一种基于鲁棒Hausdorff距离的目标匹配算法  

Object matching algorithm based on robust hausdorff distance

作　　者：周志强[1] 汪渤[1] 

机构地区：[1]北京理工大学信息科学技术学院,北京100081

出　　处：《计算机应用》2009年第1期86-88,共3页journal of Computer Applications

基　　金：国家部委预研项目(51405030104BQ0171)

摘　　要：在传统的基于边缘位置的Hausdorff距离匹配的基础上,将边缘的梯度信息引入到距离度量当中,构造了一种新的三维距离函数。在此基础上,提出了一种鲁棒的三维Hausdorff距离及其目标匹配算法,采用粗匹配与精匹配相结合的两步匹配策略有效解决了由距离度量维数增加所导致的算法复杂性增大的问题。实验表明,该算法相对于传统的基于边缘位置的Hausdorff距离目标匹配算法在鲁棒性上有很大的提高。Based on the conventional Hausdorff distance of edge position, we introduced the information of edge gradient to distance measuring, and constructed a new distance function that used the information of edge position and gradient. Then we presented a robust three-dimension Hansdorff distance and the object matching algorithm using the proposed Hausdorff distance. In the proposed algorithm, we used a two-step matching scheme that combined two steps of coarse and refined matching to solve the problem of comPutation complexity increasing caused by using 3D distance measure. Experimental result shows that the matching robustness of the proposed algorithm has been improved greatly compared to conventional algorithms that only use the information of edge position.

关 键 词：HAUSDORFF距离 目标匹配 边缘梯度 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]