Feature Matching via Topology-Aware Graph Interaction Model

doi:10.1109/JAS.2023.123774

CORC > 自动化研究所 > 中国科学院自动化研究所 > 学术期刊 > IEEE/CAA Journal of Automatica Sinica

	Feature Matching via Topology-Aware Graph Interaction Model
	Yifan Lu; Jiayi Ma; Xiaoguang Mei; Jun Huang; Xiao-Ping Zhang
刊名	IEEE/CAA Journal of Automatica Sinica
	2024
卷号	11 期号:1 页码:113-130
关键词	Feature matching graph cut outlier filtering topology preserving
ISSN号	2329-9266
DOI	10.1109/JAS.2023.123774
英文摘要	Feature matching plays a key role in computer vision. However, due to the limitations of the descriptors, the putative matches are inevitably contaminated by massive outliers. This paper attempts to tackle the outlier filtering problem from two aspects. First, a robust and efficient graph interaction model, is proposed, with the assumption that matches are correlated with each other rather than independently distributed. To this end, we construct a graph based on the local relationships of matches and formulate the outlier filtering task as a binary labeling energy minimization problem, where the pairwise term encodes the interaction between matches. We further show that this formulation can be solved globally by graph cut algorithm. Our new formulation always improves the performance of previous locality-based method without noticeable deterioration in processing time, adding a few milliseconds. Second, to construct a better graph structure, a robust and geometrically meaningful topology-aware relationship is developed to capture the topology relationship between matches. The two components in sum lead to topology interaction matching (TIM), an effective and efficient method for outlier filtering. Extensive experiments on several large and diverse datasets for multiple vision tasks including general feature matching, as well as relative pose estimation, homography and fundamental matrix estimation, loop-closure detection, and multi-modal image matching, demonstrate that our TIM is more competitive than current state-of-the-art methods, in terms of generality, efficiency, and effectiveness. The source code is publicly available at http://github.com/YifanLu2000/TIM.
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/54497]
专题	自动化研究所_学术期刊_IEEE/CAA Journal of Automatica Sinica
推荐引用方式 GB/T 7714	Yifan Lu,Jiayi Ma,Xiaoguang Mei,et al. Feature Matching via Topology-Aware Graph Interaction Model[J]. IEEE/CAA Journal of Automatica Sinica,2024,11(1):113-130.
APA	Yifan Lu,Jiayi Ma,Xiaoguang Mei,Jun Huang,&Xiao-Ping Zhang.(2024).Feature Matching via Topology-Aware Graph Interaction Model.IEEE/CAA Journal of Automatica Sinica,11(1),113-130.
MLA	Yifan Lu,et al."Feature Matching via Topology-Aware Graph Interaction Model".IEEE/CAA Journal of Automatica Sinica 11.1(2024):113-130.