We present a framework for motion segmentation that combines the concepts of layer-based methods and feature-based motion estimation. We estimate the initial correspondences by comparing vectors of filter outputs at interest points, from which we compute candidate scene relations via random sampling of minimal subsets of correspondences. We achieve a dense, piecewise smooth assignment of pixels to motion layers using a fast approximate graph-cut algorithm based on a Markov random field formulation. We demonstrate our approach on image pairs containing large inter-frame motion and partial occlusion. The approach is efficient and it successfully segments scenes with inter-frame disparities previously beyond the scope of layer-based motion segmentation methods.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    What went where [motion segmentation]


    Beteiligte:
    Wills, J. (Autor:in) / Agarwal, S. (Autor:in) / Belongie, S. (Autor:in)


    Erscheinungsdatum :

    01.01.2003


    Format / Umfang :

    879969 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    What Went Where

    Wills, J. / Agarwal, S. / Belongie, S. et al. | British Library Conference Proceedings | 2003


    Where the professor went

    Kimberley,W. / Caparo Vehicle Technologies,GB | Kraftfahrwesen | 2006


    What steel was made and where it went in 1926

    Engineering Index Backfile | 1927



    What went wrong?

    Online Contents | 1998