Kinematic structure correspondences via hypergraph matching
File(s)
Accepted version
Author(s)
Chang, HJ
Fischer, T
Petit, M
Zambelli, M
Demiris, Y
Type
Conference Paper
Abstract
In this paper, we present a novel framework for finding the kinematic structure correspondence between two objects in videos via hypergraph matching. In contrast to prior appearance and graph alignment based matching methods which have been applied among two similar static images, the proposed method finds correspondences between two dynamic kinematic structures of heterogeneous objects in videos. Our main contributions can be summarised as follows: (i) casting the kinematic structure correspondence problem into a hypergraph matching problem, incorporating multi-order similarities with normalising weights, (ii) a structural topology similarity measure by a new topology constrained subgraph isomorphism aggregation, (iii) a kinematic correlation measure between pairwise nodes, and (iv) a combinatorial local motion similarity measure using geodesic distance on the Riemannian manifold. We demonstrate the robustness and accuracy of our method through a number of experiments on complex articulated synthetic and real data.
Date Issued
2016-12-12
Date Acceptance
2016-03-02
Citation
2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp.4216-4225
ISBN
9781467388511
ISSN
1063-6919
Publisher
IEEE
Start Page
4216
End Page
4225
Journal / Book Title
2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Copyright Statement
© 2016 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Sponsor
Commission of the European Communities
Identifier
https://ieeexplore.ieee.org/document/7780826
Grant Number
612139
Source
2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Subjects
Science & Technology
Technology
Computer Science, Artificial Intelligence
Computer Science
ARTICULATED STRUCTURE
ALIGNMENT
SHAPE
RECOVERY
MOTION
Publication Status
Published
Start Date
2016-06-27
Finish Date
2016-06-30
Coverage Spatial
Las Vegas, USA
Date Publish Online
2016-12-12