摘要
角点匹配是立体视觉研究中的一个重要问题,文中针对该问题提出一种基于多邻域支持技术的迭代式角点匹配算法。该算法首先使用Marr和Frisby提出的立体匹配的五大约束限定搜索区域,然后使用了多邻域支持技术对点特征相似性的评价方法进行了改进,最后引入了左/右以及上/下两种对称性测试过程和迭代技术以提高匹配的精度。这些技术解决了传统匹配算法实时性差、精确度低的问题。仿真实验表明,该算法是一种快速、稳定并且实用的角点匹配算法。
An iterative corners correspondence algorithm based on Multi-Neighborhood support technology,which aims at solving corners correspondence problem on study of stereo vision,is proposed in this paper.First the paper uses the five restrictions to the stereo matching process introduced by Marr and Frisby to restrict the searching area,then brings forward an advanced method to measure the comparability of point features based on Multi-Neighborhood support technology.Lastly it introduces the up/down and left/right symmetry test processes and iteration technology to improve the correspondence accuracy.These techniques can solve the problems of traditional algorithms,namely bad real-time performance and low accuracy.The experiment results demonstrate that this algorithm is a speedy,stable and practical corners correspondence algorithm.
出处
《计算机仿真》
CSCD
2007年第10期192-194,215,共4页
Computer Simulation
关键词
角点
匹配
相似性度量
Corner
Correspondence
Comparability measurement
