Lancaster EPrints

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

Bhaskar, Harish and Mihaylova, Lyudmila (2011) Combined data association and evolving particle filter for tracking of multiple articulated objects. EURASIP Journal on Image and Video Processing, 2011. pp. 1-12. ISSN 1687-5176

[img]
Preview
PDF (EURASIP_2011.pdf)
Download (7Mb) | Preview

    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.

    Item Type: Article
    Journal or Publication Title: EURASIP Journal on Image and Video Processing
    Additional Information: e-ISSN: 1687-5281
    Uncontrolled Keywords: sequential Momte Carlo methods ; multiple articulated objects ; tracking ; evolving population ; genetic algorithms
    Subjects: A General Works > AI Indexes (General)
    Q Science > QA Mathematics > QA75 Electronic computers. Computer science
    T Technology > TA Engineering (General). Civil engineering (General)
    Departments: Faculty of Science and Technology > School of Computing & Communications
    ID Code: 39961
    Deposited By: Dr L Mihaylov
    Deposited On: 15 Mar 2011 15:20
    Refereed?: Yes
    Published?: Published
    Last Modified: 23 Sep 2013 15:50
    Identification Number:
    URI: http://eprints.lancs.ac.uk/id/eprint/39961

    Actions (login required)

    View Item