An artificial target detection method combining a polarimetric feature extractor with deep convolutional neural networks

doi:10.1080/01431161.2020.1727584

HFCAS OpenIR

	An artificial target detection method combining a polarimetric feature extractor with deep convolutional neural networks
	Sun, Rui 1,2,3; Sun, Xiaobing1,3 ; Chen, Feinan 1,3; Pan, Hao 1,2,3; Song, Qiang 1,2,3
	2020-02-18
发表期刊	INTERNATIONAL JOURNAL OF REMOTE SENSING
ISSN	0143-1161
通讯作者	Sun, Xiaobing(xbsun@aiofm.ac.cn)
摘要	To improve the success rate of target detection, a fusion method that comprises a polarimetric feature extractor and a deep convolutional neural network (CNN) with consecutive small (2 x 2) convolutions (or, CSC-CNN for simplicity) is proposed. First, we theoretically analyse the dispersion characteristics on a target surface based on the concept of information entropy, and it is concluded that the dispersion measure can be selected as a relevant feature for polarimetric images. Then, a polarimetric feature extractor is introduced for conveniently calculating dispersion measures with fewer prior parameters in outdoor measurements. Finally, a CSC-CNN is adopted for subsequent target detection with small scale training samples. The experimental results indicate that the proposed fusion method demonstrates great potential for reducing the detection error rate, which is less than that of the traditional method used for comparison.
DOI	10.1080/01431161.2020.1727584
关键词[WOS]	POLARIZATION ; ELIMINATION ; DIVISION
收录类别	SCI
语种	英语
资助项目	National Key R&D Program of China (NKRDPC)[2016YFE0201400] ; China High-resolution Earth Observation System (CHEOS)[30-Y20A010-9007-17/18]
项目资助者	National Key R&D Program of China (NKRDPC) ; China High-resolution Earth Observation System (CHEOS)
WOS研究方向	Remote Sensing ; Imaging Science & Photographic Technology
WOS类目	Remote Sensing ; Imaging Science & Photographic Technology
WOS记录号	WOS:000514446700001
出版者	TAYLOR & FRANCIS LTD
引用统计	被引频次：15[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.hfcas.ac.cn:8080/handle/334002/103874
专题	中国科学院合肥物质科学研究院
通讯作者	Sun, Xiaobing
作者单位	1.Chinese Acad Sci, Anhui Inst Opt & Fine Mech, Hefei, Anhui, Peoples R China 2.Univ Sci & Technol China, Hefei, Anhui, Peoples R China 3.Chinese Acad Sci, Key Lab Opt Calibrat & Characterizat, 350 Shushan Lake Rd, Hefei 230031, Anhui, Peoples R China
第一作者单位	中科院安徽光学精密机械研究所
通讯作者单位	中科院安徽光学精密机械研究所
推荐引用方式 GB/T 7714	Sun, Rui,Sun, Xiaobing,Chen, Feinan,et al. An artificial target detection method combining a polarimetric feature extractor with deep convolutional neural networks[J]. INTERNATIONAL JOURNAL OF REMOTE SENSING,2020.
APA	Sun, Rui,Sun, Xiaobing,Chen, Feinan,Pan, Hao,&Song, Qiang.(2020).An artificial target detection method combining a polarimetric feature extractor with deep convolutional neural networks.INTERNATIONAL JOURNAL OF REMOTE SENSING.
MLA	Sun, Rui,et al."An artificial target detection method combining a polarimetric feature extractor with deep convolutional neural networks".INTERNATIONAL JOURNAL OF REMOTE SENSING (2020).