计算机工程与应用Issue(12)：147-150,165,5.DOI:10.3778/j.issn.1002-8331.1206-0377
基于SIFT和Daisy相结合的立体匹配算法
Stereo matching algorithm based on combination of SIFT and Daisy descriptor
摘要
Abstract
Stereo matching is one of the most active research subjects in computer vision. Aiming at the problems that tra-ditional SIFT descriptor is subject to mismatch easily when the image has similar areas, and 200-dimensional description reduces the efficiency of Daisy descriptor algorithm, this paper presents a stereo matching algorithm based on the combina-tion of SIFT and Daisy descriptor. The method uses SIFT algorithm to generate feature points, and then describes these feature points by Daisy descriptor for its good rotation invariant, and the disparity map is obtained according to the nearest neighbor matching based on Euclidean distance and seed region growing. Experimental results show this algorithm wins high match-ing accuracy and better performance when there are different levels of image geometric distortion or radiation distortion.关键词
立体匹配/尺度不变特征变换(SIFT)/Daisy/特征描述符Key words
stereo matching/Scale Invariant Feature Transform(SIFT)/Daisy/feature descriptor分类
信息技术与安全科学引用本文复制引用
杨薇,董洪伟,刘蕾..基于SIFT和Daisy相结合的立体匹配算法[J].计算机工程与应用,2014,(12):147-150,165,5.基金项目
中央高校基本科研业务费专项资金资助（No.JUSRP211A35）。 （）
