A graph-based shape matching scheme for 3D articulated objects

Min Wen Chao, Chao Hung Lin, Chih Chieh Chang, Tong Yee Lee

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

In this paper, a novel graph-based shape matching scheme for three-dimensional articulated objects is introduced. The underlying graph structure of a given 3D model is composed of its topological skeleton and local geometric features. Matching two graph structures is generally an NP-hard combinatorial optimization problem. To reduce computation cost, two graphs are embedded on a high-dimensional space, and then matched based on an extension of Earth Mover's Distance (EMD). Furthermore, the symmetric components of an articulated object are determined by a voting algorithm with a self-matching strategy to refine the matching correspondences. Experimental results show that the proposed approach is robust, even when the models are under the surface disturbances of noise addition, smoothing, simplification, similarity transformation, and pose deformation. In addition, the proposed approach is capable of handling both global and partial shape matching.

Original languageEnglish
Pages (from-to)295-305
Number of pages11
JournalComputer Animation and Virtual Worlds
Volume22
Issue number2-3
DOIs
Publication statusPublished - 2011 Apr 1

Fingerprint

Combinatorial optimization
Earth (planet)
Costs

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Graphics and Computer-Aided Design

Cite this

@article{26301de2415847ceb2710ad8a63872cb,
title = "A graph-based shape matching scheme for 3D articulated objects",
abstract = "In this paper, a novel graph-based shape matching scheme for three-dimensional articulated objects is introduced. The underlying graph structure of a given 3D model is composed of its topological skeleton and local geometric features. Matching two graph structures is generally an NP-hard combinatorial optimization problem. To reduce computation cost, two graphs are embedded on a high-dimensional space, and then matched based on an extension of Earth Mover's Distance (EMD). Furthermore, the symmetric components of an articulated object are determined by a voting algorithm with a self-matching strategy to refine the matching correspondences. Experimental results show that the proposed approach is robust, even when the models are under the surface disturbances of noise addition, smoothing, simplification, similarity transformation, and pose deformation. In addition, the proposed approach is capable of handling both global and partial shape matching.",
author = "Chao, {Min Wen} and Lin, {Chao Hung} and Chang, {Chih Chieh} and Lee, {Tong Yee}",
year = "2011",
month = "4",
day = "1",
doi = "10.1002/cav.396",
language = "English",
volume = "22",
pages = "295--305",
journal = "Computer Animation and Virtual Worlds",
issn = "1546-4261",
publisher = "John Wiley and Sons Ltd",
number = "2-3",

}

A graph-based shape matching scheme for 3D articulated objects. / Chao, Min Wen; Lin, Chao Hung; Chang, Chih Chieh; Lee, Tong Yee.

In: Computer Animation and Virtual Worlds, Vol. 22, No. 2-3, 01.04.2011, p. 295-305.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A graph-based shape matching scheme for 3D articulated objects

AU - Chao, Min Wen

AU - Lin, Chao Hung

AU - Chang, Chih Chieh

AU - Lee, Tong Yee

PY - 2011/4/1

Y1 - 2011/4/1

N2 - In this paper, a novel graph-based shape matching scheme for three-dimensional articulated objects is introduced. The underlying graph structure of a given 3D model is composed of its topological skeleton and local geometric features. Matching two graph structures is generally an NP-hard combinatorial optimization problem. To reduce computation cost, two graphs are embedded on a high-dimensional space, and then matched based on an extension of Earth Mover's Distance (EMD). Furthermore, the symmetric components of an articulated object are determined by a voting algorithm with a self-matching strategy to refine the matching correspondences. Experimental results show that the proposed approach is robust, even when the models are under the surface disturbances of noise addition, smoothing, simplification, similarity transformation, and pose deformation. In addition, the proposed approach is capable of handling both global and partial shape matching.

AB - In this paper, a novel graph-based shape matching scheme for three-dimensional articulated objects is introduced. The underlying graph structure of a given 3D model is composed of its topological skeleton and local geometric features. Matching two graph structures is generally an NP-hard combinatorial optimization problem. To reduce computation cost, two graphs are embedded on a high-dimensional space, and then matched based on an extension of Earth Mover's Distance (EMD). Furthermore, the symmetric components of an articulated object are determined by a voting algorithm with a self-matching strategy to refine the matching correspondences. Experimental results show that the proposed approach is robust, even when the models are under the surface disturbances of noise addition, smoothing, simplification, similarity transformation, and pose deformation. In addition, the proposed approach is capable of handling both global and partial shape matching.

UR - http://www.scopus.com/inward/record.url?scp=79955012039&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79955012039&partnerID=8YFLogxK

U2 - 10.1002/cav.396

DO - 10.1002/cav.396

M3 - Article

AN - SCOPUS:79955012039

VL - 22

SP - 295

EP - 305

JO - Computer Animation and Virtual Worlds

JF - Computer Animation and Virtual Worlds

SN - 1546-4261

IS - 2-3

ER -