Hyperspectral anomaly detection via super-resolution reconstruction with an attention mechanism

doi:10.1364/AO.432704

	Hyperspectral anomaly detection via super-resolution reconstruction with an attention mechanism
	Chong, Dan 1,2; Hu, Bingliang 1; Gao, Hao 3; Gao, Xiaohui 1
	2021-09-10
发表期刊	APPLIED OPTICS
ISSN	1559-128X
卷号	60 期号:26 页码:8109-8119
摘要	Hyperspectral anomaly detection aims to classify the anomalous objects in the scene. However, the spatial resolution of the hyperspectral images is relatively low, leading to inaccurate detection of abnormal pixels. Existing methods either ignore the low-resolution problem or leverage super-resolution models to reconstruct the global image to detect abnormal pixels. We claim that reconstructing super-resolution of the global image is unnecessary, while the area where the abnormal target is located should be paid more attention to be reconstructed. In this paper, we propose a super-resolution reconstruction with an attention mechanism for hyperspectral anomaly detection. Our method can automatically extract additional high-frequency information from low-spatial-resolution images and detect abnormal pixels simultaneously. Furthermore, the spatial-channel attention mechanism is adopted to select significant features for reconstructing super-resolution images by assigning different weights to different channels and different spatial-spectral locations. Finally, a regularized join loss function is proposed that balances different tasks by adjusting the relative weight. The experimental results on the public hyperspectral real datasets demonstrate that the proposed method outperforms the state-of-the-art methods. (C) 2021 Optical Society of America
DOI	10.1364/AO.432704
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[11327303] ; National Natural Science Foundation of China[61405239] ; Key Laboratory of Spectral Imaging Technology of Chinese Academy of Sciences
WOS研究方向	Optics
WOS类目	Optics
WOS记录号	WOS:000695067100032
出版者	OPTICAL SOC AMER
引用统计	被引频次：2[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/17206
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Gao, Xiaohui
作者单位	1.Chinese Acad Sci, Xian Inst Opt & Precis Mech, Key Lab Spectral Imaging Technol, 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
推荐引用方式 GB/T 7714	Chong, Dan,Hu, Bingliang,Gao, Hao,et al. Hyperspectral anomaly detection via super-resolution reconstruction with an attention mechanism[J]. APPLIED OPTICS,2021,60(26):8109-8119.
APA	Chong, Dan,Hu, Bingliang,Gao, Hao,&Gao, Xiaohui.(2021).Hyperspectral anomaly detection via super-resolution reconstruction with an attention mechanism.APPLIED OPTICS,60(26),8109-8119.
MLA	Chong, Dan,et al."Hyperspectral anomaly detection via super-resolution reconstruction with an attention mechanism".APPLIED OPTICS 60.26(2021):8109-8119.