Hyperspectral deep convolution anomaly detection based on weight adjustment strategy

doi:10.1364/AO.400563

	Hyperspectral deep convolution anomaly detection based on weight adjustment strategy
	Chong, Dan 1,2; Hu, Bingliang 1; Gao, Xiaohui 1; Gao, Hao 3; Xia, Pu 1; Wu, Yinhua 4
刊名	APPLIED OPTICS
	2020-11-01
卷号	59 期号:31 页码:9633-9642
ISSN号	1559-128X
DOI	10.1364/AO.400563
英文摘要	Hyperspectral anomaly detection has garnered much research in recent years due to the excellent detection ability of hyperspectral remote sensing in agriculture, forestry, geological surveys, environmental monitoring, and battlefield target detection. The traditional anomaly detection method ignores the non-linearity and complexity of the hyperspectral image (HSI), while making use of the effectiveness of spatial information rarely. Besides, the anomalous pixels and the background are mixed, which causes a higher false alarm rate in the detection result. In this paper, a hyperspectral deep net-based anomaly detector using weight adjustment strategy (WAHyperDNet) is proposed to circumvent the above issues. We leverage three-dimensional convolution instead of the two-dimensional convolution to get a better way of handling high-dimensional data. In this study, the determinative spectrum-spatial features are extracted across the correlation between HSI pixels. Moreover, feature weights in the method are automatically generated based on absolute distance and the spectral similarity angle to describe the differences between the background pixels and the pixels to be tested. Experimental results on five public datasets show that the proposed approach outperforms the state-of-the-art baselines in both effectiveness and efficiency. (C) 2020 Optical Society of America
资助项目	Key Laboratory of Spectral Imaging Technology of Chinese Academy of Sciences ; National Natural Science Foundation of China[11327303] ; National Natural Science Foundation of China[61405239] ; Chinese Academy of Defense Science and Technology Innovation Fund ; West Light Foundation of the Chinese Academy of Sciences[XAB2017B23]
WOS研究方向	Optics
语种	英语
出版者	OPTICAL SOC AMER
WOS记录号	WOS:000583718000001
内容类型	期刊论文
源URL	[http://119.78.100.204/handle/2XEOYT63/16108]
专题	中国科学院计算技术研究所
通讯作者	Gao, Xiaohui
作者单位	1.Chinese Acad Sci, Key Lab Spectral Imaging Technol, Xian Inst Opt & Precis Mech, 17 Xinxi Rd, Xian 710119, Peoples R China 2.Univ Chinese Acad Sci, Ctr Mat Sci & Optoelect Engn, Beijing 100049, Peoples R China 3.Chinese Acad Sci, Inst Comp Technol, Key Lab Network Data Sci & Technol, 6 KeXueYuan South Rd, Beijing 100190, Peoples R China 4.Xian Technol Univ, Sch Optoelect Engn, 2 Xuefuzhonglu Rd, Xian 710021, Peoples R China
推荐引用方式 GB/T 7714	Chong, Dan,Hu, Bingliang,Gao, Xiaohui,et al. Hyperspectral deep convolution anomaly detection based on weight adjustment strategy[J]. APPLIED OPTICS,2020,59(31):9633-9642.
APA	Chong, Dan,Hu, Bingliang,Gao, Xiaohui,Gao, Hao,Xia, Pu,&Wu, Yinhua.(2020).Hyperspectral deep convolution anomaly detection based on weight adjustment strategy.APPLIED OPTICS,59(31),9633-9642.
MLA	Chong, Dan,et al."Hyperspectral deep convolution anomaly detection based on weight adjustment strategy".APPLIED OPTICS 59.31(2020):9633-9642.