Hyperspectral anomaly detection based on the weakly supervised robust autoencoder

doi:10.6046/zrzyyg.2022093

Abstract
Figures/Tables
References
Related Articles
Metrics

Download: PDF(4969 KB) HTML
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks

Abstract

Hyperspectral anomaly detection has received particular attention due to its unsupervised detection of targets. Moreover, autoencoder (AE), together with its variants, can automatically extract deep features and detect anomalous targets. However, AE is highly generalizable due to the existence of anomalies in the training set, thus suffering a reduced ability to distinguish anomalies from the background. This study proposed an anomaly detection algorithm based on the weakly supervised robust AE (WSRAE). First, this study developed a salient category search strategy and used probability-based category thresholds to label coarse samples in order to make preparation for network-based weakly supervised learning. Moreover, this study constructed a robust AE framework constrained jointly by l_2,1 norm and anomaly-background spectral distances. This framework was robust with regard to noise and anomalies during training. Finally, this study detected anomalous targets based on the reconstruction errors obtained from all samples. Experiments on four hyperspectral datasets show that the WSRAE algorithm has greater detection performance than other state-of-the-art anomaly detection algorithms.

Keywords hyperspectral image anomaly detection salient category search robust AE

ZTFLH:

TP79

Issue Date: 07 July 2023

	Service

	E-mail this article
	E-mail Alert
	RSS
	Articles by authors

	Guojian ZHANG
	Shengzhen LIU
	Yingjun SUN
	Kaijie YU
	Lina LIU

Cite this article:

Guojian ZHANG,Shengzhen LIU,Yingjun SUN, et al. Hyperspectral anomaly detection based on the weakly supervised robust autoencoder[J]. Remote Sensing for Natural Resources, 2023, 35(2): 167-175.

URL:

https://www.gtzyyg.com/EN/10.6046/zrzyyg.2022093 OR https://www.gtzyyg.com/EN/Y2023/V35/I2/167

Fig.1 WSRAE algorithm structure

Fig.2 Pseudo color images and the corresponding ground truth maps of the 4 HSI datasets

Tab.1 AUC values of ablation studies in four data sets

Tab.2 Comparison of detection results of different anomaly detection algorithms in 4 datasets

Fig.3 Comparison of ROC curves for different anomaly algorithms in 4 data sets

检测算法	Urban		Gulfport		San Diego-1		San Diego-2
检测算法	( $P d, P f$ )	( $P f, τ$ )	( $P d, P f$ )	( $P f, τ$ )	( $P d, P f$ )	( $P f, τ$ )	( $P d, P f$ )	( $P f, τ$ )
GRX	0.984 8	0.0344	0.952 6	0.024 8	0.911 1	0.040 6	0.940 3	0.058 9
CRD	0.982 9	0.0454	0.821 9	0.054 2	0.971 5	0.051 5	0.919 0	0.063 7
LSMAD	0.989 7	0.0190	0.939 5	0.024 6	0.975 6	0.020 1	0.965 3	0.029 1
FrFE	0.968 7	0.0162	0.894 1	0.049 2	0.953 3	0.002 4	0.962 2	0.021 4
SC_AAE	0.934 8	0.0307	0.893 0	0.024 5	0.861 7	0.019 6	0.890 5	0.028 3
MemAE	0.997 4	0.0337	0.961 6	0.037 9	0.969 7	0.047 0	0.971 3	0.048 7
WSRAE	0.997 7	0.0185	0.986 2	0.015 2	0.9846	0.005 4	0.976 3	0.018 5

Tab.3 AUC values of different anomaly algorithms in four data sets

Tab.4 Average calculation time of each anomaly detection algorithm(s)

[1]	童庆禧, 张兵, 张立福. 中国高光谱遥感的前沿进展[J]. 遥感学报, 2016, 20(5):689-707.
[1]	Tong Q X, Zhang B, Zhang L F. Current progress of hyperspectral remote sensing in China[J]. Journal of Remote Sensing, 2016, 20(5):689-707.
[2]	张兵. 高光谱图像处理与信息提取前沿[J]. 遥感学报, 2016, 20(5):1062-1090.
[2]	Zhang B. Advancement of hyperspectral image processing and information extraction[J]. Journal of Remote Sensing, 2016, 20(5):1062-1090.
[3]	成宝芝. 高光谱图像异常目标检测算法研究与进展[J]. 国土资源遥感, 2014, 26(3):1-7.doi:10.6046/gtzyyg.2014.03.01. doi: 10.6046/gtzyyg.2014.03.01
[3]	Cheng B Z. Study and progress of anomaly target detection in hyperspectral imagery[J]. Remote Sensing for Land and Resources, 2014, 26(3):1-7.doi:10.6046/gtzyyg.2014.03.01. doi: 10.6046/gtzyyg.2014.03.01
[4]	侯增福, 刘镕源, 闫柏琨, 等. 基于波段选择与学习字典的高光谱图像异常探测[J]. 国土资源遥感, 2019, 31(1),33-41.doi:10.6046/gtzyyg.2019.01.05. doi: 10.6046/gtzyyg.2019.01.05
[4]	Hou Z F, Liu R Y, Yan B K, et al. Hyperspectral imagery anomaly detection based on band selection and learning dictionary[J]. Remote Sensing for Land and Resources, 2019, 31(1),33-41.doi:10.6046/gtzyyg.2019.01.05. doi: 10.6046/gtzyyg.2019.01.05
[5]	Reed I S, Yu X. Adaptive multiple-band CFAR detection of an optical pattern with unknown spectral distribution[J]. IEEE Transactions on Acoustics,Speech,and Signal Processing, 1990, 38(10):1760-1770. doi: 10.1109/29.60107 url: http://ieeexplore.ieee.org/document/60107/
[6]	Kwon H, Nasrabad N M. Kernel RX-algorithm:A nonlinear anomaly detector for hyperspectral imagery[J]. IEEE Transactions on Geoscience and Remote Sensing, 2005, 43(2):388-397. doi: 10.1109/TGRS.2004.841487 url: http://ieeexplore.ieee.org/document/1386510/
[7]	Guo Q, Zhang B, Ran Q, et al. Weighted-RXD and linear filter-based RXD:Improving background statistics estimation for anomaly detection in hyperspectral imagery[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2014, 7(6):2351-2366. doi: 10.1109/JSTARS.4609443 url: https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=4609443
[8]	Du B, Zhang L. Random-selection-based anomaly detector for hyperspectral imagery[J]. IEEE Transactions on Geoscience and Remote sensing, 2010, 49(5):1578-1589. doi: 10.1109/TGRS.2010.2081677 url: http://ieeexplore.ieee.org/document/5628269/
[9]	Li W, Du Q. Collaborative representation for hyperspectral anomaly detection[J]. IEEE Transactions on Geoscience and Remote Sensing, 2014, 53(3):1463-1474. doi: 10.1109/TGRS.2014.2343955 url: http://ieeexplore.ieee.org/document/6876207/
[10]	刘万军, 武小杰, 曲海成, 等. 改进协同表示的高光谱图像异常检测算法[J]. 计算机应用研究, 2018 (12):68.
[10]	Liu W J, Wu X J, Qu H C, et al. Improved collaborative representation for hyperspectral imagery anomaly detection algorithm[J]. Application Research of Computers, 2018 (12):68.
[11]	Zhang Y, Du B, Zhang L, et al. A low-rank and sparse matrix decomposition-based Mahalanobis distance method for hyperspectral anomaly detection[J]. IEEE Transactions on Geoscience and Remote Sensing, 2015, 54(3):1376-1389. doi: 10.1109/TGRS.2015.2479299 url: http://ieeexplore.ieee.org/document/7293169/
[12]	Tao R, Zhao X, Li W, et al. Hyperspectral anomaly detection by fractional Fourier entropy[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2019, 12(12):4920-4929. doi: 10.1109/JSTARS.2019.2940278
[13]	Xie W, Liu B, Li Y, et al. Autoencoder and adversarial-learning-based semisupervised background estimation for hyperspectral anomaly detection[J]. IEEE Transactions on Geoscience and Remote Sensing, 2020, 58(8):5416-5427. doi: 10.1109/TGRS.36 url: https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=36
[14]	薛白, 王懿哲, 刘书含, 等. 基于孪生注意力网络的高分辨率遥感影像变化检测[J]. 自然资源遥感, 2022, 34(1):61-66.doi:10.6046/zrzyyg.2021122. doi: 10.6046/zrzyyg.2021122
[14]	Xue B, Wang Y Z, Liu S H, et al. Change detection of high-resolution remote sensing images based on Siamese network[J]. Remote Sensing for Land and Resources, 2022, 34(1):61-66.doi:10.6046/zrzyyg.2021122. doi: 10.6046/zrzyyg.2021122
[15]	韩彦岭, 崔鹏霞, 杨树瑚, 等. 基于残差网络特征融合的高光谱图像分类[J]. 国土资源遥感, 2021, 33(2):11-19.doi:10.6046/gtzyyg.2020209. doi: 10.6046/gtzyyg.2020209
[15]	Han Y L, Cui P X, Yang S H, et al. Classification of hyperspectral images based on feature fusion of residual network[J]. Remote Sensing for Land and Resources, 2021, 33(2):11-19.doi:10.6046/gtzyyg.2020209. doi: 10.6046/gtzyyg.2020209
[16]	Xie W, Lei J, Liu B, et al. Spectral constraint adversarial autoencoders approach to feature representation in hyperspectral anomaly detection[J]. Neural Networks, 2019, 119:222-234. doi: S0893-6080(19)30229-1 pmid: 31472289
[17]	Lu X, Zhang W, Huang J. Exploiting embedding manifold of autoencoders for hyperspectral anomaly detection[J]. IEEE Transactions on Geoscience and Remote Sensing, 2019, 58(3):1527-1537. doi: 10.1109/TGRS.36 url: https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=36
[18]	Zhao C, Zhang L. Spectral-spatial stacked autoencoders based on low-rank and sparse matrix decomposition for hyperspectral anomaly detection[J]. Infrared Physics & Technology, 2018, 92:166-176.
[19]	Parimala M, Lopez D, Senthilkumar N C. A survey on density based clustering algorithms for mining large spatial databases[J]. International Journal of Advanced Science and Technology, 2011, 31(1):59-66.
[20]	Ma Y, Li C, Mei X, et al. Robust sparse hyperspectral unmixing with l_2,1 norm[J]. IEEE Transactions on Geoscience and Remote Sensing, 2016, 55(3):1227-1239. doi: 10.1109/TGRS.2016.2616161 url: http://ieeexplore.ieee.org/document/7784763/
[21]	Gong D, Liu L, Le V, et al. Memorizing normality to detect anomaly:Memory-augmented deep autoencoder for unsupervised anomaly detection[C]// Proceedings of the IEEE/CVF International Conference on Computer Vision. 2019:1705-1714.

[1]	ZHENG Zongsheng, LIU Haixia, WANG Zhenhua, LU Peng, SHEN Xukun, TANG Pengfei. Improved 3D-CNN-based method for surface feature classification using hyperspectral images[J]. Remote Sensing for Natural Resources, 2023, 35(2): 105-111.
[2]	WANG Ping. Application of thermal infrared remote sensing in monitoring the steel overcapacity cutting[J]. Remote Sensing for Natural Resources, 2023, 35(2): 271-276.
[3]	ZHANG Pengqiang, GAO Kuiliang, LIU Bing, TAN Xiong. Classification of hyperspectral images based on deep Transformer network combined with spatial-spectral information[J]. Remote Sensing for Natural Resources, 2022, 34(3): 27-32.
[4]	SUN Xiao, XU Linlin, WANG Xiaoyang, TIAN Ye, WANG Wei, ZHANG Zhongyue. Mineral identification from hyperspectral images based on the optimized K-P-Means unmixing method[J]. Remote Sensing for Natural Resources, 2022, 34(3): 43-49.
[5]	QU Haicheng, WAND Yaxuan, SHEN Lei. Hyperspectral super-resolution combining multi-receptive field features with spectral-spatial attention[J]. Remote Sensing for Natural Resources, 2022, 34(1): 43-52.
[6]	GAO Wenlong, ZHANG Shengwei, LIN Xi, LUO Meng, REN Zhaoyi. The remote sensing-based estimation and spatial-temporal dynamic analysis of SOM in coal mining[J]. Remote Sensing for Natural Resources, 2021, 33(4): 235-242.
[7]	WANG Hua, LI Weiwei, LI Zhigang, CHEN Xueye, SUN Le. Hyperspectral image classification based on multiscale superpixels[J]. Remote Sensing for Natural Resources, 2021, 33(3): 63-71.
[8]	LIU Yongmei, FAN Hongjian, GE Xinghua, LIU Jianhong, WANG Lei. Estimation accuracy of fractional vegetation cover based on normalized difference vegetation index and UAV hyperspectral images[J]. Remote Sensing for Natural Resources, 2021, 33(3): 11-17.
[9]	HAN Yanling, CUI Pengxia, YANG Shuhu, LIU Yekun, WANG Jing, ZHANG Yun. Classification of hyperspectral image based on feature fusion of residual network[J]. Remote Sensing for Land & Resources, 2021, 33(2): 11-19.
[10]	SUN Ke. Remote sensing image classification based on super pixel and peak density[J]. Remote Sensing for Land & Resources, 2020, 32(4): 41-45.
[11]	Benzuo YAO, Fang HE. Spatial and spectral feature hierarchical fusion for hyperspectral image feature extraction[J]. Remote Sensing for Land & Resources, 2019, 31(3): 59-64.
[12]	Xiaolu LIAO, Jia LIU, Xingxia ZHOU. Feature extraction and classification of hyperspectral image with ground-sky synchronization test[J]. Remote Sensing for Land & Resources, 2019, 31(3): 65-71.
[13]	Ruhan A, Fang HE, Biaobiao WANG. Hyperspectral images classification via weighted spatial-spectral dimensionality reduction principle component analysis[J]. Remote Sensing for Land & Resources, 2019, 31(2): 17-23.
[14]	Haicheng QU, Yue GUO, Yuanyuan WANG. Hyperspectral image classification based on dominant sets clustering and Markov random fields[J]. Remote Sensing for Land & Resources, 2019, 31(2): 24-31.
[15]	Bing TU, Xiaofei ZHANG, Guoyun ZHANG, Jinping WANG, Yao ZHOU. Hyperspectral image classification via recursive filtering and KNN[J]. Remote Sensing for Land & Resources, 2019, 31(1): 22-32.

Viewed

Full text

Abstract

Cited

Shared

Discussed