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.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Flow lookup and biological motion perception


    Beteiligte:
    Howe, N.R. (Autor:in)


    Erscheinungsdatum :

    01.01.2005


    Format / Umfang :

    201172 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Flowlookup and Biological Motion Perception

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


    Translation and articulation in biological motion perception

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

    Freier Zugriff

    Lookup-tables for TransClim

    Rieger, Vanessa / Grewe, Volker | DataCite | 2022

    Freier Zugriff

    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

    Freier Zugriff