We consider the problem of localizing the articulated and deformable shape of a walking person in a single view. We represent the non-rigid 2D body contour by a Bayesian graphical model whose nodes correspond to point positions along the contour. The deformability of the model is constrained by learned priors corresponding to two basic mechanisms: local non-rigid deformation, and rotation motion of the joints. Four types of image cues are combined to relate the model configuration to the observed image, including edge gradient map, foreground/background mask, skin color mask, and appearance consistency constraints. The constructed Bayes network is sparse and chain-like, enabling efficient spatial inference through sequential Monte Carlo sampling methods. We evaluate the performance of the model on images taken in cluttered, outdoor scenes. The utility of each image cue is also empirically explored.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Representation and matching of articulated shapes


    Contributors:
    Jiayong Zhang, (author) / Collins, R. (author) / Yanxi Liu, (author)


    Publication date :

    2004-01-01


    Size :

    1640301 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Representation and Matching of Articulated Shapes

    Zhang, J. / Collins, R. / Liu, Y. et al. | British Library Conference Proceedings | 2004


    Matching 2D and 3D articulated shapes using the eccentricity transform

    Ion, A. / Artner, N. M. / Peyre, G. et al. | British Library Online Contents | 2011


    EigenTracking: Robust Matching and Tracking of Articulated Objects Using a View-Based Representation

    Black, M. J. / Jepson, A. D. | British Library Online Contents | 1998



    Matching shapes

    Belongie, S. / Malik, J. / Puzicha, J. | IEEE | 2001