Non-Negative Matrix Factorization of Partial Track Data for Motion Segmentation
Abstract
This paper addresses the problem of segmenting low-level partial feature point tracks belonging to multiple motions. We show that the local velocity vectors at each instant of the trajectory are an effective basis for motion segmentation. We decompose the velocity profiles of point tracks into different motion components and corresponding non-negative weights using non-negative matrix factorization (NNMF). We then segment the different motions using spectral clustering on the derived weights. We test our algorithm on the Hopkins 155 benchmarking database and several new sequences, demonstrating that the proposed algorithm can accurately segment multiple motions at a speed of a few seconds per frame. We show that our algorithm is particularly successful on low-level tracks from real-world video that are fragmented, noisy and inaccurate.
Cite
Text
Cheriyadat and Radke. "Non-Negative Matrix Factorization of Partial Track Data for Motion Segmentation." IEEE/CVF International Conference on Computer Vision, 2009. doi:10.1109/ICCV.2009.5459311Markdown
[Cheriyadat and Radke. "Non-Negative Matrix Factorization of Partial Track Data for Motion Segmentation." IEEE/CVF International Conference on Computer Vision, 2009.](https://mlanthology.org/iccv/2009/cheriyadat2009iccv-non/) doi:10.1109/ICCV.2009.5459311BibTeX
@inproceedings{cheriyadat2009iccv-non,
title = {{Non-Negative Matrix Factorization of Partial Track Data for Motion Segmentation}},
author = {Cheriyadat, Anil M. and Radke, Richard J.},
booktitle = {IEEE/CVF International Conference on Computer Vision},
year = {2009},
pages = {865-872},
doi = {10.1109/ICCV.2009.5459311},
url = {https://mlanthology.org/iccv/2009/cheriyadat2009iccv-non/}
}