Markerless human motion capture using hierarchical particle swarm optimisation

Vijay John, Spela Ivekovic, Emanuele Trucco

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


    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), annealed particle filter (APF) and partitioned sampling annealed particle filter (PSAPF). Our test results, obtained using the framework proposed by Balan et al [1] to compare articulated body tracking algorithms, show that HPSO's pose estimation accuracy and consistency is better than PF, APF and PSAPF.

    Original languageEnglish
    Title of host publicationComputer Vision, Imaging and Computer Graphics
    Subtitle of host publicationTheory and Applications
    EditorsAlpesh Kumar Ranchordas, João Madeiras Pereira, Hélder J. Araujo, João Manuel R. S. Tavares
    Place of PublicationBerlin
    Number of pages14
    ISBN (Electronic)9783642118401
    ISBN (Print)9783642118395
    Publication statusPublished - 2010
    EventInternational Joint Conference, VISIGRAPP 2009 - Lisbon, Portugal
    Duration: 5 Feb 20098 Feb 2009

    Publication series

    NameCommunications in computer and information science
    ISSN (Print)1865-0929


    ConferenceInternational Joint Conference, VISIGRAPP 2009




    Dive into the research topics of 'Markerless human motion capture using hierarchical particle swarm optimisation'. Together they form a unique fingerprint.

    Cite this