Dual Collaborative Constraints Regularized Low-Rank and Sparse Representation via Robust Dictionaries Construction for Hyperspectral Anomaly Detection

Abstract

Low rank and sparse representation (LRSR) technique has attracted increasing attention for hyperspectral anomaly detection (HAD). Although a large quantity of researches based on LRSR for HAD is proposed, the detection performance is still limited, due to the unsatisfactory dictionary construction and insufficient consideration of global and local characteristics. To tackle above concern, a novel HAD method, termed as dual collaborative constraints regularized low rank and sparse representation via robust dictionaries construction (DCC-LRSR-RDC), is proposed in this paper. Concretely, a robust dictionary construction strategy, which thoroughly excavates the potential of density estimation model and local outlier factor, is proposed to yield pure and representative dictionary atoms. To fully exploit the global and local characteristics of HSI, dual collaborative constraints corresponding to the background and anomaly components are imposed on the LRSR model. Notably, two weighted matrices are further exerted on the representation coefficients to improve the effect of collaborative constraints, considering the fact that the surrounding pixels similar to the testing pixel should be given large weight, otherwise the weight is expected to be small. In this way, the background and anomaly components can be well modeled. Additionally, a nonlinear transformation operation, which combines the output of the density estimation model and local outlier factor with the detection result derived from the LRSR model, is developed to suppress the background. The experiments conducted on one simulated dataset and three real datasets demonstrate the superiority of the proposed method compared with the four typical methods and four state-of-the-art methods.

SAM-Induced Pseudo Fully Supervised Learning for Weakly Supervised Object Detection in Remote Sensing Images

“…Compared with fully supervised object detection (FSOD) [1][2][3][4][5][6][7][8], the major advantage of weakly supervised object detection (WSOD) is that only image-level category annotations are necessary for training the WSOD model. Considering the low cost of data labeling, WSOD has been widely researched in recent years [9][10][11][12][13][14][15][16][17] and has been applied in scene classification [18,19], disaster detection [20,21], military [22,23], and other applications [24][25][26][27][28][29].…”

Hyperspectral Anomaly Detection via Sparse Representation and Collaborative Representation

“…To this end, Su et al [44] proposed a low rank and collaborative representation detector to further promote the effect of the background dictionary construction. Additionally, some regularization terms are imposed into the LRR model, such as graph and total variation regularized low-rank representation (GTVLRR) [45], local spatial constraint and total variation (LSC-TV) [46], and dual collaborative constraints regularized low rank and sparse representation (DCC-LRSR) [47] and so on.…”

Automatic Modulation Classification Based on CNN-Transformer Graph Neural Network

“…Machine learning-based approaches extract meaningful attributes from raw data to describe and represent the data. These methods have shown remarkable performance in computer vision [ 16 ], natural language processing [ 17 ], recommendation systems [ 18 ], object detection [ 19 ], anomaly detection [ 20 , 21 , 22 ], and other domains. In recent years, the field of deep learning has witnessed remarkable progress, giving rise to a diverse range of network models, such as convolutional neural network (CNN) [ 23 ], recurrent neural network (RNN) [ 24 ], graph neural network (GNN) [ 25 ], and transformer network [ 26 ] models.…”