symmetric information-theoretic metric learning (SITML) method for hyperspectral target detection. The SITML algorithm is designed based on the classical information-theoretic metric learning (ITML) and, minimizes the differential Kullback–Leibler (KL) divergence. To enhance both of the detection performance and the generalization ability, we build metric spaces from the neighborhood of training samples to preserve the local discriminative information. Then, we conduct local pairwise constraints to maximize the Jeffery divergence (also named the symmetric KL divergence) of two multivariate Gaussian distributions to solve the problem of an asymmetric KL divergence. Finally, we use a closed-form solution to solve the optimization problem. Intensive experiments on three hyperspectral datasets indicate that SITML outperforms the classical ITML algorithm and other state-of-the-art target detection methods.

Pyramid self-attention mechanism-based change detection in hyperspectral imagery

To address the problem of “pseudochange” caused by illumination, phasing, and shadows in multiperiod remote sensing images, a bitemporal, hyperspectral remote sensing image change detection method is proposed. The method uses a pyramid self-attention mechanism, and the attention module is introduced to simulate the attention mechanism of human eyes, where more attention is given to a small number of important objects. The model architecture uses a general encoder–decoder paradigm, in which shared encoders extract common features, whereas individual decoders learn task-specific representations. The classifier takes fused data to locate where the changes occurred. The method is tested on the ZY1-CD dataset.

Onboard target detection in hyperspectral image based on deep learning with FPGA implementation

Onboard target detection of Hyperspectral Imagery (HSI) is widely adopted in the field of remote sensing. It requires high detection accuracy and low computational complexity for processing a large volume of HSI data. In this study, a Locally Preserving Discriminative Broad Learning (LPDBL) was introduced for target detection due to its simple, excellent generalization ability, and its competitive performance. The detection was done through spatial-spectral information, band selection, and estimation of the covariance matrix. The fisher discriminant method was used to reduce the dimension of HSI data. Weights was adjusted through manifold regularization in order to enhance the detection ability of the proposed method. To study the performance of the proposed LPDBL, experiment was conducted on two different datasets of HSI. The results revealed that the proposed method performed better and suitable for target detection. The LPDBL was implemented on Virtex-7 Field Programmable Gate Array (FPGA) board. Furthermore, the LPDBL technique was practically validated by two different techniques such as a broad learning system (BLS) and Automatic Target Detection in HSI (ATD-HSI). The result obtained from the FPGA was very close to the actual target position.

Hierarchical Suppression Based Matched Filter for Hyperspertral Imagery Target Detection.

Target detection in hyperspectral imagery (HSI) aims at extracting target components of interest from hundreds of narrow contiguous spectral bands, where the prior target information plays a vital role. However, the limitation of the previous methods is that only single-layer detection is carried out, which is not sufficient to discriminate the target parts from complex background spectra accurately. In this paper, we introduce a hierarchical structure to the traditional algorithm matched filter (MF). Because of the advantages of MF in target separation performance, that is, the background components are suppressed while preserving the targets, the detection result of MF is used to further suppress the background components in a cyclic iterative manner. In each iteration, the average output of the previous iteration is used as a suppression criterion to distinguish these pixels judged as backgrounds in the current iteration. To better stand out the target spectra from the background clutter, HSI spectral input and the given target spectrum are whitened and then used to construct the MF in the current iteration. Finally, we provide the corresponding proofs for the convergence of the output and suppression criterion. Experimental results on three classical hyperspectral datasets confirm that the proposed method performs better than some traditional and recently proposed methods.

Prior-Based Tensor Approximation for Anomaly Detection in Hyperspectral Imagery.

The key to hyperspectral anomaly detection is to effectively distinguish anomalies from the background, especially in the case that background is complex and anomalies are weak. Hyperspectral imagery (HSI) as an image-spectrum merging cube data can be intrinsically represented as a third-order tensor that integrates spectral information and spatial information. In this article, a prior-based tensor approximation (PTA) is proposed for hyperspectral anomaly detection, in which HSI is decomposed into a background tensor and an anomaly tensor. In the background tensor, a low-rank prior is incorporated into spectral dimension by truncated nuclear norm regularization, and a piecewise-smooth prior on spatial dimension can be embedded by a linear total variation-norm regularization. For anomaly tensor, it is unfolded along spectral dimension coupled with spatial group sparse prior that can be represented by the l2,1 -norm regularization. In the designed method, all the priors are integrated into a unified convex framework, and the anomalies can be finally determined by the anomaly tensor. Experimental results validated on several real hyperspectral data sets demonstrate that the proposed algorithm outperforms some state-of-the-art anomaly detection methods.

Anomaly Detection in Hyperspectral Imagery Based on Gaussian Mixture Model

Hyperspectral images (HSIs) with rich spectral information have been widely used in many fields. Anomaly detection is one of the most interesting and important applications. In this article, a novel Gaussian mixture model (GMM)-based anomaly detection (GMMD) method for HSI is proposed. The main contributions of this article are a new GMM-based extraction approach for extracting the anomaly pixels and an effective GMM-based weighting approach for fusing the extracted anomaly results. Specifically, based on the fact that the spectral values of anomaly pixels in some bands are different from those of background pixels, we propose a GMM-based anomaly extraction approach in which the HSI is characterized by the GMM and the anomaly pixels are extracted by a range prescribed by the GMM parameters. In order to fuse the extracted anomaly results, the GMM-based weighting method is introduced to adaptively construct the detection map. The detection map is rectified by using a guided filter to obtain the final anomaly detection map. Experimental results conducted on four hyperspectral data sets demonstrate the superior performance of the proposed GMMD method.

Total Variation and Sparsity Regularized Decomposition Model With Union Dictionary for Hyperspectral Anomaly Detection

Anomaly detection in hyperspectral imagery has been an active topic among the remote sensing applications. It aims at identifying anomalous targets with different spectra from their surrounding background. Therefore, an effective detector should be able to distinguish the anomalies, especially for the weak ones, from the background and noise. In this article, we propose a novel method for hyperspectral anomaly detection based on total variation (TV) and sparsity regularized decomposition model. This model decomposes the hyperspectral imagery into three components: background, anomaly, and noise. In order to distinguish effectively these components, a union dictionary consisting of both background and potential anomalous atoms is utilized to represent the background and anomalies, respectively. Moreover, the TV and the sparsity-inducing regularizations are incorporated to facilitate the separation. Besides, we present a new strategy for constructing the union dictionary with the density peak-based clustering. The proposed detector is evaluated on both simulated and real hyperspectral data sets and the experimental results demonstrate its superiority compared with several traditional and state-of-the-art anomaly detectors.

Low-Rank and Sparse Decomposition With Mixture of Gaussian for Hyperspectral Anomaly Detection.

Recently, the low-rank and sparse decomposition model (LSDM) has been used for anomaly detection in hyperspectral imagery. The traditional LSDM assumes that the sparse component where anomalies and noise reside can be modeled by a single distribution which often potentially confuses weak anomalies and noise. Actually, a single distribution cannot accurately describe different noise characteristics. In this article, a combination of a mixture noise model with low-rank background may more accurately characterize complex distribution. A modified LSDM, by modeling the sparse component as a mixture of Gaussian (MoG), is employed for hyperspectral anomaly detection. In the proposed framework, the variational Bayes (VB) algorithm is applied to infer a posterior MoG model. Once the noise model is determined, anomalies can be easily separated from the noise components. Furthermore, a simple but effective detector based on the Manhattan distance is incorporated for anomaly detection under complex distribution. The experimental results demonstrate that the proposed algorithm outperforms the classic Reed-Xiaoli (RX), and the state-of-the-art detectors, such as robust principal component analysis (RPCA) with RX.

Coincidence of the Rao Test, Wald Test and GLRT for anomaly detection in hyperspectral imagery

Anomaly detection methods are designed to detect targets (small anomalies) without a priori information on the target spectral signature. In this letter, we deal with the problem of anomaly detection for hyperspectral images based on the Gaussian model assuming that the background obeys a real-valued Gaussian multivariate distribution with unknown covariance matrix. This model is widely used in hyperspectral images. We derive the corresponding Rao and Wald tests, and show that both the two tests are equivalent to the generalized likelihood ratio test.

Spectral Adversarial Feature Learning for Anomaly Detection in Hyperspectral Imagery

Theoretically, hyperspectral images (HSIs) are capable of providing subtle spectral differences between different materials, but in fact, it is difficult to distinguish between background and anomalies because the samples of anomalous pixels in HSIs are limited and susceptible to background and noise. To explore the discriminant features, a spectral adversarial feature learning (SAFL) architecture is specially designed for hyperspectral anomaly detection in this article. In addition to reconstruction loss, SAFL also introduces spectral constraint loss and adversarial loss in the network with batch normalization to extract the intrinsic spectral features in deep latent space. To further reduce the false alarm rate, we present an iterative optimization approach by a weighted suppression function that depends on the contribution rate of each feature to the detection. In particular, the structure tensor matrix is adopted to adaptively calculate the contribution rate of each feature. Benefiting from these improvements, the proposed method is superior to the typical and state-of-the-art methods either in detection probability or false alarm rate.

Anomaly Detection in Hyperspectral Imagery Based on Low-Rank Representation Incorporating a Spatial Constraint

Hyperspectral imagery contains abundant spectral information. Each band contains some specific characteristics closely related to target objects. Therefore, using these characteristics, hyperspectral imagery can be used for anomaly detection. Recently, with the development of compressed sensing, low-rank-representation-based methods have been applied to hyperspectral anomaly detection. In this study, novel low-rank representation methods were developed for anomaly detection from hyperspectral images based on the assumption that hyperspectral pixels can be effectively decomposed into a low-rank component (for background) and a sparse component (for anomalies). In order to improve detection performance, we imposed a spatial constraint on the low-rank representation coefficients, and single or multiple local window strategies was applied to smooth the coefficients. Experiments on both simulated and real hyperspectral datasets demonstrated that the proposed approaches can effectively improve hyperspectral anomaly detection performance.

Sparse-SpatialCEM for Hyperspectral Target Detection

The constrained energy minimization (CEM) algorithm is widely used for target detection in hyperspectral imagery. This method, as well as most target detection algorithms, focuses on the use of spectral information and neglects the spatial information embedded in images. In real hyperspectral images, it is usual that targets of interest only occupy a minor portion of the pixels, and an object may consist of multiple consecutive pixels in space. Considering these facts, we propose a novel constrained detection algorithm, referred to as Sparse-SpatialCEM, to simultaneously force the sparsity and spatial correlation of the detection output via proper regularizations. Several algorithms, including the CEM, SparseCEM, and constrained magnitude minimization algorithms, are limiting cases of the proposed framework. The formulated problems are solved by using the alternating direction method of multipliers. We validate the proposed algorithms and illustrate its advantages via both synthetic and real hyperspectral data.

A Constrained Sparse-Representation-Based Binary Hypothesis Model for Target Detection in Hyperspectral Imagery

In this paper, we propose a novel constrained sparse-representation-based binary hypothesis model for target detection in hyperspectral imagery. This model is based on the concept that a target pixel can only be linearly represented by the union dictionary combined by the background dictionary and target dictionary, while a background pixel can be linearly represented by both the background dictionary and the union dictionary. To be physically meaningful, the non-negativity constraint is imposed to the weight vector. To suppress the target signals in the background dictionary, the upper bound constraint is also imposed to the weight vector. These upper bounds are adaptively estimated by the similarities between the atoms in the background dictionary and target. Then, the weight vectors under different hypotheses are recovered by a fast coordinate descent method. Finally, both the residual difference and weight difference between the two hypotheses are used to perform the target detection. An important advantage of the proposed method is the robustness to varying target contamination. Extensive experiments conducted on real and synthetic hyperspectral datasets have demonstrated the superiority of the proposed detector in detection performance and computational cost. Specifically, for the Avon dataset, our method achieves the highest area under the receiver operating characteristic (ROC) curve of 99.91%, and achieves the shortest runtime of 109.76 s.

A Constrained Sparse Representation Model for Hyperspectral Anomaly Detection

In this paper, we propose a novel sparsity-based algorithm for anomaly detection in hyperspectral imagery. The algorithm is based on the concept that a background pixel can be approximately represented as a sparse linear combination of its spatial neighbors while an anomaly pixel cannot if the anomalies are removed from its neighborhood. To be physically meaningful, the sum-to-one and nonnegativity constraints are imposed to abundance vector based on the linear mixture model, and the upper bound constraint on sparsity level is removed for better recovery of the test pixel. First, the proposed method utilizes the redundant background information to automatically remove anomalies from the background dictionary. Then, the reconstruction error obtained by the new background dictionary is directly used for anomaly detection. Moreover, a kernel version of the proposed method is also derived to completely exploit the nonlinear feature of hyperspectral data. An important advantage of the proposed methods is their capability to adaptively model the background even when some anomaly pixels are involved. Extensive experiments have been conducted on three real hyperspectral data sets. It is demonstrated that the proposed detectors achieve a promising detection performance with a relatively low computational cost.

基于双边滤波的最优波段子空间高光谱异常目标检测

基于双边滤波的最优波段子空间高光谱异常目标检测