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

作　　者：刘李漫[1] 孙琨[2] 徐海洋[2] 胡怀飞[1] LIU Liman;SUN Kun;XU Haiyang;HU Huaifei(School of Biomedical Engineering, South-Central University for Nationalities, Wuhan 430074, China;School of Automation, Huazhong University of Science and Technology, Wuhan 430074, China)

机构地区：[1]中南民族大学生物医学工程学院,武汉430074 [2]华中科技大学自动化学院,武汉430074

出　　处：《计算机工程与应用》2017年第17期202-206,211,共6页Computer Engineering and Applications

基　　金：国家自然科学基金(No.61305044);高校博士点基金(No.20130144120004)

摘　　要：针对基于图像进行三维重建技术在使用大规模图像集合进行重建时,需要对图像集合中图像进行两两匹配耗时问题,提出了基于哈希技术对图像构建全局哈希特征的方法,通过过滤掉无效的图像关系对来减少计算时间,极大地提高了大规模图像集合三维重建的匹配计算效率。提出的大规模图像快速哈希匹配算法包括构建图像哈希特征、构建初始匹配图、挑选候选匹配对、哈希匹配几个步骤。实验结果表明该方法能显著地提高三维重建中图像匹配的速度。This paper addresses the heavy image matching cost when building3D 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 reconstruction.In this paper a Hash-based technique is proposed to filter non-overlapping pairs to avoid exhaustive pairwise matching,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 in3D reconstruction.

关 键 词：三维重建 快速匹配 哈希 匹配图 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]