计算机工程与应用2017，Vol.53Issue(17)：202-206,211,6.DOI:10.3778/j.issn.1002-8331.1506-0207
基于哈希特征的大规模图像快速匹配算法
Image pair selecting and Hash mapping based fast matching for large scale image collection
摘要
Abstract
This paper addresses the heavy image matching cost when building 3D models from large scale images. Since most images in a collection do not overlap, matching such pairs is cumbersome and does not contribute to the reconstruc-tion. In this paper a Hash-based technique is proposed to filter non-overlapping pairs to avoid exhaustive pairwise match-ing, thus improve matching efficiency. The proposed method consists of four consecutive steps:image Hash description, matching graph initialization, candidate matching graph selection and Hash matching. Experimental results show that the proposed method can greatly speed up the matching stage in 3D reconstruction.关键词
三维重建/快速匹配/哈希/匹配图Key words
3D reconstruction/fast matching/Hash/matching graph分类
信息技术与安全科学引用本文复制引用
刘李漫,孙琨,徐海洋,胡怀飞..基于哈希特征的大规模图像快速匹配算法[J].计算机工程与应用,2017,53(17):202-206,211,6.基金项目
国家自然科学基金(No.61305044) （No.61305044）
高校博士点基金(No.20130144120004). （No.20130144120004）
