Optical flow in monocular video can serve as a key for recognizing and tracking the three-dimensional pose of human subjects. In comparison with prior work using silhouettes as a key for pose lookup, flow data contains richer information and in experiments can successfully track more difficult sequences. Furthermore, flow recognition is powerful enough to model human abilities in perceiving biological motion from sparse input. The experiments described herein show that a tracker using flow moment lookup can reconstruct a common biological motion (walking) from images containing only point light sources attached to the joints of the moving subject.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Flow lookup and biological motion perception


    Contributors:
    Howe, N.R. (author)


    Publication date :

    2005-01-01


    Size :

    201172 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Flowlookup and Biological Motion Perception

    Howe, N. R. | British Library Conference Proceedings | 2005


    Biological motion drives perception and action.

    Orban de Xivry, Jean-Jacques / Coppe, Sébastien / Lefèvre, Philippe et al. | BASE | 2010

    Free access

    Translation and articulation in biological motion perception

    Masselink, J. (Jana) / Lappe, M. (Markus) | BASE | 2015

    Free access

    Monocular Perception of Biological Motion in Johansson Displays

    Song, Y. / Goncalves, L. / Di Bernardo, E. et al. | British Library Online Contents | 2001


    Perception of biological motion from size-invariant body representations

    Lappe, M. (Markus) / Wittinghofer, K. (Karin) / Lussanet, M.H.E. (Marc) de | BASE | 2015

    Free access