Toward Efficient Hyperspectral Anomaly Detection With Subspace Transformation Learning

被引:0
作者
Li, Qian [1 ]
Wang, Changbo [2 ]
Yu, Laihang [1 ]
Zhang, Jian [3 ]
Zhang, Li [3 ]
Liu, Kai [4 ]
Shen, Xiangfei [5 ]
机构
[1] Zhoukou Normal Univ, Sch Comp Sci andTechnol, Zhoukou 466001, Henan, Peoples R China
[2] Zhengzhou Coll Finance & Econ, Online Teaching Ctr, Zhengzhou 450000, Henan, Peoples R China
[3] Lvliang Univ, Dept Comp Sci & Technol, Lvliang 033001, Shanxi, Peoples R China
[4] Chongqing Finance & Econ Coll, Sch Software, Chongqing 401320, Peoples R China
[5] Chongqing Univ, Sch Microelect & Commun Engn, Chongqing 400044, Peoples R China
关键词
Hyperspectral imaging; Detectors; TV; Tensors; Computational modeling; Anomaly detection; Task analysis; Alternating direction method of multiplier (ADMM); anomaly detection; hyperspectral image; low-rank (LR); sparse; subspace transformation learning; LOW-RANK REPRESENTATION;
D O I
10.1109/LGRS.2024.3404951
中图分类号
P3 [地球物理学]; P59 [地球化学];
学科分类号
0708 ; 070902 ;
摘要
Current research in hyperspectral anomaly detection often incorporates low-rank (LR) or total variation (TV) priors to encode the background matrix. However, applying such regularizers to the detection model increases the computational burden. In this letter, we propose a subspace transformation learning-based anomaly detector (termed STLAD). In STLAD, we employ an orthogonal transformation to represent the background in its subspace, where both the background and the transformation share spatial smoothness prior and approximate sparsity properties based on carefully selected basis vectors. By leveraging this background characterization, the anomaly component can be effectively described using the $\ell _{2,1}$ mixed norm. To solve the STLAD model, we design an alternating direction method of multipliers (ADMM) with guaranteed convergence. Experiments conducted on benchmark hyperspectral datasets demonstrate that STLAD outperforms several state-of-the-art anomaly detection methods. The demo of STLAD will be publicly available at https://github.com/XiangfeiShen/STLAD.
引用
收藏
页数:5
相关论文
共 24 条
[1]   Hyperspectral Remote Sensing Data Analysis and Future Challenges [J].
Bioucas-Dias, Jose M. ;
Plaza, Antonio ;
Camps-Valls, Gustavo ;
Scheunders, Paul ;
Nasrabadi, Nasser M. ;
Chanussot, Jocelyn .
IEEE GEOSCIENCE AND REMOTE SENSING MAGAZINE, 2013, 1 (02) :6-36
[2]   Improved covariance matrices for point target detection in hyperspectral data [J].
Caefer, Charlene E. ;
Silverman, Jerry ;
Orthal, Oded ;
Antonelli, Dani ;
Sharoni, Yaron ;
Rotman, Stanley R. .
OPTICAL ENGINEERING, 2008, 47 (07)
[3]   Robust Principal Component Analysis? [J].
Candes, Emmanuel J. ;
Li, Xiaodong ;
Ma, Yi ;
Wright, John .
JOURNAL OF THE ACM, 2011, 58 (03)
[4]   An Effective Evaluation Tool for Hyperspectral Target Detection: 3D Receiver Operating Characteristic Curve Analysis [J].
Chang, Chein-, I .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2021, 59 (06) :5131-5153
[5]   Graph and Total Variation Regularized Low-Rank Representation for Hyperspectral Anomaly Detection [J].
Cheng, Tongkai ;
Wang, Bin .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2020, 58 (01) :391-406
[6]   Hyperspectral Anomaly Detection With Robust Graph Autoencoders [J].
Fan, Ganghui ;
Ma, Yong ;
Mei, Xiaoguang ;
Fan, Fan ;
Huang, Jun ;
Ma, Jiayi .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2022, 60
[7]   Local Spatial Constraint and Total Variation for Hyperspectral Anomaly Detection [J].
Feng, Ruyi ;
Li, Hao ;
Wang, Lizhe ;
Zhong, Yanfei ;
Zhang, Liangpei ;
Zeng, Tieyong .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2022, 60
[8]   BS3LNet: A New Blind-Spot Self-Supervised Learning Network for Hyperspectral Anomaly Detection [J].
Gao, Lianru ;
Wang, Degang ;
Zhuang, Lina ;
Sun, Xu ;
Huang, Min ;
Plaza, Antonio .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2023, 61
[9]  
Gorelnik H., 2010, P 2 WORKSH HYP IM SI, P1
[10]   Prior-Based Tensor Approximation for Anomaly Detection in Hyperspectral Imagery [J].
Li, Lu ;
Li, Wei ;
Qu, Ying ;
Zhao, Chunhui ;
Tao, Ran ;
Du, Qian .
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2022, 33 (03) :1037-1050