CASIA OpenIR  > 模式识别国家重点实验室  > 多媒体计算与图形学
ROML: A Robust Feature Correspondence Approach for Matching Objects in A Set of Images
Jia, Kui1; Chan, Tsung-Han2; Zeng, Zinan3; Gao, Shenghua4; Wang, Gang5; Zhang, Tianzhu6; Ma, Yi4
AbstractFeature-based object matching is a fundamental problem for many applications in computer vision, such as object recognition, 3D reconstruction, tracking, and motion segmentation. In this work, we consider simultaneously matching object instances in a set of images, where both inlier and outlier features are extracted. The task is to identify the inlier features and establish their consistent correspondences across the image set. This is a challenging combinatorial problem, and the problem complexity grows exponentially with the image number. To this end, we propose a novel framework, termed Robust Object Matching using Low-rank constraint (ROML), to address this problem. ROML optimizes simultaneously a partial permutation matrix (PPM) for each image, and feature correspondences are established by the obtained PPMs. Two of our key contributions are summarized as follows. (1) We formulate the problem as rank and sparsity minimization for PPM optimization, and treat simultaneous optimization of multiple PPMs as a regularized consensus problem in the context of distributed optimization. (2) We use the alternating direction method of multipliers method to solve the thus formulated ROML problem, in which a subproblem associated with a single PPM optimization appears to be a difficult integer quadratic program (IQP). We prove that under wildly applicable conditions, this IQP is equivalent to a linear sum assignment problem, which can be efficiently solved to an exact solution. Extensive experiments on rigid/non-rigid object matching, matching instances of a common object category, and common object localization show the efficacy of our proposed method.
KeywordObject Matching Feature Correspondence Low-rank Sparsity
WOS HeadingsScience & Technology ; Technology
Indexed BySCI
Funding OrganizationNational Natural Science Foundation of China(61202158) ; Singapore's Agency for Science, Technology and Research (A*STAR)
WOS Research AreaComputer Science
WOS SubjectComputer Science, Artificial Intelligence
WOS IDWOS:000372926500005
Citation statistics
Document Type期刊论文
Affiliation1.Univ Macau, Fac Sci & Technol, Dept Comp & Informat Sci, E11 Ave Univ, Taipa, Macau Sar, Peoples R China
2.MediaTek Inc, 1,Dusing 1st Rd,Hsinchu Sci Pk, Hsinchu 30078, Taiwan
3.Adv Digital Sci Ctr, 1 Fusionopolis Way, Singapore, Singapore
4.ShanghaiTech Univ, Sch Informat Sci & Technol, 8 Bldg,319 Yueyang Rd, Shanghai 200031, Peoples R China
5.Nanyang Technol Univ, Sch Elect & Elect Engn, Singapore 639798, Singapore
6.Chinese Acad Sci, Inst Automat, 95 Zhongguancun East Rd, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Jia, Kui,Chan, Tsung-Han,Zeng, Zinan,et al. ROML: A Robust Feature Correspondence Approach for Matching Objects in A Set of Images[J]. INTERNATIONAL JOURNAL OF COMPUTER VISION,2016,117(2):173-197.
APA Jia, Kui.,Chan, Tsung-Han.,Zeng, Zinan.,Gao, Shenghua.,Wang, Gang.,...&Ma, Yi.(2016).ROML: A Robust Feature Correspondence Approach for Matching Objects in A Set of Images.INTERNATIONAL JOURNAL OF COMPUTER VISION,117(2),173-197.
MLA Jia, Kui,et al."ROML: A Robust Feature Correspondence Approach for Matching Objects in A Set of Images".INTERNATIONAL JOURNAL OF COMPUTER VISION 117.2(2016):173-197.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Jia, Kui]'s Articles
[Chan, Tsung-Han]'s Articles
[Zeng, Zinan]'s Articles
Baidu academic
Similar articles in Baidu academic
[Jia, Kui]'s Articles
[Chan, Tsung-Han]'s Articles
[Zeng, Zinan]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Jia, Kui]'s Articles
[Chan, Tsung-Han]'s Articles
[Zeng, Zinan]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.