Hyperspectral Image Anomaly Detection Based on Laplasse Constrained Low Rank Representation

被引:0
|
作者
Wang Jie-chao [1 ,2 ,3 ]
Sun Da-peng [1 ,2 ,3 ]
Zhang Chang-zing [1 ]
Xie Feng [1 ]
Wang Jian-yu [1 ]
机构
[1] Chinese Acad Sci, Key Lab Space Act Optoelect Technol, Shanghai Inst Tech Phys, Shanghai 200083, Peoples R China
[2] Univ Chinese Acad Sci, Beijing 100049, Peoples R China
[3] ShanghaiTech Univ, Shanghai 200120, Peoples R China
关键词
Hyperspectral image; Laplasse; Low rank representation; Anomaly detection;
D O I
10.3964/j.issn.1000-0593(2018)11-3507-09
中图分类号
O433 [光谱学];
学科分类号
0703 ; 070302 ;
摘要
With the widespread use of hyperspectral images, hyperspectral image technology has made considerable progress, of which hyperspectral image anomaly detection technology has received more and more attention. In order to solve the problem of poor practicability and poor detection effect of traditional hyperspectral image anomaly detection techniques, this paper presents a novel low rank representation detection algorithm. For hyperspectral images, most of the background pixels can be approximated by a small number of major background pixel combinations, and their representation coefficients will be located in a low-rank space. While the remaining anomalous pixels in the sparse part that can not be represented by the main background pixels can be extracted by the detection algorithm. In low-rank representations, the construction of the background pixel dictionary will affect the representation of the background pixels in the hyperspectral image. When extracting the background pixels directly from the existing hyperspectral image to construct the dictionary, this process will lead to the contamination of the background pixel dictionary by the abnormal pixels. So in this paper, the background pixel dictionary is constructed by using the observed data on the hyperspectral image to be detected and the potential unobserved data that can be synthesized by the principle of spectral composition, and the main features of the background pixels are extracted, helping to better separate the sparse anomalous pixel Information. Hyperspectral image data is characterized by high-dimensional geometry. In this paper, we introduce a Laplacian matrix to constrain the representation of locally similar pixels in the space to be detected, and get a closer representation of the true representation coefficients. The experimental results are validated respectively on the simulation data and the real data, showing that the proposed method reduces the false detection rate by effectively highlighting the abnormal pixels and improves the detection rate by suppressing the background pixels.
引用
收藏
页码:3507 / 3515
页数:9
相关论文
共 9 条
  • [1] [Anonymous], 2011, P ADV NEUR INF PROC
  • [2] Chang CI, 2013, WILEY INTERSCIENCE, V81, P441
  • [3] Collaborative Representation for Hyperspectral Anomaly Detection
    Li, Wei
    Du, Qian
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2015, 53 (03): : 1463 - 1474
  • [4] Detection Algorithms in Hyperspectral Imaging Systems
    Manolakis, Dimitris
    Truslow, Eric
    Pieper, Michael
    Cooley, Thomas
    Brueggeman, Michael
    [J]. IEEE SIGNAL PROCESSING MAGAZINE, 2014, 31 (01) : 24 - 33
  • [5] Low-rank and sparse matrix decomposition-based anomaly detection for hyperspectral imagery
    Sun, Weiwei
    Liu, Chun
    Li, Jialin
    Lai, Yenming Mark
    Li, Weiyue
    [J]. JOURNAL OF APPLIED REMOTE SENSING, 2014, 8
  • [6] [童庆禧 Tong Qingxi], 2016, [遥感学报, Journal of Remote Sensing], V20, P689
  • [7] Alternating direction augmented Lagrangian methods for semidefinite programming
    Wen Z.
    Goldfarb D.
    Yin W.
    [J]. Mathematical Programming Computation, 2010, 2 (3-4) : 203 - 230
  • [8] Sparse Representation for Computer Vision and Pattern Recognition
    Wright, John
    Ma, Yi
    Mairal, Julien
    Sapiro, Guillermo
    Huang, Thomas S.
    Yan, Shuicheng
    [J]. PROCEEDINGS OF THE IEEE, 2010, 98 (06) : 1031 - 1044
  • [9] Anomaly Detection in Hyperspectral Images Based on Low-Rank and Sparse Representation
    Xu, Yang
    Wu, Zebin
    Li, Jun
    Plaza, Antonio
    Wei, Zhihui
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2016, 54 (04): : 1990 - 2000