We aim to infer 3D body pose directly from human silhouettes. Given a visual input (silhouette), the objective is to recover the intrinsic body configuration, recover the viewpoint, reconstruct the input and detect any spatial or temporal outliers. In order to recover intrinsic body configuration (pose) from the visual input (silhouette), we explicitly learn view-based representations of activity manifolds as well as learn mapping functions between such central representations and both the visual input space and the 3D body pose space. The body pose can be recovered in a closed form in two steps by projecting the visual input to the learned representations of the activity manifold, i.e., finding the point on the learned manifold representation corresponding to the visual input, followed by interpolating 3D pose.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Inferring 3D body pose from silhouettes using activity manifold learning


    Contributors:
    Elgammal, A. (author) / Chan-Su Lee, (author)


    Publication date :

    2004-01-01


    Size :

    2118998 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Inferring 3D Body Pose from Silhouettes Using Activity Manifold Learning

    Elgammal, A. / Lee, C.-S. / IEEE Computer Society | British Library Conference Proceedings | 2004



    3D Human Pose from Silhouettes by Relevance Vector Regression

    Agarwal, A. / Triggs, B. / IEEE Computer Society | British Library Conference Proceedings | 2004


    Head pose estimation using Fisher Manifold learning

    Chen, L. / Zhang, L. / Hu, Y. et al. | IEEE | 2003


    Head Pose Estimation Using Fisher Manifold Learning

    Chen, L. / Zhang, L. / Hu, Y. et al. | British Library Conference Proceedings | 2003