版权说明 帮助中心
首页 > 成果 > 详情

Unsupervised change detection with expectation-maximization-based level set

SCI-EEI
WOS被引频次:29
认领
导出
Link by DOI
反馈
分享
QQ微信 微博
成果类型:
期刊论文
作者:
Hao, Ming*;Shi, Wenzhong;Zhang, Hua;Li, Chang
通讯作者:
Hao, Ming
作者机构:
[Hao, Ming; Zhang, Hua] School of Environment Science and Spatial Informatics, China University of Mining and Technology, Xuzhou 221116, China
[Shi, Wenzhong] Department of Land Surveying and Geoinformatics, Hong Kong Polytechnic University, Hong Kong, Hong Kong
[Li, Chang] College of Urban and Environmental Science, Central China Normal University, Wuhan 430079, China
通讯机构:
[Hao, Ming] China Univ Min & Technol, Sch Environm Sci & Spatial Informat, Xuzhou 221116, Peoples R China.
语种:
英文
关键词:
Difference images - Expectation Maximization - Gaussian Mixture Model - Level Set method - Multi-temporal image - Remotely sensed images - Topological changes - Unsupervised change detection
期刊:
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
ISSN:
1545-598X
年:
2014
卷:
11
期:
1
页码:
210-214
文献类别:
WOS:Article;EI:Journal article (JA)
所属学科:
ESI学科类别:地球科学;WOS学科类别:Engineering, Electrical & Electronic;Geochemistry & Geophysics;Imaging Science & Photographic Technology;Remote Sensing
入藏号:
WOS:000328698400044;EI:20134817037395
基金类别:
Fundamental Research Funds for the Central Universities [2012LWB31]; Priority Academic Program Development of Jainism Higher Education Institutions; National Natural Science Foundation of China [41101407, 41201451]
机构署名:
本校为其他机构
院系归属:
城市与环境科学学院
摘要:
The level set method, because of its implicit handling of topological changes and low sensitivity to noise, is one of the most effective unsupervised change detection techniques for remotely sensed images. In this letter, an expectation-maximization-based level set method (EMLS) is proposed to detect changes. First, the distribution of the difference image generated from multitemporal images is supposed to satisfy Gaussian mixture model, and expectation-maximization (EM) is then used to estimate the mean values of changed and unchanged pixels in the difference image. Second, two new energy terms, based on the estimated means, are defined and added into the level set method to detect those changes without initial contours and improve final accuracy. Finally, the improved level set method is implemented to partition pixels into changed and unchanged pixels. Landsat and QuickBird images were tested, and experimental results confirm the EMLS effectiveness when compared to state-of-the-art unsupervised change detection methods. ©2013 IEEE.
参考文献:
Ahmadi S, 2010, INT J APPL EARTH OBS, V12, P150, DOI 10.1016/j.jag.2010.02.001
Ball JE, 2007, IEEE T GEOSCI REMOTE, V45, P3022, DOI 10.1109/TGRS.2007.905629
Bazi Y, 2010, IEEE T GEOSCI REMOTE, V48, P3178, DOI 10.1109/TGRS.2010.2045506
Bishop C., 2006, PATTERN RECOGNITION
Bruzzone L, 2000, IEEE T GEOSCI REMOTE, V38, P1171, DOI 10.1109/36.843009

反馈

验证码:
看不清楚,换一个
确定
取消

成果认领

标题:
用户 作者 通讯作者
请选择
请选择
确定
取消

提示

该栏目需要登录且有访问权限才可以访问

如果您有访问权限,请直接 登录访问

如果您没有访问权限,请联系管理员申请开通

管理员联系邮箱:yun@hnwdkj.com