Discovery - University of Dundee - Online Publications

Library & Learning Centre

Articulated human motion tracking with HPSO

Standard

Articulated human motion tracking with HPSO. / John, Vijay; Ivekovic, Spela; Trucco, Emanuele.

Visapp 2009: Proceedings of The Fourth International Conference on Computer Vision Theory and Applications, VOL 1. ed. / A Ranchordas; H Araujo. Setubal : Institute for Systems and Technologies of Information, Control and Communication, 2009. p. 531-538.

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

Harvard

John, V, Ivekovic, S & Trucco, E 2009, 'Articulated human motion tracking with HPSO'. in A Ranchordas & H Araujo (eds), Visapp 2009: Proceedings of The Fourth International Conference on Computer Vision Theory and Applications, VOL 1. Institute for Systems and Technologies of Information, Control and Communication, Setubal, pp. 531-538, 4th International Conference on Computer Vision Theory and Applications, Lisbon, Portugal, 5-8 February.

APA

John, V., Ivekovic, S., & Trucco, E. (2009). Articulated human motion tracking with HPSO. In Ranchordas, A., & Araujo, H. (Eds.), Visapp 2009: Proceedings of The Fourth International Conference on Computer Vision Theory and Applications, VOL 1. (pp. 531-538). Setubal: Institute for Systems and Technologies of Information, Control and Communication.

Vancouver

John V, Ivekovic S, Trucco E. Articulated human motion tracking with HPSO. In Ranchordas A, Araujo H, editors, Visapp 2009: Proceedings of The Fourth International Conference on Computer Vision Theory and Applications, VOL 1. Setubal: Institute for Systems and Technologies of Information, Control and Communication. 2009. p. 531-538.

Author

John, Vijay; Ivekovic, Spela; Trucco, Emanuele / Articulated human motion tracking with HPSO.

Visapp 2009: Proceedings of The Fourth International Conference on Computer Vision Theory and Applications, VOL 1. ed. / A Ranchordas; H Araujo. Setubal : Institute for Systems and Technologies of Information, Control and Communication, 2009. p. 531-538.

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

Bibtex - Download

@inbook{0e553ab8ea134347ac3ba9614ccd728d,
title = "Articulated human motion tracking with HPSO",
publisher = "Institute for Systems and Technologies of Information, Control and Communication",
author = "Vijay John and Spela Ivekovic and Emanuele Trucco",
year = "2009",
editor = "A Ranchordas and H Araujo",
isbn = "978-989-8111-69-2",
pages = "531-538",
booktitle = "Visapp 2009: Proceedings of The Fourth International Conference on Computer Vision Theory and Applications, VOL 1",

}

RIS (suitable for import to EndNote) - Download

TY - CHAP

T1 - Articulated human motion tracking with HPSO

A1 - John,Vijay

A1 - Ivekovic,Spela

A1 - Trucco,Emanuele

AU - John,Vijay

AU - Ivekovic,Spela

AU - Trucco,Emanuele

PB - Institute for Systems and Technologies of Information, Control and Communication

CY - Setubal

PY - 2009

Y1 - 2009

N2 - <p>In this paper, we address full-body articulated human motion tracking from multi-view video sequences acquired in a studio environment. The tracking is formulated as a multi-dimensional nonlinear optimisation and solved using particle swarm optimisation (PSO), a swarm-intelligence algorithm which has gained popularity in recent years due to its ability to solve difficult nonlinear optimisation problems. Our tracking approach is designed to address the limits of particle filtering approaches: it initialises automatically, removes the need for a sequence-specific motion model and recovers from temporary tracking divergence through the use of a powerful hierarchical search algorithm (HPSO). We quantitatively compare the performance of HPSO with that of the particle filter (PF) and annealed particle filter (APF). Our test results, obtained using the framework proposed by (Balan et al., 2005) to compare articulated body tracking algorithms, show that HPSO's pose estimation accuracy and consistency is better than PF and compares favourably with the APF, outperforming it in sequences with sudden and fast motion.</p>

AB - <p>In this paper, we address full-body articulated human motion tracking from multi-view video sequences acquired in a studio environment. The tracking is formulated as a multi-dimensional nonlinear optimisation and solved using particle swarm optimisation (PSO), a swarm-intelligence algorithm which has gained popularity in recent years due to its ability to solve difficult nonlinear optimisation problems. Our tracking approach is designed to address the limits of particle filtering approaches: it initialises automatically, removes the need for a sequence-specific motion model and recovers from temporary tracking divergence through the use of a powerful hierarchical search algorithm (HPSO). We quantitatively compare the performance of HPSO with that of the particle filter (PF) and annealed particle filter (APF). Our test results, obtained using the framework proposed by (Balan et al., 2005) to compare articulated body tracking algorithms, show that HPSO's pose estimation accuracy and consistency is better than PF and compares favourably with the APF, outperforming it in sequences with sudden and fast motion.</p>

KW - Articulated human motion tracking

KW - Hierarchical particle swarm optimisation

KW - Annealed particle filter

KW - CAPTURE

M1 - Conference contribution

SN - 978-989-8111-69-2

BT - Visapp 2009: Proceedings of The Fourth International Conference on Computer Vision Theory and Applications, VOL 1

T2 - Visapp 2009: Proceedings of The Fourth International Conference on Computer Vision Theory and Applications, VOL 1

A2 - Araujo,H

ED - Araujo,H

SP - 531

EP - 538

ER -

Library & Learning Centre

Contact | Accessibility | Policy