Regularized Multiple Sparse Bayesian Learning for Hyperspectral Target Detection

被引:6
作者
Kong, Fanqiang [1 ]
Wen, Keyao [1 ]
Li, Yunsong [2 ]
机构
[1] Nanjing Univ Aeronaut & Astronaut, Coll Astronaut, Nanjing 210016, Peoples R China
[2] Xidian Univ, State Key Lab Integrated Serv Networks, Xian 710071, Peoples R China
基金
中国国家自然科学基金;
关键词
Hyperspectral imagery; Target detection; Sparse representation; Multiple sparse Bayesian learning; COLLABORATIVE REPRESENTATION; ANOMALY DETECTION; ALGORITHMS; RECONSTRUCTION; RECOVERY;
D O I
10.1007/s41651-019-0034-1
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
The sparse representation method has been successfully applied in the field of hyperspectral image target detection. It assumes that target detection can be achieved by using target and background libraries to represent test pixels. Under this formulation, the presentation of the target and background signatures can be solved by L-1-norm minimization of the weight coefficient and the target detection output is simply achieved by the difference between the two representation residuals. In this paper, a regularized multiple sparse Bayesian learning (RMSBL) method for hyperspectral target detection is proposed, which is established by Bayesian inference using the conditional posterior distributions of the model parameters under a hierarchical Bayesian model. According to the cost function for multiple sparse Bayesian learning, the presentation of the target and background signatures can be obtained by an L-2,L-1-norm iterative minimization method. And the target detection result can be achieved with the difference between the two representation residuals. Four groups of hyperspectral datasets are used for simulation experiments. The results are compared with those of other common detection algorithms. The experimental results demonstrate that the RMSBL algorithm has higher detection performance.
引用
收藏
页数:10
相关论文
共 28 条
  • [1] A VARIABLE SPLITTING AUGMENTED LAGRANGIAN APPROACH TO LINEAR SPECTRAL UNMIXING
    Bioucas-Dias, Jose M.
    [J]. 2009 FIRST WORKSHOP ON HYPERSPECTRAL IMAGE AND SIGNAL PROCESSING: EVOLUTION IN REMOTE SENSING, 2009, : 1 - 4
  • [2] Hyperspectral Image Classification Using Dictionary-Based Sparse Representation
    Chen, Yi
    Nasrabadi, Nasser M.
    Tran, Trac D.
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2011, 49 (10): : 3973 - 3985
  • [3] Sparse Representation for Target Detection in Hyperspectral Imagery
    Chen, Yi
    Nasrabadi, Nasser M.
    Tran, Trac D.
    [J]. IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING, 2011, 5 (03) : 629 - 640
  • [4] Kong Fanqiang, 2017, Transactions of Nanjing University of Aeronautics & Astronautics, V34, P456, DOI 10.16356/j.1005-1120.2017.04.456
  • [5] Regularized MSBL algorithm with spatial correlation for sparse hyperspectral unmixing
    Kong, Fanqiang
    Li, Yunsong
    Guo, Wenjun
    [J]. JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2016, 40 : 525 - 537
  • [6] DETECTING HYPERSPECTRAL ANOMALY BY USING BACKGROUND RESIDUAL ERROR DATA
    Li Jie
    Zhao Chun-Hui
    Mei Feng
    [J]. JOURNAL OF INFRARED AND MILLIMETER WAVES, 2010, 29 (02) : 150 - 155
  • [7] Combined sparse and collaborative representation for hyperspectral target detection
    Li, Wei
    Du, Qian
    Zhang, Bing
    [J]. PATTERN RECOGNITION, 2015, 48 (12) : 3904 - 3916
  • [8] Collaborative Representation for Hyperspectral Anomaly Detection
    Li, Wei
    Du, Qian
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2015, 53 (03): : 1463 - 1474
  • [9] Hyperspectral image reconstruction by deep convolutional neural network for classification
    Li, Yunsong
    Xie, Weiying
    Li, Huaqing
    [J]. PATTERN RECOGNITION, 2017, 63 : 371 - 383
  • [10] Detection algorithms for hyperspectral Imaging applications
    Manolakis, D
    Shaw, G
    [J]. IEEE SIGNAL PROCESSING MAGAZINE, 2002, 19 (01) : 29 - 43