Home > Research > Publications & Outputs > Combined data association and evolving particle...

Research

Associated organisational units

Electronic data

Links

Text available via DOI:

Keywords

View graph of relations

Combined data association and evolving particle filter for tracking of multiple articulated objects.

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Published

Standard

Combined data association and evolving particle filter for tracking of multiple articulated objects. / Bhaskar, Harish; Mihaylova, Lyudmila.
In: EURASIP Journal on Image and Video Processing, Vol. 2011, 15.03.2011, p. 1-12.

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Harvard

Bhaskar, H & Mihaylova, L 2011, 'Combined data association and evolving particle filter for tracking of multiple articulated objects.', EURASIP Journal on Image and Video Processing, vol. 2011, pp. 1-12. https://doi.org/10.1155/2011/642532

APA

Bhaskar, H., & Mihaylova, L. (2011). Combined data association and evolving particle filter for tracking of multiple articulated objects. EURASIP Journal on Image and Video Processing, 2011, 1-12. https://doi.org/10.1155/2011/642532

Vancouver

Bhaskar H, Mihaylova L. Combined data association and evolving particle filter for tracking of multiple articulated objects. EURASIP Journal on Image and Video Processing. 2011 Mar 15;2011:1-12. doi: 10.1155/2011/642532

Author

Bhaskar, Harish ; Mihaylova, Lyudmila. / Combined data association and evolving particle filter for tracking of multiple articulated objects. In: EURASIP Journal on Image and Video Processing. 2011 ; Vol. 2011. pp. 1-12.

Bibtex

@article{d5d71831c2f044b5a3d9c40c31722c44,
title = "Combined data association and evolving particle filter for tracking of multiple articulated objects.",
abstract = "This paper proposes an approach for tracking multiple articulated targets using a combined data association and evolving population particle filter. A visual target is represented as a pictorial structure using a collection of parts together with a model of their geometry. Tracking multiple targets in video involves an iterative alternating scheme of selecting valid measurements belonging to a target from a clutter or other measurements that all fall within a validation gate. An algorithm with extended likelihood probabilistic data association and evolving groups of populations of particles representing a multiple-part distribution is designed. Variety in the particles is introduced using constrained genetic operators both in the sampling and resampling steps. We explore the effect of various model parameters on system performance and show that the proposed model achieves better accuracy than other widely used methods on standard datasets.",
keywords = "sequential Momte Carlo methods, multiple articulated objects, tracking, evolving population, genetic algorithms",
author = "Harish Bhaskar and Lyudmila Mihaylova",
note = "e-ISSN: 1687-5281",
year = "2011",
month = mar,
day = "15",
doi = "10.1155/2011/642532",
language = "English",
volume = "2011",
pages = "1--12",
journal = "EURASIP Journal on Image and Video Processing",
issn = "1687-5176",
publisher = "Springer Publishing Company",

}

RIS

TY - JOUR

T1 - Combined data association and evolving particle filter for tracking of multiple articulated objects.

AU - Bhaskar, Harish

AU - Mihaylova, Lyudmila

N1 - e-ISSN: 1687-5281

PY - 2011/3/15

Y1 - 2011/3/15

N2 - This paper proposes an approach for tracking multiple articulated targets using a combined data association and evolving population particle filter. A visual target is represented as a pictorial structure using a collection of parts together with a model of their geometry. Tracking multiple targets in video involves an iterative alternating scheme of selecting valid measurements belonging to a target from a clutter or other measurements that all fall within a validation gate. An algorithm with extended likelihood probabilistic data association and evolving groups of populations of particles representing a multiple-part distribution is designed. Variety in the particles is introduced using constrained genetic operators both in the sampling and resampling steps. We explore the effect of various model parameters on system performance and show that the proposed model achieves better accuracy than other widely used methods on standard datasets.

AB - This paper proposes an approach for tracking multiple articulated targets using a combined data association and evolving population particle filter. A visual target is represented as a pictorial structure using a collection of parts together with a model of their geometry. Tracking multiple targets in video involves an iterative alternating scheme of selecting valid measurements belonging to a target from a clutter or other measurements that all fall within a validation gate. An algorithm with extended likelihood probabilistic data association and evolving groups of populations of particles representing a multiple-part distribution is designed. Variety in the particles is introduced using constrained genetic operators both in the sampling and resampling steps. We explore the effect of various model parameters on system performance and show that the proposed model achieves better accuracy than other widely used methods on standard datasets.

KW - sequential Momte Carlo methods

KW - multiple articulated objects

KW - tracking

KW - evolving population

KW - genetic algorithms

U2 - 10.1155/2011/642532

DO - 10.1155/2011/642532

M3 - Journal article

VL - 2011

SP - 1

EP - 12

JO - EURASIP Journal on Image and Video Processing

JF - EURASIP Journal on Image and Video Processing

SN - 1687-5176

ER -