基于边缘相关性距离约束的角点匹配  

Corner Matching Based on Edge Correlation Distance Constraints

作　　者：王万良[1] 金亦挺[1] 赵燕伟[1] 郑建炜[1] 

机构地区：[1]浙江工业大学计算机科学与技术学院,杭州310023

出　　处：《计算机科学》2013年第5期283-286,共4页Computer Science

基　　金：国家自然科学基金(61070043);浙江省科技厅项目(2010R50002-11)资助

摘　　要：在双目视觉技术中,针对物体边缘上的角点误匹配问题,提出了一种基于边缘相关性距离约束的角点匹配算法。该算法首先采用基于边缘的角点检测子来提取角点,通过极线约束和角点特征值约束来确定候选角点匹配集合;然后提出"边缘相关性"约束,基于角点距离构造候选角点对的贡献值来对其进行精匹配;最后构造角点特征向量,通过子向量匹配方法进一步对角点匹配对进行检验。实验结果表明,该匹配算法正确率高,有效地解决了边缘角点对的误匹配问题,非常适用于基于边缘曲线的双目视觉应用。In the binocular vision technology, for solving the incorrect matching of edge corner, a comer matching algo- rithm based on edge correlation distance constraint was proposed. Firstly, use comer detection algorithm based on edge to extract comer, confirm candidate corner matching assemble by epipolar constraint and corner＇s threshold constraint. Then, put forward the ＂edge correlation＂ constraint, structure candidate comer pair＇s contribution value based on cor- ner distance to have it fine matched. Finally, structure corner＇s vector, and test comer matching further using sub-vector matching method. The experiment results show that this matching algorithm has high accurate rate, solves the incorrect matching problem of edge corner pair effectively, and it＇s quite suitable for the applications of edge-based binocular vi- sion.

关 键 词：双目视觉 角点匹配 边缘相关性 角点距离 子向量匹配 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]