The computation of optical flow relies on merging information available over an image patch to form an estimate of 2-D image velocity at a point. This merging process raises many issues. These include the treatment of outliers in component velocity measurements and the modeling of multiple motions within a patch which arise from occlusion boundaries or transparency. A new approach for dealing with these issues is presented. It is based on the use of a probabilistic mixture model to explicitly represent multiple motions within a patch. A simple extension of the EM-algorithm is used to compute a maximum likelihood estimate for the various motion parameters. Preliminary experiments indicate that this approach is computationally efficient, and that it can provide robust estimates of the optical flow values in the presence of outliers and multiple motions.<>


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Mixture models for optical flow computation


    Contributors:
    Jepson, A. (author) / Black, M.J. (author)


    Publication date :

    1993-01-01


    Size :

    180094 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Multispectral constraints for optical flow computation

    Markandey, V. / Flinchbaugh, B.E. | IEEE | 1990


    Diffusion constructs in optical flow computation

    Condell, J. V. / Scotney, B. W. / Morrow, P. J. | British Library Online Contents | 2005


    Superpipelined high-performance optical-flow computation architecture

    Diaz, J. / Ros, E. / Agis, R. et al. | British Library Online Contents | 2008


    Optical flow modeling and computation: A survey

    Fortun, D. / Bouthemy, P. / Kervrann, C. | British Library Online Contents | 2015


    Salient Feature Detection for optical flow computation

    Jiaoru Yang / Wang, Rui / Rui Xu | IEEE | 2016