Spectral graph theoretic methods have recently shown great promise for the problem of image segmentation, but due to the computational demands, applications of such methods to spatiotemporal data have been slow to appear For even a short video sequence, the set of all pairwise voxel similarities is a huge quantity of data: one second of a 256/spl times/384 sequence captured at 30 Hz entails on the order of 10/sup 13/ pairwise similarities. The contribution of this paper is a method that substantially reduces the computational requirements of grouping algorithms based on spectral partitioning, making it feasible to apply them to very large spatiotemporal grouping problems. Our approach is based on a technique for the numerical solution of eigenfunction problems known as the Nystrom method This method allows extrapolation of the complete grouping solution using only a small number of "typical" samples. In doing so, we successfully exploit the fact that there are far fewer coherent groups in an image sequence than pixels.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Efficient spatiotemporal grouping using the Nystrom method


    Contributors:
    Fowlkes, C. (author) / Belongie, S. (author) / Malik, J. (author)


    Publication date :

    2001-01-01


    Size :

    1005912 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Efficient Spatiotemporal Grouping Using the Nystrom Method

    Fowlkes, C. / Belongie, S. / Malik, J. et al. | British Library Conference Proceedings | 2001


    Improved Nystrom Integrators

    Lear, William M. | NTRS | 1993



    Efficient grouping under perspective skew

    Turina, A. / Tuytelaars, T. / Van Gool, L. | IEEE | 2001


    Efficient Grouping under Perspective Skew

    Turina, A. / Tuytelaars, T. / Van Gool, L. et al. | British Library Conference Proceedings | 2001