Human body pose estimation with PSO

Spela Ivekovic, Emanuele Trucco

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

Abstract

In this paper we describe the application of Particle Swarm Optimisation to the problem of human body pose estimation from multiple view video sequences. We use a subdivision body model with an underlying skeleton layer to estimate and illustrate the body pose. The optimisation looks for the best match between the silhouettes extracted from the original video sequence and the silhouettes generated by the projection of the model in a pose suggested by the PSO. The original PSO algorithm is applied hierarchically and combined with the full overall optimisation to decrease the effects of error propagation. Results demonstrate the ability of PSO to reliably recover the correct body pose from 4-viewpoint video sequences. © 2006 IEEE.

Original languageEnglish
Title of host publication2006 IEEE Congress on Evolutionary Computation, CEC 2006
Pages1256-1263
Number of pages8
Publication statusPublished - 2006
Event2006 IEEE Congress on Evolutionary Computation - Vancouver, BC, Canada
Duration: 16 Jul 200621 Jul 2006

Conference

Conference2006 IEEE Congress on Evolutionary Computation
Abbreviated titleCEC 2006
CountryCanada
CityVancouver, BC
Period16/07/0621/07/06

Fingerprint

Particle swarm optimization (PSO)

Cite this

Ivekovic, S., & Trucco, E. (2006). Human body pose estimation with PSO. In 2006 IEEE Congress on Evolutionary Computation, CEC 2006 (pp. 1256-1263)
Ivekovic, Spela ; Trucco, Emanuele. / Human body pose estimation with PSO. 2006 IEEE Congress on Evolutionary Computation, CEC 2006. 2006. pp. 1256-1263
@inproceedings{2d397f5c922f4211b8c7e5660ae69850,
title = "Human body pose estimation with PSO",
abstract = "In this paper we describe the application of Particle Swarm Optimisation to the problem of human body pose estimation from multiple view video sequences. We use a subdivision body model with an underlying skeleton layer to estimate and illustrate the body pose. The optimisation looks for the best match between the silhouettes extracted from the original video sequence and the silhouettes generated by the projection of the model in a pose suggested by the PSO. The original PSO algorithm is applied hierarchically and combined with the full overall optimisation to decrease the effects of error propagation. Results demonstrate the ability of PSO to reliably recover the correct body pose from 4-viewpoint video sequences. {\circledC} 2006 IEEE.",
author = "Spela Ivekovic and Emanuele Trucco",
year = "2006",
language = "English",
isbn = "0780394879",
pages = "1256--1263",
booktitle = "2006 IEEE Congress on Evolutionary Computation, CEC 2006",

}

Ivekovic, S & Trucco, E 2006, Human body pose estimation with PSO. in 2006 IEEE Congress on Evolutionary Computation, CEC 2006. pp. 1256-1263, 2006 IEEE Congress on Evolutionary Computation, Vancouver, BC, Canada, 16/07/06.

Human body pose estimation with PSO. / Ivekovic, Spela; Trucco, Emanuele.

2006 IEEE Congress on Evolutionary Computation, CEC 2006. 2006. p. 1256-1263.

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

TY - GEN

T1 - Human body pose estimation with PSO

AU - Ivekovic, Spela

AU - Trucco, Emanuele

PY - 2006

Y1 - 2006

N2 - In this paper we describe the application of Particle Swarm Optimisation to the problem of human body pose estimation from multiple view video sequences. We use a subdivision body model with an underlying skeleton layer to estimate and illustrate the body pose. The optimisation looks for the best match between the silhouettes extracted from the original video sequence and the silhouettes generated by the projection of the model in a pose suggested by the PSO. The original PSO algorithm is applied hierarchically and combined with the full overall optimisation to decrease the effects of error propagation. Results demonstrate the ability of PSO to reliably recover the correct body pose from 4-viewpoint video sequences. © 2006 IEEE.

AB - In this paper we describe the application of Particle Swarm Optimisation to the problem of human body pose estimation from multiple view video sequences. We use a subdivision body model with an underlying skeleton layer to estimate and illustrate the body pose. The optimisation looks for the best match between the silhouettes extracted from the original video sequence and the silhouettes generated by the projection of the model in a pose suggested by the PSO. The original PSO algorithm is applied hierarchically and combined with the full overall optimisation to decrease the effects of error propagation. Results demonstrate the ability of PSO to reliably recover the correct body pose from 4-viewpoint video sequences. © 2006 IEEE.

UR - http://www.scopus.com/inward/record.url?scp=34547303260&partnerID=8YFLogxK

M3 - Conference contribution

SN - 0780394879

SN - 9780780394872

SP - 1256

EP - 1263

BT - 2006 IEEE Congress on Evolutionary Computation, CEC 2006

ER -

Ivekovic S, Trucco E. Human body pose estimation with PSO. In 2006 IEEE Congress on Evolutionary Computation, CEC 2006. 2006. p. 1256-1263