An Improved Low Rank and Sparse Matrix Decomposition-Based Anomaly Target Detection Algorithm for Hyperspectral Imagery

Abstract

Anomaly target detection has been a hotspot of the hyperspectral imagery (HSI) processing in recent decades. One of the key research points in the HSI anomaly detection is the accurate descriptions of the background and anomaly targets. Considering this point, we propose a novel anomaly target detector in this article. Improving upon the low-rank and sparse matrix decomposition (LRaSMD) approach, the proposed method assumes that the lowrank component can be described as the parts-based representation. Parts refer to the various ground objects in HSI. A new update rule of the low-rank component and sparse component is proposed. The proposed approach can be divided into three main steps: first, further refining the low-rank component in the LRaSMD model as the parts-based representation. Then, the HSI is decomposed as three parts: the product of the basis matrix and coefficient matrix, sparse matrix, and noise. Second, the basis vectors matrix, coefficient matrix, and sparse matrix are solved by the new update rules. Third, since the anomaly targets exist in the sparse matrix, the sparse matrix is thus employed to detect the anomaly targets. The experiments implemented for five data sets demonstrate that the proposed algorithm achieved a better performance than the traditional algorithms.

An Unmixing-Based Network for Underwater Target Detection From Hyperspectral Imagery

“…According to related research works [25], [26], targets pixels usually occupy a tiny percent of the total HSI in hyperspectral target detection task. Following this viewpoint, target-water mixed pixels in the underwater HSI own the sparse characteristic as well.…”

A Fast Hyperspectral Anomaly Detection Algorithm Based on Greedy Bilateral Smoothing and Extended Multi-Attribute Profile

“…An HSI includes hundreds of nearly continuous spectral bands [1][2][3]. Compared to traditional optical and multispectral images, HSIs convey more features, significantly improving the ability to detect subtle differences in the characteristics of different materials [4]. Therefore, it offers unique advantages for classification and target detection [5][6][7][8][9].…”

“…Therefore, the LRaSMD method decomposes the original HSI into low-rank, sparse, and noise matrices. Some LRaSMD methods show relatively good performance in hyperspectral anomaly detection, including Euclidean distance-based LRaSMD (EDL-RaSMD) [34], two-norm-based LRaSMD [35], the LRaSMD-based Mahalanobis distance method for hyperspectral anomaly detection (LSMAD) [36] and the parts representationbased LRaSMD (PRLRaSAD) [4].…”

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

“…These techniques make use of the conspicuous characteristics of anomalies: the low probability of occurrence and the different spectral signature from the background pixels [27]. There are several forms of representation-based methods, including the sparse representation-based methods [1,[31][32][33][34][35][36][37], the low-rank methods [38][39][40][41][42][43], and the collaborative methods [44][45][46][47][48].…”

“…Owing to the sparse properties of the anomaly target, it is grounded in a holistic-based representation, while the background is grounded in partsbased representation. Based on these descriptions of HSI, the PRLRaSAD method divides the HSI decomposition optimization problem into three subproblems, so that the basis vector matrix, coefficient matrix, and sparse matrix, respectively, can be computed [42].…”