POS数据辅助的航空影像变化检测方法研究  

Change Detection Using Aerial Images with POS Data

作　　者：袁修孝[1] 季顺平[1] 

机构地区：[1]武汉大学遥感信息工程学院,武汉市珞喻路129号430079

出　　处：《武汉大学学报（信息科学版）》2007年第4期283-286,共4页Geomatics and Information Science of Wuhan University

基　　金：高等学校全国优秀博士学位论文作者专项基金资助项目(200142);国家教育部新世纪优秀人才支持计划资助项目(NCET-04-0662)

摘　　要：提出了一种利用机载定位定向系统(POS)数据辅助航空影像进行影像匹配和变化检测的方法。首先利用带POS数据的老影像解求新影像的外方位元素,然后在老立体影像上提取特征点,根据前方交会和共线条件方程得到新影像上同名点的近似位置,再与新影像进行匹配,寻找匹配不好的点作为变化区域的初始位置。以此为基础选择精检测窗口,进行边缘提取和跟踪,并进行链码匹配,最终确定发生变化的区域。试验证实,本文方法是可行的。A method of change detection using aerial images with POS data is presented. Firstly, the new images ＇ orientation parameters are resolved using the old aerial images with POS data in the same area, and feature points are extracted in old images, and new images＇ conjugate points are computed using forward intersection and collinearity equations. Then gray matching are done with the conjugate points, and the points which can not match well are found. These points will be preliminary regarded as been changed, and based on them, check-up windows are selected for the next precise detection. Edge extraction and chain code trace are done in these windows, and the corresponding chain codes are matched. At last the change areas are obtained according to the matching results. Experiment proves that this method is feasible, and gets relatively encourage result.

关 键 词：变化检测 POS系统 航空影像 影像匹配 

分 类 号：TP753[自动化与计算机技术—检测技术与自动化装置] P231.5[自动化与计算机技术—控制科学与工程]