Hyperspectral Anomaly Detection via Convolutional Neural Network and Low Rank With Density-Based Clustering

被引:78
作者
Song, Shangzhen [1 ]
Zhou, Huixin [1 ]
Yang, Yixin [1 ]
Song, Jiangluqi [1 ]
机构
[1] Xidian Univ, Sch Phys & Optoelect Engn, Xian 710071, Shaanxi, Peoples R China
基金
中国国家自然科学基金;
关键词
Anomaly detection (AD); density-based spatial clustering of applications with noise (DBSCAN); hyperspectral image (HSI); low-rank representation (LRR); neural network; IMAGE CLASSIFICATION; DIMENSIONALITY REDUCTION; RX-ALGORITHM;
D O I
10.1109/JSTARS.2019.2926130
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Over the last two decades, anomaly detection (AD) has been known to play a critical role in hyperspectral image analysis, which provides a new way to distinguish the targets from the background without prior knowledge. Recently, the representation-based methods were proposed and soon became a significant type of methods on hyperspectral AD. In this paper, a novel AD algorithm based on convolutional neural network (CNN) and low-rank representation (LRR) is proposed. First, a CNN model is built and trained on hyperspectral image (HSI) datasets to accurately obtain the resulting abundance maps. Compared with the raw dataset, abundance maps contain more distinctive features to identify anomalies from the background. Second, a dictionary is constructed by the density-based spatial clustering of applications with noise (DBSCAN) algorithm to stably represent the background component. Third, a matrix decomposition method based on LRR is adopted. In this way, a coefficient matrix corresponding to the constructed dictionary is obtained, which is low rank. At the same time, a residual matrix can be obtained as well, which is sparse. Finally, anomalies can be extracted from the residual matrix. The experimental results show that the proposed method achieves a superior performance compared to some of the state-of-the-art methods in the field of hyperspectral AD.
引用
收藏
页码:3637 / 3649
页数:13
相关论文
共 45 条
[1]   A support vector method for anomaly detection in hyperspectral imagery [J].
Banerjee, Amit ;
Burlina, Philippe ;
Diehl, Chris .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2006, 44 (08) :2282-2291
[2]   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
[3]   Hyperspectral Unmixing Overview: Geometrical, Statistical, and Sparse Regression-Based Approaches [J].
Bioucas-Dias, Jose M. ;
Plaza, Antonio ;
Dobigeon, Nicolas ;
Parente, Mario ;
Du, Qian ;
Gader, Paul ;
Chanussot, Jocelyn .
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2012, 5 (02) :354-379
[4]   Robust Principal Component Analysis? [J].
Candes, Emmanuel J. ;
Li, Xiaodong ;
Ma, Yi ;
Wright, John .
JOURNAL OF THE ACM, 2011, 58 (03)
[5]   A cluster-based approach for detecting man-made objects and changes in imagery [J].
Carlotto, MJ .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2005, 43 (02) :374-387
[6]   Hyperspectral Image Classification via Kernel Sparse Representation [J].
Chen, Yi ;
Nasrabadi, Nasser M. ;
Tran, Trac D. .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2013, 51 (01) :217-231
[7]  
Chen Y, 2011, IEEE IMAGE PROC, P1233, DOI 10.1109/ICIP.2011.6115655
[8]   Sparse Representation for Target Detection in Hyperspectral Imagery [J].
Chen, Yi ;
Nasrabadi, Nasser M. ;
Tran, Trac D. .
IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING, 2011, 5 (03) :629-640
[9]   Simultaneous Joint Sparsity Model for Target Detection in Hyperspectral Imagery [J].
Chen, Yi ;
Nasrabadi, Nasser M. ;
Tran, Trac D. .
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2011, 8 (04) :676-680
[10]  
Ester M., 1996, KDD-96 Proceedings. Second International Conference on Knowledge Discovery and Data Mining, P226