Hyperspectral Anomaly Detection via Discriminative Feature Learning with Multiple-Dictionary Sparse Representation

Dictionary trained attention constrained low rank and sparse autoencoder for hyperspectral anomaly detection

Dictionary representations and deep learning Autoencoder (AE) models have proven effective in hyperspectral anomaly detection. Dictionary representations offer self-explanation but struggle with complex scenarios. Conversely, autoencoders can capture details in complex scenes but lack self-explanation. Complex scenarios often involve extensive spatial information, making its utilization crucial in hyperspectral anomaly detection. To effectively combine the advantages of both methods and address the insufficient use of spatial information, we propose an attention constrained low-rank and sparse autoencoder for hyperspectral anomaly detection. This model includes two encoders: an attention constrained low-rank autoencoder (AClrAE) trained with a background dictionary and incorporating a Global Self-Attention Module (GAM) to focus on global spatial information, resulting in improved background reconstruction; and an attention constrained sparse autoencoder (ACsAE) trained with an anomaly dictionary and incorporating a Local Self-Attention Module (LAM) to focus on local spatial information, resulting in enhanced anomaly reconstruction. Finally, to merge the detection results from both encoders, a nonlinear fusion scheme is employed. Experiments on multiple real and synthetic datasets demonstrate the effectiveness and feasibility of the proposed method.

Multipixel Anomaly Detection With Unknown Patterns for Hyperspectral Imagery

In this article, anomaly detection is considered for hyperspectral imagery in the Gaussian background with an unknown covariance matrix. The anomaly to be detected occupies multiple pixels with an unknown pattern. Two adaptive detectors are proposed based on the generalized likelihood ratio test design procedure and ad hoc modification of it. Surprisingly, it turns out that the two proposed detectors are equivalent. Analytical expressions are derived for the probability of false alarm of the proposed detector, which exhibits a constant false alarm rate against the noise covariance matrix. Numerical examples using simulated data reveal how some system parameters (e.g., the background data size and pixel number) affect the performance of the proposed detector. Experiments are conducted on five real hyperspectral data sets, demonstrating that the proposed detector achieves better detection performance than its counterparts.

Target Height Measurement under Complex Multipath Interferences without Exact Knowledge on the Propagation Environment

This paper investigates the direction-of-arrival (DOA) estimation-based target localization problem using an array radar under complex multipath propagation scenarios. Prevalent methods may suffer from performance degradation due to the deterministic signal model mismatch, especially when the exact knowledge of a propagation environment is unavailable. To cope with this problem, we first establish an improved signal model of multipath propagation for low-angle target localization scenarios, where the dynamic nature of convoluted interferences induced by complex terrain reflections is taken into account. Subsequently, an iterative implementation-based target localization algorithm with the improved propagation model is proposed to eliminate the detrimental effect of coherent interferences on target localization performance. Compared to existing works, the proposed algorithm can maintain satisfactory estimation performance in terms of target location parameters, even in severe multipath interference conditions, where the decorrelation preprocessing and accurate knowledge about the multipath propagation environment are not required. Both simulation and experimental results demonstrate the effectiveness of the proposed propagation model and localization algorithm.

Locality Constrained Low Rank Representation and Automatic Dictionary Learning for Hyperspectral Anomaly Detection

Hyperspectral anomaly detection (HAD) as a special target detection can automatically locate anomaly objects whose spectral information are quite different from their surroundings, without any prior information about background and anomaly. In recent years, HAD methods based on the low rank representation (LRR) model have caught much attention, and achieved good results. However, LRR is a global structure model, which inevitably ignores the local geometrical information of hyperspectral image. Furthermore, most of these methods need to construct dictionaries with clustering algorithm in advance, and they are carried out stage by stage. In this paper, we introduce a locality constrained term inspired by manifold learning topreserve the local geometrical structure during the LRR process, and incorporate the dictionary learning into the optimization process of the LRR. Our proposed method is an one-stage algorithm, which can obtain the low rank representation coefficient matrix, the dictionary matrix, and the residual matrix referring to anomaly simultaneously. One simulated and three real hyperspectral images are used as test datasets. Three metrics, including the ROC curve, AUC value, and box plot, are used to evaluate the detection performance. The visualized results demonstrate convincingly that our method can not only detect anomalies accurately, but also suppress the background information and noises effectively. The three evaluation metrics also prove that our method is superior to other typical methods.

An Efficient and Robust Framework for Hyperspectral Anomaly Detection

Hyperspectral images contain distinguishing spectral information and show great potential in the anomaly detection (AD) task which aims to extract discrepant targets from the background. However, most of the popular hyperspectral AD techniques are time consuming and suffer from poor detection performance due to noise disturbance. To address these issues, we propose an efficient and robust AD method for hyperspectral images. In our framework, principal component analysis (PCA) is adopted for spectral dimensionality reduction and to enhance the anti-noise ability. An improved guided filter with edge weight is constructed to purify the background and highlight the potential anomalies. Moreover, a diagonal matrix operation is designed to quickly accumulate the energy of each pixel and efficiently locate the abnormal targets. Extensive experiments conducted on the real-world hyperspectral datasets qualitatively and quantitatively demonstrate that, compared with the existing state-of-the-art approaches, the proposed method achieves higher detection accuracy with faster detection speed which verifies the superiority and effectiveness of the proposed method.

L₁ Sparsity-Regularized Attention Multiple-Instance Network for Hyperspectral Target Detection

Attention-based deep multiple-instance learning (MIL) has been applied to many machine-learning tasks with imprecise training labels. It is also appealing in hyperspectral target detection, which only requires the label of an area containing some targets, relaxing the effort of labeling the individual pixel in the scene. This article proposes an L1 sparsity-regularized attention multiple-instance neural network (L1-attention MINN) for hyperspectral target detection with imprecise labels that enforces the discrimination of false-positive instances from positively labeled bags. The sparsity constraint applied to the attention estimated for the positive training bags strictly complies with the definition of MIL and maintains better discriminative ability. The proposed algorithm has been evaluated on both simulated and real-field hyperspectral (subpixel) target detection tasks, where advanced performance has been achieved over the state-of-the-art comparisons, showing the effectiveness of the proposed method for target detection from imprecisely labeled hyperspectral data.

Systematic Review of Anomaly Detection in Hyperspectral Remote Sensing Applications

Hyperspectral sensors are passive instruments that record reflected electromagnetic radiation in tens or hundreds of narrow and consecutive spectral bands. In the last two decades, the availability of hyperspectral data has sharply increased, propelling the development of a plethora of hyperspectral classification and target detection algorithms. Anomaly detection methods in hyperspectral images refer to a class of target detection methods that do not require any a-priori knowledge about a hyperspectral scene or target spectrum. They are unsupervised learning techniques that automatically discover rare features on hyperspectral images. This review paper is organized into two parts: part A provides a bibliographic analysis of hyperspectral image processing for anomaly detection in remote sensing applications. Development of the subject field is discussed, and key authors and journals are highlighted. In part B an overview of the topic is presented, starting from the mathematical framework for anomaly detection. The anomaly detection methods were generally categorized as techniques that implement structured or unstructured background models and then organized into appropriate sub-categories. Specific anomaly detection methods are presented with corresponding detection statistics, and their properties are discussed. This paper represents the first review regarding hyperspectral image processing for anomaly detection in remote sensing applications.

Random Collective Representation-Based Detector with Multiple Features for Hyperspectral Images

Collaborative representation-based detector (CRD), as the most representative anomaly detection method, has been widely applied in the field of hyperspectral anomaly detection (HAD). However, the sliding dual window of the original CRD introduces high computational complexity. Moreover, most HAD models only consider a single spectral or spatial feature of the hyperspectral image (HSI), which is unhelpful for improving detection accuracy. To solve these problems, in terms of speed and accuracy, we propose a novel anomaly detection approach, named Random Collective Representation-based Detector with Multiple Feature (RCRDMF). This method includes the following steps. This method first extract the different features include spectral feature, Gabor feature, extended multiattribute profile (EMAP) feature, and extended morphological profile (EMP) feature matrix from the HSI image, which enables us to improve the accuracy of HAD by combining the multiple spectral and spatial features. The ensemble and random collaborative representation detector (ERCRD) method is then applied, which can improve the anomaly detection speed. Finally, an adaptive weight approach is proposed to calculate the weight for each feature. Experimental results on six hyperspectral datasets demonstrate that the proposed approach has the superiority over accuracy and speed.

A Constrained Sparse-Representation-Based Spatio-Temporal Anomaly Detector for Moving Targets in Hyperspectral Imagery Sequences

At present, small dim moving target detection in hyperspectral imagery sequences is mainly based on anomaly detection (AD). However, most conventional detection algorithms only utilize the spatial spectral information and rarely employ the temporal spectral information. Besides, multiple targets in complex motion situations, such as multiple targets at different velocities and dense targets on the same trajectory, are still challenges for moving target detection. To address these problems, we propose a novel constrained sparse representation-based spatio-temporal anomaly detection algorithm that extends AD from the spatial domain to the spatio-temporal domain. Our algorithm includes a spatial detector and a temporal detector, which play different roles in moving target detection. The former can suppress moving background regions, and the latter can suppress non-homogeneous background and stationary objects. Two temporal background purification procedures maintain the effectiveness of the temporal detector for multiple targets in complex motion situations. Moreover, the smoothing and fusion of the spatial and temporal detection maps can adequately suppress background clutter and false alarms on the maps. Experiments conducted on a real dataset and a synthetic dataset show that the proposed algorithm can accurately detect multiple targets with different velocities and dense targets with the same trajectory and outperforms other state-of-the-art algorithms in high-noise scenarios.

Hyperspectral Anomaly Detection with Harmonic Analysis and Low-Rank Decomposition

Hyperspectral anomaly detection methods are often limited by the effects of redundant information and isolated noise. Here, a novel hyperspectral anomaly detection method based on harmonic analysis (HA) and low rank decomposition is proposed. This paper introduces three main innovations: first and foremost, in order to extract low-order harmonic images, a single-pixel-related HA was introduced to reduce dimension and remove redundant information in the original hyperspectral image (HSI). Additionally, adopting the guided filtering (GF) and differential operation, a novel background dictionary construction method was proposed to acquire the initial smoothed images suppressing some isolated noise, while simultaneously constructing a discriminative background dictionary. Last but not least, the original HSI was replaced by the initial smoothed images for a low-rank decomposition via the background dictionary. This operation took advantage of the low-rank attribute of background and the sparse attribute of anomaly. We could finally get the anomaly objectives through the sparse matrix calculated from the low-rank decomposition. The experiments compared the detection performance of the proposed method and seven state-of-the-art methods in a synthetic HSI and two real-world HSIs. Besides qualitative assessment, we also plotted the receiver operating characteristic (ROC) curve of each method and report the respective area under the curve (AUC) for quantitative comparison. Compared with the alternative methods, the experimental results illustrated the superior performance and satisfactory results of the proposed method in terms of visual characteristics, ROC curves and AUC values.

Hyperspectral Anomaly Detection Based on Separability-Aware Sample Cascade

A hyperspectral image usually covers a large scale of ground scene, which contains various materials with different spectral properties. When directly exploring the background information using all the image pixels, complex spectral interactions and inter-/intra-difference of different samples will significantly reduce the accuracy of background evaluation and further affect the detection performance. To address this problem, this paper proposes a novel hyperspectral anomaly detection method based on separability-aware sample cascade model. Through identifying separability of hyperspectral pixels, background samples are sifted out layer-by-layer according to their separable degrees from anomalies, which can ensure the accuracy and distinctiveness of background representation. First, as spatial structure is beneficial for recognizing target, a new spectral–spatial feature extraction technique is used in this work based on the PCA technique and edge-preserving filtering. Second, depending on different separability computed by sparse representation, samples are separated into different sets which can effectively and completely reflect various characteristics of background across all the cascade layers. Meanwhile, some potential abnormal targets are removed at each selection step to avoid their effects on subsequent layers. Finally, comprehensively taking different good properties of all the separability-aware layers into consideration, a simple multilayer anomaly detection strategy is adopted to obtain the final detection map. Extensive experimental results on five real-world hyperspectral images demonstrate our method’s superior performance. Compared with seven representative anomaly detection methods, our method improves the average detection accuracy with great advantages.

A Lightweight Hyperspectral Image Anomaly Detector for Real-Time Mission

In real-time onboard hyperspectral-image(HSI) anomalous targets detection, processing speed and accuracy are equivalently desirable which is hard to satisfy at the same time. To improve detection accuracy, deep learning based HSI anomaly detectors (ADs) are widely studied. However, their large scale network results in a massive computational burden. In this paper, to improve the detection throughput without sacrificing the accuracy, a pruning–quantization–anomaly–detector (P-Q-AD) is proposed by building an underlying constraint formulation to make a trade-off between accuracy and throughput. To solve this formulation, multi-objective optimization with nondominated sorting genetic algorithm II (NSGA-II) is employed to shrink the network. As a result, the redundant neurons are removed. A mixed precision network is implemented with a delicate customized fixed-point data expression to further improve the efficiency. In the experiments, the proposed P-Q-AD is implemented on two real HSI data sets and compared with three types of detectors. The results show that the performance of the proposed approach is no worse than those comparison detectors in terms of the receiver operating characteristic curve (ROC) and area under curve (AUC) value. For the onboard mission, the proposed P-Q-AD reaches over 4 . 5 × speedup with less than 0 . 5 % AUC loss compared with the floating-based detector. The pruning and the quantization approach in this paper can be referenced for designing the anomalous targets detectors for high efficiency.

Label Noise Cleansing with Sparse Graph for Hyperspectral Image Classification

In a real hyperspectral image classification task, label noise inevitably exists in training samples. To deal with label noise, current methods assume that noise obeys the Gaussian distribution, which is not the real case in practice, because in most cases, we are more likely to misclassify training samples at the boundaries between different classes. In this paper, we propose a spectral–spatial sparse graph-based adaptive label propagation (SALP) algorithm to address a more practical case, where the label information is contaminated by random noise and boundary noise. Specifically, the SALP mainly includes two steps: First, a spectral–spatial sparse graph is constructed to depict the contextual correlations between pixels within the same superpixel homogeneous region, which are generated by superpixel image segmentation, and then a transfer matrix is produced to describe the transition probability between pixels. Second, after randomly splitting training pixels into “clean” and “polluted,” we iteratively propagate the label information from “clean” to “polluted” based on the transfer matrix, and the relabeling strategy for each pixel is adaptively adjusted along with its spatial position in the corresponding homogeneous region. Experimental results on two standard hyperspectral image datasets show that the proposed SALP over four major classifiers can significantly decrease the influence of noisy labels, and our method achieves better performance compared with the baselines.

Superpixel based Feature Specific Sparse Representation for Spectral-Spatial Classification of Hyperspectral Images

To improve the performance of the sparse representation classification (SRC), we propose a superpixel-based feature specific sparse representation framework (SPFS-SRC) for spectral-spatial classification of hyperspectral images (HSI) at superpixel level. First, the HSI is divided into different spatial regions, each region is shape- and size-adapted and considered as a superpixel. For each superpixel, it contains a number of pixels with similar spectral characteristic. Since the utilization of multiple features in HSI classification has been proved to be an effective strategy, we have generated both spatial and spectral features for each superpixel. By assuming that all the pixels in a superpixel belongs to one certain class, a kernel SRC is introduced to the classification of HSI. In the SRC framework, we have employed a metric learning strategy to exploit the commonalities of different features. Experimental results on two popular HSI datasets have demonstrated the efficacy of our proposed methodology.

A Multiscale Hierarchical Model for Sparse Hyperspectral Unmixing

Due to the complex background and low spatial resolution of the hyperspectral sensor, observed ground reflectance is often mixed at the pixel level. Hyperspectral unmixing (HU) is a hot-issue in the remote sensing area because it can decompose the observed mixed pixel reflectance. Traditional sparse hyperspectral unmixing often leads to an ill-posed inverse problem, which can be circumvented by spatial regularization approaches. However, their adoption has come at the expense of a massive increase in computational cost. In this paper, a novel multiscale hierarchical model for a method of sparse hyperspectral unmixing is proposed. The paper decomposes HU into two domain problems, one is in an approximation scale representation based on resampling the method’s domain, and the other is in the original domain. The use of multiscale spatial resampling methods for HU leads to an effective strategy that deals with spectral variability and computational cost. Furthermore, the hierarchical strategy with abundant sparsity representation in each layer aims to obtain the global optimal solution. Both simulations and real hyperspectral data experiments show that the proposed method outperforms previous methods in endmember extraction and abundance fraction estimation, and promotes piecewise homogeneity in the estimated abundance without compromising sharp discontinuities among neighboring pixels. Additionally, compared with total variation regularization, the proposed method reduces the computational time effectively.

Fast Spectral Clustering for Unsupervised Hyperspectral Image Classification

Hyperspectral image classification is a challenging and significant domain in the field of remote sensing with numerous applications in agriculture, environmental science, mineralogy, and surveillance. In the past years, a growing number of advanced hyperspectral remote sensing image classification techniques based on manifold learning, sparse representation and deep learning have been proposed and reported a good performance in accuracy and efficiency on state-of-the-art public datasets. However, most existing methods still face challenges in dealing with large-scale hyperspectral image datasets due to their high computational complexity. In this work, we propose an improved spectral clustering method for large-scale hyperspectral image classification without any prior information. The proposed algorithm introduces two efficient approximation techniques based on Nyström extension and anchor-based graph to construct the affinity matrix. We also propose an effective solution to solve the eigenvalue decomposition problem by multiplicative update optimization. Experiments on both the synthetic datasets and the hyperspectral image datasets were conducted to demonstrate the efficiency and effectiveness of the proposed algorithm.

Hyperspectral Anomaly Detection via Dictionary Construction-Based Low-Rank Representation and Adaptive Weighting

Anomaly detection (AD), which aims to distinguish targets with significant spectral differences from the background, has become an important topic in hyperspectral imagery (HSI) processing. In this paper, a novel anomaly detection algorithm via dictionary construction-based low-rank representation (LRR) and adaptive weighting is proposed. This algorithm has three main advantages. First, based on the consistency with AD problem, the LRR is employed to mine the lowest-rank representation of hyperspectral data by imposing a low-rank constraint on the representation coefficients. Sparse component contains most of the anomaly information and can be used for anomaly detection. Second, to better separate the sparse anomalies from the background component, a background dictionary construction strategy based on the usage frequency of the dictionary atoms for HSI reconstruction is proposed. The constructed dictionary excludes possible anomalies and contains all background categories, thus spanning a more reasonable background space. Finally, to further enhance the response difference between the background pixels and anomalies, the response output obtained by LRR is multiplied by an adaptive weighting matrix. Therefore, the anomaly pixels are more easily distinguished from the background. Experiments on synthetic and real-world hyperspectral datasets demonstrate the superiority of our proposed method over other AD detectors.

Structured Background Modeling for Hyperspectral Anomaly Detection

Background modeling has been proven to be a promising method of hyperspectral anomaly detection. However, due to the cluttered imaging scene, modeling the background of an hyperspectral image (HSI) is often challenging. To mitigate this problem, we propose a novel structured background modeling-based hyperspectral anomaly detection method, which clearly improves the detection accuracy through exploiting the block-diagonal structure of the background. Specifically, to conveniently model the multi-mode characteristics of background, we divide the full-band patches in an HSI into different background clusters according to their spatial-spectral features. A spatial-spectral background dictionary is then learned for each cluster with a principal component analysis (PCA) learning scheme. When being represented onto those dictionaries, the background often exhibits a block-diagonal structure, while the anomalous target shows a sparse structure. In light of such an observation, we develop a low-rank representation based anomaly detection framework that can appropriately separate the sparse anomaly from the block-diagonal background. To optimize this framework effectively, we adopt the standard alternating direction method of multipliers (ADMM) algorithm. With extensive experiments on both synthetic and real-world datasets, the proposed method achieves an obvious improvement in detection accuracy, compared with several state-of-the-art hyperspectral anomaly detection methods.