Change detection in very high-resolution images based on ensemble CNNs

doi:10.1080/01431161.2020.1723818

	Change detection in very high-resolution images based on ensemble CNNs
	Zhang, Xinlong 1; Fan, Rui 1; Ma, Lei 1; Liao, Xiaohan 3; Chen, Xiuwan 2
刊名	INTERNATIONAL JOURNAL OF REMOTE SENSING
	2020-06-17
卷号	41 期号:12 页码:4755-4777
ISSN号	0143-1161
DOI	10.1080/01431161.2020.1723818
通讯作者	Zhang, Xinlong(mtxinlong@126.com)
英文摘要	This paper presents a novel change detection method for very-high-resolution images based on deep learning. In the method, an ensemble CNN change detection framework is proposed. Different from other deep learning change detection methods, samples of changed and unchanged regions of two very-high-resolution images acquired at different times are fed into two CNN. The discriminative deep metric learning based on dissimilarity degree is used to adjust discriminative distance metric of two CNN output layers quantitatively, under which the distance of unchanged samples becomes smaller and that of changed samples becomes higher, respectively. During its training procedure, cost module function based on dissimilarity degree of samples is used to train the ensemble CNN and high-level and abstract features of changed and unchanged pair of samples are driven to learn by the proposed framework. After training, the discriminative distance of unchanged samples becomes smaller and that of changed samples becomes larger. The proposed method justifies the changed and unchanged area of original images and change detection results can be obtained. Experiments on real datasets and theoretical analysis validate the effectiveness and superiority of the proposed method.
资助项目	National key research and development program of China[2017YFB0503005] ; National Natural Science Foundation of China[41771388]
WOS关键词	LAND-COVER CHANGE ; CLASSIFICATION ; PIXEL ; MODEL
WOS研究方向	Remote Sensing ; Imaging Science & Photographic Technology
语种	英语
出版者	TAYLOR & FRANCIS LTD
WOS记录号	WOS:000517366000001
资助机构	National key research and development program of China ; National Natural Science Foundation of China
内容类型	期刊论文
源URL	[http://ir.igsnrr.ac.cn/handle/311030/132640]
专题	中国科学院地理科学与资源研究所
通讯作者	Zhang, Xinlong
作者单位	1.China Elect Technol Grp Corp, China Acad Elect & Informat Technol, Beijing, Peoples R China 2.Peking Univ, Sch Earth & Space Sci, Beijing, Peoples R China 3.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Zhang, Xinlong,Fan, Rui,Ma, Lei,et al. Change detection in very high-resolution images based on ensemble CNNs[J]. INTERNATIONAL JOURNAL OF REMOTE SENSING,2020,41(12):4755-4777.
APA	Zhang, Xinlong,Fan, Rui,Ma, Lei,Liao, Xiaohan,&Chen, Xiuwan.(2020).Change detection in very high-resolution images based on ensemble CNNs.INTERNATIONAL JOURNAL OF REMOTE SENSING,41(12),4755-4777.
MLA	Zhang, Xinlong,et al."Change detection in very high-resolution images based on ensemble CNNs".INTERNATIONAL JOURNAL OF REMOTE SENSING 41.12(2020):4755-4777.