Producing an accurate motion flow field is very difficult at motion boundaries. We present a noniterative approach for segmentation from image motion, based on two voting processes, in different dimensional spaces. By expressing the motion layers as surfaces in a 4D (four-dimensional) space, a voting process is first used to enforce the smoothness of motion and determine an estimation of pixel velocities, motion regions and boundaries. The boundary estimation is then combined with intensity information from the original images in order to locally define a boundary tensor field. The correct boundary is inferred by a 2D (two-dimensional) voting process within this field that enforces the smoothness of boundaries. Finally, correct velocities are computed for the pixels near boundaries, as they are reassigned to different regions. We demonstrate our contribution by analyzing several image sequences, containing multiple types of motion.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Motion segmentation with accurate boundaries - a tensor voting approach


    Beteiligte:
    Nicolescu, M. (Autor:in) / Medioni, G. (Autor:in)


    Erscheinungsdatum :

    2003-01-01


    Format / Umfang :

    821035 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Motion Segmentation with Accurate Boundaries - A Tensor Voting Approach

    Nicolescu, M. / Medioni, G. / IEEE | British Library Conference Proceedings | 2003


    4-D Tensor Voting Motion Segmentation for Obstacle Detection in Autonomous Guided Vehicle

    Dumortier, Y. / Herlin, I. / Ducrot, A. | British Library Conference Proceedings | 2008


    4-D Tensor Voting motion segmentation for obstacle detection in autonomous guided vehicle

    Dumortier, Yann / Herlin, Isabelle / Ducrot, Andre | IEEE | 2008


    A Tensor Voting Approach for the Hierarchical Segmentation of 3-D Acoustic Images

    Tao, L. / Murino, V. / Medioni, G. | British Library Conference Proceedings | 2002


    Automatic Moving Object Segmentation with Accurate Boundaries

    Wang, Jia / Wang, Haifeng / Liu, Qingshan et al. | Springer Verlag | 2006