Motion Segmentation by SCC on the Hopkins 155 Database
Computer Vision and Pattern Recognition
2012-10-08 v1
Abstract
We apply the Spectral Curvature Clustering (SCC) algorithm to a benchmark database of 155 motion sequences, and show that it outperforms all other state-of-the-art methods. The average misclassification rate by SCC is 1.41% for sequences having two motions and 4.85% for three motions.
Cite
@article{arxiv.0909.1608,
title = {Motion Segmentation by SCC on the Hopkins 155 Database},
author = {G. Chen and G. Lerman},
journal= {arXiv preprint arXiv:0909.1608},
year = {2012}
}
Comments
Accepted to 2009 ICCV Workshop on Dynamical Vision