摘要
提出了一种基于矢量图进行遥感影像的区域变化检测的方法，该方法通过将历史矢量图与当前影像进行匹配后叠加、设定全局变化系数与局部变化系数等步骤，对各矢量图斑区域内的影像DN值做统计分析，达到检测区域变化的目的。试算分析表明，全局变化系数比局部变化系数表现得更加敏感，更易对错判数目造成影响。利用历史矢量图做变化检测，不仅可以避免复杂的影像辐射校正工作，还可以充分利用历史形成的矢量库资料，实现数据复用，同时也便于矢量库的历史继承与发展。
This paper takes advantage of the historical vector graph of the land use and combines it with the present remote sensed image and has the necessary geometric rectification and match, to detect the region change of the remote sensed image corresponding to patches in the vector graph. This study calculates statistics indexes of image corresponding to patches of vector graph with different coefficient groups and assesses the computing results by kappa matrix. According to analytical results, the coefficient of entire change is more important to the number of commission error than the coefficient of part change. This method is benefit to the reuse of historical vector graphs. As the image-processing work of this method is based on patches of historical vector graph, it helps to the development of different vector graphs.
出处
《高技术通讯》
CAS
CSCD
北大核心
2006年第6期566-569,共4页
Chinese High Technology Letters
基金
中国科学院知识创新工程重大项目（KZCX3-SW-338-4,KZCX1-SW-01-02）,863计划（2003AA131170）资助项目.
关键词
变化检测
矢量图
局部变化
总体变化
change detection, vector graph, part change, entire change
