摘要
提出了一种基于区域变化率的变化检测方法,该方法在考虑阴影及灰度匹配的基础上,采用区域信息降低由配准误差引起的虚检率。实验表明,本文方法能够在一定程度上消除配准误差的影响。
A method is presented to decrease the effects of misalignment. Firstly, the images are registered with a reliable strategy so that the ground can be registered correctly. Then the changes of image are detected with traditional algorithm according to image difference based on iterative radiometric calibration. At last, change rate of segmented image regions are used to improve the change detection results. The experiments show that the false detection of misregistering can reduced greatly.
出处
《武汉大学学报（信息科学版）》
EI
CSCD
北大核心
2006年第8期687-690,共4页
Geomatics and Information Science of Wuhan University
基金
国家自然科学基金资助项目(40001018)
关键词
影像配准
变化检测
迭代辐射校正
区域变化率
image registering
change detection
iterative radiometric calibration
local change frequency
