Landslide Detection of Hyperspectral Remote Sensing Data Based on Deep Learning With Constrains

doi:10.1109/JSTARS.2019.2951725

CORC > 成都山地灾害与环境研究所 > 中国科学院水利部成都山地灾害与环境研究所 > 山地灾害与地表过程重点实验室

	Landslide Detection of Hyperspectral Remote Sensing Data Based on Deep Learning With Constrains
	Ye, Chengming 9; Li, Yao 1,2,10; Cui, Peng 1,2,10; Liang, Li 3; Pirasteh, Saeid 4; Marcato, Jose, Jr.5; Goncalves, Wesley Nunes 5,6; Li, Jonathan 7,8
刊名	IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
	2019-12-01
卷号	12 期号:12 页码:5047-5060
关键词	Terrain factors Feature extraction Hyperspectral imaging Deep learning Support vector machines Deep belief network (DBN) deep learning feature extraction hyperspectral data landslide
ISSN号	1939-1404
DOI	10.1109/JSTARS.2019.2951725
通讯作者	Li, Yao(yaolicd@hotmail.com)
产权排序	2
文献子类	Article
英文摘要	Detecting and monitoring landslides are hot topics in remote sensing community, particularly with the development of remote sensing technologies and the significant progress of computer vision. To the best of our knowledge, no study focused on deep learning-based methods for landslide detection on hyperspectral images. We proposes a deep learning framework with constraints to detect landslides on hyperspectral image. The framework consists of two steps. First, a deep belief network is employed to extract the spectral-spatial features of a landslide. Second, we insert the high-level features and constraints into a logistic regression classifier for verifying the landslide. Experimental results demonstrated that the framework can achieve higher overall accuracy when compared to traditional hyperspectral image classification methods. The precision of the landslide detection on the whole image, obtained by the proposed method, can reach 97.91%, whereas the precision of the linear support vector machine, spectral information divergence, and spectral angle match are 94.36%, 84.50%, and 86.44%, respectively. Also, this article reveals that the high-level feature extraction system has a significant potential for landslide detection, especially in multi-source remote sensing.
电子版国际标准刊号	2151-1535
资助项目	Strategic Priority Research Program of the Chinese Academy of Sciences[XDA23090203] ; Key Research Program of Frontier Sciences, CAS[QYZDY-SSW-DQC006] ; Key Program of Sichuan science and technology department[2018SZ0350]
WOS关键词	SPECTRAL-SPATIAL CLASSIFICATION ; IMAGE CLASSIFICATION ; WENCHUAN EARTHQUAKE ; SOIL-EROSION ; INVENTORY ; FOREST ; INTERFEROMETRY ; BIODIVERSITY ; REGRESSION ; FEATURES
WOS研究方向	Engineering ; Physical Geography ; Remote Sensing ; Imaging Science & Photographic Technology
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000515698700030
资助机构	Strategic Priority Research Program of the Chinese Academy of Sciences ; Key Research Program of Frontier Sciences, CAS ; Key Program of Sichuan science and technology department
内容类型	期刊论文
源URL	[http://ir.imde.ac.cn/handle/131551/34057]
专题	成都山地灾害与环境研究所_山地灾害与地表过程重点实验室
通讯作者	Li, Yao
作者单位	1.Chinese Acad Sci, Inst Mt Hazards & Environm, Chengdu 610041, Peoples R China; 2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China; 3.Chengdu Univ Technol, Coll Management Sci, Chengdu 610059, Peoples R China; 4.Southwest Jiaotong Univ, Fac Geosci & Environm Engn, Chengdu 611756, Peoples R China; 5.Univ Fed Mato Grosso do Sul, Fac Engn Architecture & Urbanism & Geog, BR-79070900 Campo Grande, MS, Brazil; 6.Univ Fed Mato Grosso do Sul, Fac Comp Sci, BR-79070900 Campo Grande, MS, Brazil; 7.Univ Waterloo, Dept Geog & Environm Management, Waterloo, ON N2L 3G1, Canada; 8.Univ Waterloo, Dept Syst Design Engn, Waterloo, ON N2L 3G1, Canada 9.Chengdu Univ Technol, Minist Educ, Key Lab Earth Explorat & Informat Technol, Chengdu 610059, Peoples R China; 10.Chinese Acad Sci, Key Lab Mt Hazards & Earth Surface Proc, Chengdu 610041, Peoples R China;
推荐引用方式 GB/T 7714	Ye, Chengming,Li, Yao,Cui, Peng,et al. Landslide Detection of Hyperspectral Remote Sensing Data Based on Deep Learning With Constrains[J]. IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING,2019,12(12):5047-5060.
APA	Ye, Chengming.,Li, Yao.,Cui, Peng.,Liang, Li.,Pirasteh, Saeid.,...&Li, Jonathan.(2019).Landslide Detection of Hyperspectral Remote Sensing Data Based on Deep Learning With Constrains.IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING,12(12),5047-5060.
MLA	Ye, Chengming,et al."Landslide Detection of Hyperspectral Remote Sensing Data Based on Deep Learning With Constrains".IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 12.12(2019):5047-5060.