Markerless human motion tracking using hierarchical multi-swarm cooperative particle swarm optimization

The high-dimensional search space involved in markerless full-body articulated human motion tracking from multiple-views video sequences has led to a number of solutions based on metaheuristics, the most recent form of which is Particle Swarm Optimization (PSO). However, the classical PSO suffers fr...

Full description

Main Authors: Saini, S., Zakaria, N., Rambli, D.R.A., Sulaiman, S.
Format: Article
Institution: Universiti Teknologi Petronas
Record Id / ISBN-0: utp-eprints.31373 /
Published: Public Library of Science 2015
Online Access: https://www.scopus.com/inward/record.uri?eid=2-s2.0-84929305746&doi=10.1371%2fjournal.pone.0127833&partnerID=40&md5=8b5ae31942e9fad4f93fc36bdb6ce3a3
http://eprints.utp.edu.my/31373/
Tags: Add Tag
No Tags, Be the first to tag this record!
id utp-eprints.31373
recordtype eprints
spelling utp-eprints.313732022-03-26T03:18:22Z Markerless human motion tracking using hierarchical multi-swarm cooperative particle swarm optimization Saini, S. Zakaria, N. Rambli, D.R.A. Sulaiman, S. The high-dimensional search space involved in markerless full-body articulated human motion tracking from multiple-views video sequences has led to a number of solutions based on metaheuristics, the most recent form of which is Particle Swarm Optimization (PSO). However, the classical PSO suffers from premature convergence and it is trapped easily into local optima, significantly affecting the tracking accuracy. To overcome these drawbacks, we have developed a method for the problem based on Hierarchical Multi-Swarm Cooperative Particle Swarm Optimization (H-MCPSO). The tracking problem is formulated as a non-linear 34-dimensional function optimization problem where the fitness function quantifies the difference between the observed image and a projection of the model configuration. Both the silhouette and edge likelihoods are used in the fitness function. Experiments using Brown and HumanEva-II dataset demonstrated that H-MCPSO performance is better than two leading alternative approaches-Annealed Particle Filter (APF) and Hierarchical Particle Swarm Optimization (HPSO). Further, the proposed tracking method is capable of automatic initialization and self-recovery from temporary tracking failures. Comprehensive experimental results are presented to support the claims. © 2015 Saini et al. Public Library of Science 2015 Article NonPeerReviewed https://www.scopus.com/inward/record.uri?eid=2-s2.0-84929305746&doi=10.1371%2fjournal.pone.0127833&partnerID=40&md5=8b5ae31942e9fad4f93fc36bdb6ce3a3 Saini, S. and Zakaria, N. and Rambli, D.R.A. and Sulaiman, S. (2015) Markerless human motion tracking using hierarchical multi-swarm cooperative particle swarm optimization. PLoS ONE, 10 (5). http://eprints.utp.edu.my/31373/
institution Universiti Teknologi Petronas
collection UTP Institutional Repository
description The high-dimensional search space involved in markerless full-body articulated human motion tracking from multiple-views video sequences has led to a number of solutions based on metaheuristics, the most recent form of which is Particle Swarm Optimization (PSO). However, the classical PSO suffers from premature convergence and it is trapped easily into local optima, significantly affecting the tracking accuracy. To overcome these drawbacks, we have developed a method for the problem based on Hierarchical Multi-Swarm Cooperative Particle Swarm Optimization (H-MCPSO). The tracking problem is formulated as a non-linear 34-dimensional function optimization problem where the fitness function quantifies the difference between the observed image and a projection of the model configuration. Both the silhouette and edge likelihoods are used in the fitness function. Experiments using Brown and HumanEva-II dataset demonstrated that H-MCPSO performance is better than two leading alternative approaches-Annealed Particle Filter (APF) and Hierarchical Particle Swarm Optimization (HPSO). Further, the proposed tracking method is capable of automatic initialization and self-recovery from temporary tracking failures. Comprehensive experimental results are presented to support the claims. © 2015 Saini et al.
format Article
author Saini, S.
Zakaria, N.
Rambli, D.R.A.
Sulaiman, S.
spellingShingle Saini, S.
Zakaria, N.
Rambli, D.R.A.
Sulaiman, S.
Markerless human motion tracking using hierarchical multi-swarm cooperative particle swarm optimization
author_sort Saini, S.
title Markerless human motion tracking using hierarchical multi-swarm cooperative particle swarm optimization
title_short Markerless human motion tracking using hierarchical multi-swarm cooperative particle swarm optimization
title_full Markerless human motion tracking using hierarchical multi-swarm cooperative particle swarm optimization
title_fullStr Markerless human motion tracking using hierarchical multi-swarm cooperative particle swarm optimization
title_full_unstemmed Markerless human motion tracking using hierarchical multi-swarm cooperative particle swarm optimization
title_sort markerless human motion tracking using hierarchical multi-swarm cooperative particle swarm optimization
publisher Public Library of Science
publishDate 2015
url https://www.scopus.com/inward/record.uri?eid=2-s2.0-84929305746&doi=10.1371%2fjournal.pone.0127833&partnerID=40&md5=8b5ae31942e9fad4f93fc36bdb6ce3a3
http://eprints.utp.edu.my/31373/
_version_ 1741197562558283776
score 11.62408

Similar Items