Learning kinematic structure correspondences using multi-order similarities

File Description SizeFormat 
tpami-learning-kinematic-stamped.pdfAccepted version4.39 MBAdobe PDFDownload
Title: Learning kinematic structure correspondences using multi-order similarities
Author(s): Chang, HJ
Fischer, T
Petit, M
Zambelli, M
Demiris, Y
Item Type: Journal Article
Abstract: We present a novel framework for finding the kinematic structure correspondences between two articulated objects in videos via hypergraph matching. In contrast to 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. Thus our method allows matching the structure of objects which have similar topologies or motions, or a combination of the two. Our main contributions are summarised as follows: (i)casting the kinematic structure correspondence problem into a hypergraph matching problem by incorporating multi-order similarities with normalising weights, (ii)introducing a structural topology similarity measure by aggregating topology constrained subgraph isomorphisms, (iii)measuring kinematic correlations between pairwise nodes, and (iv)proposing 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 synthetic and real data, showing that various other recent and state of the art methods are outperformed. Our method is not limited to a specific application nor sensor, and can be used as building block in applications such as action recognition, human motion retargeting to robots, and articulated object manipulation.
Publication Date: 24-Nov-2017
Date of Acceptance: 4-Nov-2017
URI: http://hdl.handle.net/10044/1/54198
DOI: https://dx.doi.org/10.1109/TPAMI.2017.2777486
Publisher: IEEE
Journal / Book Title: IEEE Transactions on Pattern Analysis and Machine Intelligence
Copyright Statement: © 2017 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/Funder: Commission of the European Communities
Funder's Grant Number: 612139
Keywords: Articulated kinematic structure correspondences
hypergraph matching
subgraph isomorphism aggregation
kinematic correlation
combinatorial local motion similarity
humanoid robots
0801 Artificial Intelligence And Image Processing
0806 Information Systems
0906 Electrical And Electronic Engineering
Artificial Intelligence & Image Processing
Appears in Collections:Faculty of Engineering
Electrical and Electronic Engineering



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

Creative Commons