The problem of multibody motion segmentation is an important and challenging issue in computer vision. In this paper, a novel segmentation technique based on simulated annealing (SA) is proposed. According to the fact that under linear projection models, feature points of multibody reside in multiple subspaces, firstly, a meaningful energy function is proposed, which favors the correct formation of those subspaces, and some subspaces are generated as the initial state. Then, two strategies of subspace evolution and transformation are developed to optimize the energy function in a manner of simulated annealing. The ultimate configuration of these subspaces will reveal the inherent multiple subspace structure embedded in the data space. The classification of data points to these subspaces is equivalent to multibody grouping. The global optimization process results in an increase of robustness with noise tolerance. The method is also effective in degenerate cases. Promising results on synthetic and real data are presented.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Multibody motion segmentation based on simulated annealing


    Contributors:
    Zhimin Fan, (author) / Jie Zhou, (author) / Ying Wu, (author)


    Publication date :

    2004-01-01


    Size :

    459374 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Multibody Motion Segmentation Based on Simulated Annealing

    Fan, Z. / Zhou, J. / Wu, Y. et al. | British Library Conference Proceedings | 2004


    Illumination Subspace for Multibody Motion Segmentation

    Maki, A. / Hattori, H. / IEEE | British Library Conference Proceedings | 2001


    Photometric subspace for multibody motion segmentation

    Maki, A. | British Library Online Contents | 2004



    The Multibody Trifocal Tensor: Motion Segmentation from 3 Perspective Views

    Hartley, R. / Vidal, R. / IEEE Computer Society | British Library Conference Proceedings | 2004