Kinematic Structure Correspondences via Hypergraph Matching

Hyung Jin Chang, Tobias Fischer, Maxime Petit, Martina Zambelli, Yiannis Demiris

Research output: Chapter in Book/Report/Conference proceedingConference contribution

10 Citations (Scopus)

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.
Original languageEnglish
Title of host publication2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
PublisherIEEE Computer Society
Pages4216-4225
ISBN (Print)9781467388504
DOIs
Publication statusPublished - 27 Jun 2016
Event29th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2016) - Las Vegas, Nevada, United States
Duration: 26 Jun 20161 Jul 2016

Conference

Conference29th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2016)
Country/TerritoryUnited States
CityLas Vegas, Nevada
Period26/06/161/07/16

Fingerprint

Dive into the research topics of 'Kinematic Structure Correspondences via Hypergraph Matching'. Together they form a unique fingerprint.

Cite this