摘要
遥感影像匹配是遥感技术中的热点和难点问题,是三维重建、导航、模式识别、DEM自动提取等工作的基础。传统的匹配方法通常是针对同源数据的,文中研究基于广义立体像对的匹配方法,设计并实现了基于小波变换的特征匹配和灰度匹配相结合的匹配方法,并结合现有的遥感数据,人工选取40对同名控制点对匹配点的精度进行检验,实验结果表明该算法具有较快的运行速度和较好的匹配精度。
The image matching has been the hot spot and difficulty in the field of remote sensing,and it is the basis of 3D reconstruction,navigation,mode identify and DEM extraction automatically too.Traditional matching methods aim at the image from the same sensor.It investigates the matching methods based on the generalized stereopair,then an algorithm combined with gray and feature information based on wavelet is presented.We uses the imagery in existance to experiment on the matching method of generalized stereopair.Then we choose forty control points to test the matching precision.The result shows that this algorithm has a better efficiency and precision.
出处
《测绘工程》
CSCD
2011年第4期26-30,共5页
Engineering of Surveying and Mapping
关键词
广义立体像对
特征匹配
金字塔分层
角点
小波
generalized stereopair
feature matching
pyramid delamination
corner
wavelet
