Imperial College London

Professor Yiannis Demiris

Faculty of EngineeringDepartment of Electrical and Electronic Engineering

Professor of Human-Centred Robotics, Head of ISN
 
 
 
//

Contact

 

+44 (0)20 7594 6300y.demiris Website

 
 
//

Location

 

1014Electrical EngineeringSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@inproceedings{Chang:2016:10.1109/CVPR.2016.457,
author = {Chang, HJ and Fischer, T and Petit, M and Zambelli, M and Demiris, Y and Chang, HJ and Fischer, T and Petit, M and Zambelli, M and Demiris, Y},
doi = {10.1109/CVPR.2016.457},
pages = {4216--4225},
publisher = {IEEE},
title = {Kinematic Structure Correspondences via Hypergraph Matching},
url = {http://dx.doi.org/10.1109/CVPR.2016.457},
year = {2016}
}

RIS format (EndNote, RefMan)

TY  - CPAPER
AB - 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.
AU - Chang,HJ
AU - Fischer,T
AU - Petit,M
AU - Zambelli,M
AU - Demiris,Y
AU - Chang,HJ
AU - Fischer,T
AU - Petit,M
AU - Zambelli,M
AU - Demiris,Y
DO - 10.1109/CVPR.2016.457
EP - 4225
PB - IEEE
PY - 2016///
SN - 1063-6919
SP - 4216
TI - Kinematic Structure Correspondences via Hypergraph Matching
UR - http://dx.doi.org/10.1109/CVPR.2016.457
UR - http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000400012304031&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=1ba7043ffcc86c417c072aa74d649202
UR - http://ieeexplore.ieee.org/
UR - http://hdl.handle.net/10044/1/30904
ER -