Efficient Spatiotemporal Grouping Using the Nyström Method
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 256x384 sequence captured at 30Hz
entails on the order of 10^13 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 spa- tiotemporal grouping problems. Our approach is
based on a technique for the numerical solution of eigenfunction problems
known as the Nyström 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.
Download: pdf
Text Reference
Charless Fowlkes, Serge Belongie, and Jitendra Malik. Efficient spatiotemporal grouping using the nyström method. In CVPR, I:231–238. 2001.BibTeX Reference
@inproceedings{FowlkesBM_CVPR_2001,AUTHOR = "Fowlkes, Charless and Belongie, Serge and Malik, Jitendra",
TITLE = {Efficient Spatiotemporal Grouping Using the Nystr{\"o}m Method},
BOOKTITLE = "CVPR",
YEAR = "2001",
PAGES = "I:231-238",
TAG = "grouping"
}