Multiple view human articulated tracking using charting and particle swarm optimisation

Vijay John, Emanuele Trucco

    Research output: Chapter in Book/Report/Conference proceedingOther chapter contribution

    3 Citations (Scopus)


    We present a framework for markerless articulated human motion tracking in multi-view sequences. We learn motion models of common actions in a low-dimensional latent space using charting, a nonlinear dimensionality reduction tool which estimates automatically the dimension of the latent space and keeps similar poses close together in it. Additionally charting obtains the inverse mapping from the lowdimensional latent space to the high-dimensional joint angle space. The tracking is formulated as a low-dimensional nonlinear optimisation in the latent space 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. Tracking results with the walking, kicking, praying, posing and punch sequences demonstrate the good accuracy and performance of our approach.
    Original languageEnglish
    Title of host publication3DVP'10
    Subtitle of host publicationProceedings of the 2010 ACM Workshop on 3D Video Processing, Co-located with ACM Multimedia 2010
    Place of PublicationNew York
    PublisherAssociation for Computing Machinery
    Number of pages6
    ISBN (Print)9781450301596
    Publication statusPublished - 2010


    • Charting
    • Particle swarm optimisation
    • Articulated tracking
    • Dimensionality reduction


    Dive into the research topics of 'Multiple view human articulated tracking using charting and particle swarm optimisation'. Together they form a unique fingerprint.

    Cite this