We describe a probabilistic framework for detecting and tracking motion boundaries. It builds on previous work (M.J. Black and D.J. Fleet, 2000) that used a particle filter to compute a posterior distribution over multiple, local motion models, one of which was specific for motion boundaries. We extend that framework in two ways: 1) with an enhanced likelihood that combines motion and edge support, 2) with a spatiotemporal model that propagates beliefs between adjoining image neighborhoods to encourage boundary continuity and provide better temporal predictions for motion boundaries. Approximate inference is achieved with a combination of tools: sampled representations allow us to represent multimodal non-Gaussian distributions and to apply nonlinear dynamics, while mixture models are used to simplify the computation of joint prediction distributions.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Probabilistic tracking of motion boundaries with spatiotemporal predictions


    Contributors:
    Nestares, O. (author) / Fleet, D.J. (author)


    Publication date :

    2001-01-01


    Size :

    1773055 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Probabilistic Tracking of Motion Boundaries with Spatiotemporal Predictions

    Nestares, O. / Fleet, D. J. / IEEE | British Library Conference Proceedings | 2001


    Probabilistic Detection and Tracking of Motion Boundaries

    Black, M. J. / Fleet, D. J. | British Library Online Contents | 2000



    Probabilistic Bus Delay Predictions with Bayesian Networks

    Buchel, Beda / Corman, Francesco | IEEE | 2021


    Probabilistic Tracking and Recognition of Non-Rigid Hand Motion

    Fei, H. / Reid, I. / IEEE | British Library Conference Proceedings | 2003