We present a method for unsupervised learning of classes of motions in video. We project optical flow fields to a complete, orthogonal, a-priori set of basis functions in a probabilistic fashion, which improves the estimation of the projections by incorporating uncertainties in the flows. We then cluster the projections using a mixture of feature-weighted Gaussians over optical flow fields. The resulting model extracts a concise probabilistic description of the major classes of optical flow present. The method is demonstrated on a video of a person's facial expressions.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Bayesian clustering of optical flow fields


    Contributors:
    Hoey, (author) / Little, (author)


    Publication date :

    2003-01-01


    Size :

    1477212 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Bayesian Clustering of Optical Flow Fields

    Hoey, J. / Little, J. / IEEE | British Library Conference Proceedings | 2003



    Towards Bayesian real-time optical flow

    Zelek, J. S. | British Library Online Contents | 2004



    Bayesian image classification using Markov random fields

    Berthod, M. / Kato, Z. / Yu, S. et al. | British Library Online Contents | 1996