一种新的邻域搜索特征点匹配算法  

A novel feature points matching algorithm for neighborhood searching

作　　者：周杰[1] 邱运春 黄弋钊[1] 

机构地区：[1]四川工程职业技术学院,四川德阳618000 [2]西南科技大学计算机科学与技术学院,四川绵阳621010

出　　处：《兰州理工大学学报》2016年第3期102-106,共5页Journal of Lanzhou University of Technology

基　　金：国家863计划(2013AA01A213);四川省科技厅项目(2014JY0066)

摘　　要：依据双目立体视觉原理结合光栅投影进行形貌恢复的方法是以被测物体表面投射光栅的相位为特征,其中特征点匹配是双目光栅投影进行形貌恢复的关键步骤.特征点匹配算法的速度和精度,直接决定了形貌恢复的速度和精度.本文主要研究双目光栅投影中的特征点匹配算法,提出一种利用匹配点之间邻域关系进行特征点匹配的算法.实验结果表明该方法匹配精度高,时间复杂度低,不需要知道相机内外参数即可进行匹配,并且能够处理不连通区域的匹配.In the method of morphology recovery with the principle of binocular stereo vision combined with grating projection,the phase of the projected grating on the object surface is taken as a feature.Therefore,the feature points matching is the key to morphology recovery with binocular raster projection.The speed and precision of the feature points matching algorithm will directly determine the speed and accuracy of the morphology recovery.In this paper,feature points matching algorithm with binocular grating projection is investigated emphatically and a method for feature points matching with the neighborhood relations among matching points is presented.The experimental result shows that this method possesses high matching precision and low time complexity.In addition,it does not need to know the internal and external parameters of the camera to handle the matching and the matching of unconnected area as well.

关 键 词：形貌恢复 光栅投影 立体匹配 相位 

分 类 号：TP39[自动化与计算机技术—计算机应用技术]