首页 | 本学科首页   官方微博 | 高级检索  
     

基于非下采样Shearlet和几何结构的遥感图像无监督变化检测
引用本文:李青松,覃锡忠,贾振红,杨杰,胡英杰.基于非下采样Shearlet和几何结构的遥感图像无监督变化检测[J].遥感技术与应用,2014,29(3):482-488.
作者姓名:李青松  覃锡忠  贾振红  杨杰  胡英杰
作者单位:(1.新疆大学信息科学与工程学院,新疆 乌鲁木齐830046;; 2.上海交通大学图像处理和模式识别研究所,上海200240;; 3.新西兰奥克兰理工大学知识工程与开发研究所,新西兰 奥克兰1020)
基金项目:教育部促进与美大地区科研合作与高层次人才培养项目(20101595)。
摘    要:提出了基于非下采样Shearlet和几何结构的遥感图像无监督变化检测新算法。首先将两幅SAR图像相减取绝对值得到差异图像,然后利用基于非下采样Shearlet自适应贝叶斯阈值去噪算法对差异图像进行去噪处理来减少噪声的影响。最后根据差异图像的局部几何特征和邻域信息构造跨特征矢量,再利用模糊C-means聚类算法对跨特征矢量聚类,聚类的结果为变化类和未变化类即最终的变化检测结果。实验证明:该算法对噪声的抗噪性能平稳而且有效,可以得到较好的检测结果。

关 键 词:非下采样Shearlet  几何结构  模糊C-means聚类  遥感图像  变化检测  
收稿时间:2013-03-26

Unsupervised Change Detection of Remote Sensing Images based on Nonsubsampled Shearlet and Geometrical Structure
Li Qingsong,Qin Xizhong,Jia Zhenhong,Yang Jie,Raphael Hu.Unsupervised Change Detection of Remote Sensing Images based on Nonsubsampled Shearlet and Geometrical Structure[J].Remote Sensing Technology and Application,2014,29(3):482-488.
Authors:Li Qingsong  Qin Xizhong  Jia Zhenhong  Yang Jie  Raphael Hu
Affiliation:(1.College of Information Science and Engineering,Xinjiang University,Urumqi 830046,China;; 2.Institute of Image Processing and Pattern Recognition,Shanghai Jiao Tong University,Shanghai 200240,China;; 3.Knowledge Engineering and Discovery Research Institute,Auckland University of Technology,Auckland 1020,New Zealand)
Abstract:A novel unsupervised change detection algorithm of remote sensing images based on Nonsubsampled shearlet and Geometrical structure is proposed.Firstly,the difference image is composed of the absolute value of the difference of two remote sensing images.Then denoising algorithm based on Nonsubsampled shearlet adaptive Bayesian threshold is used to deal with the difference image to reduce the influence of noise.Finally,local geometric features and neighborhood information of the difference image are used to construct the cross\|feature vector,and then the cross\|feature vector is clustered by Fuzzy C\|means clustering algorithm.The results of clustering is change class and no change class,which are the final change detection results.Experiments show that Anti\|noise performance of the proposed algorithm is steady and effective and the proposed algorithm can get a better change detection results.
Keywords:Nonsubsampled shearlet  Geometrical structure  Fuzzy C-means clustering  Remote sensing images  Change detection
本文献已被 CNKI 等数据库收录!
点击此处可从《遥感技术与应用》浏览原始摘要信息
点击此处可从《遥感技术与应用》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号