|
|
|
|
|
|
Hyperspectral Image Anomaly Detection Based on Laplasse Constrained Low Rank Representation |
WANG Jie-chao1, 2, 3, SUN Da-peng1, 2, 3, ZHANG Chang-xing1, XIE Feng1, WANG Jian-yu1* |
1. Shanghai Institute of Technical Physics of the Chinese Academy of Sciences, Key Laboratory of Space Active Opto-Electronics Technology of the Chinese Academy of Sciences, Shanghai 200083, China
2. University of Chinese Academy of Sciences,Beijing 100049, China
3. ShanghaiTech University, Shanghai 200120, China |
|
|
Abstract 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.
|
Received: 2017-11-03
Accepted: 2018-03-20
|
|
Corresponding Authors:
WANG Jian-yu
E-mail: wangjy@shb.ac.cn
|
|
[1] TONG Qing-xi, ZHANG Bing, ZHANG Li-fu(童庆禧,张 兵,张立福). Journal of Remote Sensing(遥感学报), 2016, 20(5): 689.
[2] GAO Kun, LIU Ying, WANG Li-jing, et al(高 昆,刘 莹,王丽静,等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2015, 35(10): 2846.
[3] Chang C I. Wiley-Interscience, 2013, 81(6): 441.
[4] Manolakis D, Truslow E, Pieper M, et al. IEEE Signal Processing Magazine, 2014, 31(1): 24.
[5] Matteoli S, Diani M, Corsini G. Optical Engineering, 2010, 49(4): 258.
[6] Li W, Du Q. IEEE Transactions on Geoscience and Remote Sensing, 2015, 53(3): 1463.
[7] Sun W, Liu C, Li J, et al. Journal of Applied Remote Sensing, 2014, 8(1): 083641.
[8] Xu Y, Wu Z, Li J, et al. IEEE Transactions on Geoscience and Remote Sensing, 2016, 54(4): 1990.
[9] Liu G, Yan S. Latent Low-Rank Representation for Subspace Segmentation and Feature Extraction, 2011 IEEE International Conference on Computer Vision, 2011: 1615.
[10] Wright J, Ma Y, Mairal J, et al. Proceedings of the IEEE, 2010, 98(6): 1031.
[11] Wen Z, Goldfarb D, Yin W. Mathematical Programming Computation, 2010, 2(3): 203.
[12] Lin Z, Liu R, Su Z. Linearized Alternating Direction Method with Adaptive Penalty for Low-Rank Representation, Advances in Neural Information Processing Systems,2011: 612. |
[1] |
WANG Cai-ling1,ZHANG Jing1,WANG Hong-wei2*, SONG Xiao-nan1, JI Tong3. A Hyperspectral Image Classification Model Based on Band Clustering and Multi-Scale Structure Feature Fusion[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(01): 258-265. |
[2] |
GAO Hong-sheng1, GUO Zhi-qiang1*, ZENG Yun-liu2, DING Gang2, WANG Xiao-yao2, LI Li3. Early Classification and Detection of Kiwifruit Soft Rot Based on
Hyperspectral Image Band Fusion[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(01): 241-249. |
[3] |
ZHANG Fu1, 2, WANG Xin-yue1, CUI Xia-hua1, YU Huang1, CAO Wei-hua1, ZHANG Ya-kun1, XIONG Ying3, FU San-ling4*. Identification of Maize Varieties by Hyperspectral Combined With Extreme Learning Machine[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(09): 2928-2934. |
[4] |
TANG Ting, PAN Xin*, LUO Xiao-ling, GAO Xiao-jing. Fusion of ConvLSTM and Multi-Attention Mechanism Network for
Hyperspectral Image Classification[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(08): 2608-2616. |
[5] |
LIANG Wan-jie1, FENG Hui2, JIANG Dong3, ZHANG Wen-yu1, 4, CAO Jing1, CAO Hong-xin1*. Early Recognition of Sclerotinia Stem Rot on Oilseed Rape by Hyperspectral Imaging Combined With Deep Learning[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(07): 2220-2225. |
[6] |
WANG Guang-lai, WANG En-feng, WANG Cong-cong, LIU Da-yang*. Early Bruise Detection of Crystal Pear Based on Hyperspectral Imaging Technology and Transfer Learning[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(11): 3626-3630. |
[7] |
XIANG Song-yang1, 3, XU Zhang-hua1, 2, 4, 5, 6*, ZHANG Yi-wei1, 2, ZHANG Qi1, 3, ZHOU Xin1, 2, YU Hui1, 3, LI Bin1, 2, LI Yi-fan1, 2. Construction and Application of ReliefF-RFE Feature Selection Algorithm for Hyperspectral Image Classification[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(10): 3283-3290. |
[8] |
DAI Ruo-chen1, TANG Huan2*, TANG Bin1*, ZHAO Ming-fu1, DAI Li-yong1, ZHAO Ya3, LONG Zou-rong1, ZHONG Nian-bing1. Study on Detection Method of Foxing on Paper Artifacts Based on
Hyperspectral Imaging Technology[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(05): 1567-1571. |
[9] |
WANG Sheng-ming1, WANG Tao1*, TANG Sheng-jin2, SU Yan-zhao1. Hyperspectral Anomaly Detection Based on 3D Convolutional
Autoencoder Network[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(04): 1270-1277. |
[10] |
ZHOU Bing, LI Bing-xuan*, HE Xuan, LIU He-xiong,WANG Fa-zhen. Classification of Camouflages Using Hyperspectral Images Combined With Fusing Adaptive Sparse Representation and Correlation Coefficient[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41(12): 3851-3856. |
[11] |
ZHANG Liu1, YE Nan1, MA Ling-ling2, WANG Qi2, LÜ Xue-ying1, ZHANG Jia-bao1*. Hyperspectral Band Selection Based on Improved Particle Swarm Optimization Algorithm[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41(10): 3194-3199. |
[12] |
YANG Bao-hua1, GAO Yuan1, WANG Meng-xuan1, QI Lin1, NING Jing-ming2. Estimation Model of Polyphenols Content in Yellow Tea Based on Spectral-Spatial Features[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41(03): 936-942. |
[13] |
ZHAO Peng1,2*, HAN Jin-cheng1, WANG Cheng-kun1. Wood Species Classification With Microscopic Hyper-Spectral Imaging Based on I-BGLAM Texture and Spectral Fusion[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41(02): 599-605. |
[14] |
ZHAO Fan, YAN Zhao-ru, XUE Jian-xin, XU Bing. Identification of Wild Black and Cultivated Goji Berries by Hyperspectral Image[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41(01): 201-205. |
[15] |
NING Hong-zhang1, 2, TAN Xin1*, LI Yu-hang1, 2, JIAO Qing-bin1, LI Wen-hao1. Joint Space-Spectrum SG Filtering Algorithms for Hyperspectral Images and Its Application[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2020, 40(12): 3699-3704. |
|
|
|
|