We present a novel approach to motion segmentation by formulating it as the computation of the volume spanned by moving regions in the 3-dimensional spatio-temporal domain, in contrast to standard approaches to motion segmentation which are based on 2-dimensional spatial segmentations. We propose a Bayesian formulation for motion-based segmentation of image sequences, and we solve this Bayesian estimation problem through level set partial differential equations, which we then generalize to the case of multiple motion volumes. In addition, we provide an algorithm for estimating motion parameters independently of any segmentation. The experimental results validate our proposed approach.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Joint space-time motion-based segmentation of image sequences with level set PDEs


    Contributors:


    Publication date :

    2002-01-01


    Size :

    557432 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Joint Space-Time Motion-Based Segmentation of Image Sequences with Level Set PDES

    Mansouri, A.-R. / Mitiche, A. / Langevin, C. | British Library Conference Proceedings | 2002


    The Joint Illumination and Motion Space of Video Sequences

    Xu, Y. / Roy-Chowdhury, A. K. | British Library Conference Proceedings | 2005


    The joint illumination and motion space of video sequences

    Yilei Xu, / Roy-Chowdhury, A.K. | IEEE | 2005


    Variational Space-Time Motion Segmentation

    Cremers, D. / Soatto, S. / IEEE | British Library Conference Proceedings | 2003


    Object-oriented motion estimation and segmentation in image sequences

    Diehl,N. / Daimler-Benz,Ulm,DE | Automotive engineering | 1991