This paper proposes a unified framework for spatiotemporal segmentation of video sequences. A Bayesian network is presented to model the interactions among the motion vector field, the intensity segmentation field, and the video segmentation field. The notions of distance transformation and Markov random field are used to express spatiotemporal constraints. Given consecutive frames, an optimization method is proposed to maximize the conditional probability density of the three fields in an iterative way. Experimental results show that the approach is robust and generates spatiotemporally coherent segmentation results.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Video segmentation based on graphical models


    Contributors:
    Yang Wang, (author) / Tele Tan, (author) / Kia-Fock Loe, (author)


    Publication date :

    2003-01-01


    Size :

    933122 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Video Segmentation Based on Graphical Models

    Wang, Y. / Tan, T. / Loe, K.-F. et al. | British Library Conference Proceedings | 2003


    Mixture of Trees Probabilistic Graphical Model for Video Segmentation

    Badrinarayanan, V. / Budvytis, I. / Cipolla, R. | British Library Online Contents | 2014


    Optimising dynamic graphical models for video content analysis

    Xiang, T. / Gong, S. | British Library Online Contents | 2008



    Diagnostic assistant based on graphical probabilistic models

    Prytuly,K.W. / Smith,S. / HRL Labs.,US et al. | Automotive engineering | 2004