首页 | 官方网站   微博 | 高级检索  
     

基于PCA与EM算法的多光谱遥感影像变化检测研究
引用本文:吴柯,牛瑞卿,王毅,杜博.基于PCA与EM算法的多光谱遥感影像变化检测研究[J].计算机科学,2010,37(3):282-284.
作者姓名:吴柯  牛瑞卿  王毅  杜博
作者单位:1. 中国地质大学地球物理与空间信息学院,武汉,430074
2. 武汉大学测绘遥感信息工程国家重点实验室,武汉,430079
基金项目:国家863计划资助项目(2007AA12Z160);;国家自然科学基金(40672205);;中科院海洋环流与波动重点实验室开放基金(KLOCAW0906)资助
摘    要:变化检测技术能够从观测数据中有效地提取各种变化信息。以多时相的多光谱遥感影像作为主要研究对象,就基于直接比较像元特征的变化检测中两方面的关键问题——差异影像的构造和变化阈值的提取来开展研究,具体采用PCA结合差值比较的方法构造差异影像,采用EM自动确定变化阈值以提取变化区域。通过与传统变化检测方法的实验比较,证明了该方法的有效性。

关 键 词:变化检测  主成分变换  EM  多光谱  遥感影像  
收稿时间:2009/4/20 0:00:00
修稿时间:2009/7/13 0:00:00

Change Detection of Multi-spectral Remote Sensed Images Based on PCA and EM Algorithm
WU Ke,NIU Rui-qing,WANG Yi,DU Bo.Change Detection of Multi-spectral Remote Sensed Images Based on PCA and EM Algorithm[J].Computer Science,2010,37(3):282-284.
Authors:WU Ke  NIU Rui-qing  WANG Yi  DU Bo
Affiliation:Institute of Geophysics and Geomatics/a>;China University of Geosciences/a>;Wuhan 430074/a>;China;State Key Laboratory for Information Engineering in Surveying/a>;Mapping and Remote Sensing/a>;Wuhan University/a>;Wuhan 430079/a>;China
Abstract:Change detection can get useful changed information from the observed data about the earth. In this paper, a new technology aimed at two aspects in the directly compared way is based on pixel's characters in the multi-spectral and multi temporal remote sensed images,which arc "build the different image" and "threshold determination". In our method, an exact difference image can be made by PCA method, and then the threshold from the EM algorithm is used to obtain changed area,which can be seen as the result. Compared with the traditional method, the proposed method has a higher accuracy, and is more effective.
Keywords:Change detection  Principal component analysis  EM  Multi-spectral  Remote sensed images  
本文献已被 CNKI 万方数据 等数据库收录!
点击此处可从《计算机科学》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-23

京公网安备 11010802026262号