Iterative Point Matching via multi-direction geometric serialization and reliable correspondence selection

doi:10.1016/j.neucom.2016.02.066

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 机器人理论与应用

	Iterative Point Matching via multi-direction geometric serialization and reliable correspondence selection
	Qian, Deheng1 ; Chen, Tianshi 2; Qiao, Hong1,3 ; Tang, Tang 1
发表期刊	NEUROCOMPUTING
	2016-07-12
卷号	197 页码:171-183
文章类型	Article
摘要	Point matching aims at finding the optimal matching between two sets of feature points. It is widely accomplished by graph matching methods which match nodes of graphs via minimizing energy functions. However, the obtained correspondences between feature points vary in their matching qualities. In this paper, we propose an innovative matching algorithm which iteratively improves the matching found by such methods. The intuition is that we may improve a given matching by identifying "reliable" correspondences, and re-matching the rest feature points without reliable correspondences. A critical issue here is how to identify reliable correspondences, which is addressed with two novel mechanisms, Multi-direction Geometric Serialization (MGS) and Reliable Correspondence Selection (RCS). Specifically, MGS provides representations of the spatial relations among feature points. With these representations, RCS determines whether a correspondence is reliable according to a reliability metric. By recursively applying MGS and RCS, and re-matching feature points without reliable correspondences, a new (intermediate) matching can be obtained. In this manner, our algorithm starts with a matching provided by a classical method, iteratively generates a number of intermediate matchings, and chooses the best one as the final matching. Experiments demonstrate that our algorithm significantly improves the matching precisions of classical graph matching methods. (C) 2016 Published by Elsevier B.V.
关键词	Point Matching Order Relation Projection Graph Matching Dynamic Programming
WOS标题词	Science & Technology ; Technology
DOI	10.1016/j.neucom.2016.02.066
关键词[WOS]	REGISTRATION ; RECOGNITION ; ALGORITHM
收录类别	SCI
语种	英语
项目资助者	National Science Foundation of China(61210009 ; Strategic Priority Research Program of the CAS(XDB02080003) ; Beijing Natural Science Foundation(2141100002014002) ; 61503383)
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:000376694700015
引用统计	被引频次：2[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/11611
专题	多模态人工智能系统全国重点实验室_机器人理论与应用
作者单位	1.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China 2.Chinese Acad Sci, Inst Comp, State Key Lab Comp Architecture, Beijing 100190, Peoples R China 3.Chinese Acad Sci, CEBSIT, Shanghai, Peoples R China
第一作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Qian, Deheng,Chen, Tianshi,Qiao, Hong,et al. Iterative Point Matching via multi-direction geometric serialization and reliable correspondence selection[J]. NEUROCOMPUTING,2016,197:171-183.
APA	Qian, Deheng,Chen, Tianshi,Qiao, Hong,&Tang, Tang.(2016).Iterative Point Matching via multi-direction geometric serialization and reliable correspondence selection.NEUROCOMPUTING,197,171-183.
MLA	Qian, Deheng,et al."Iterative Point Matching via multi-direction geometric serialization and reliable correspondence selection".NEUROCOMPUTING 197(2016):171-183.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
1-s2.0-S092523121600（3616KB）	期刊论文	作者接受稿	开放获取	CC BY-NC-SA	浏览下载