ML Anthology

Motion Segmentation by Subspace Separation and Model Selection

Ken-ichi Kanatani
ICCV 2001 pp. 586-591
doi:10.1109/ICCV.2001.937679 /iccv/2001/kanatani2001iccv-motion/

Abstract

Reformulating the Costeira-Kanade algorithm as a pure mathematical theorem independent of the Tomasi-Kanade factorization, we present a robust segmentation algorithm by incorporating such techniques as dimension correction, model selection using the geometric AIC, and least-median fitting. Doing numerical simulations, we demonstrate that oar algorithm dramatically outperforms existing methods. It does not involve any parameters which need to be adjusted empirically.

PDF ICCV Semantic Scholar

Cite

Text

Kanatani. "Motion Segmentation by Subspace Separation and Model Selection." IEEE/CVF International Conference on Computer Vision, 2001. doi:10.1109/ICCV.2001.937679

Markdown

[Kanatani. "Motion Segmentation by Subspace Separation and Model Selection." IEEE/CVF International Conference on Computer Vision, 2001.](https://mlanthology.org/iccv/2001/kanatani2001iccv-motion/) doi:10.1109/ICCV.2001.937679

BibTeX

@inproceedings{kanatani2001iccv-motion,
  title     = {{Motion Segmentation by Subspace Separation and Model Selection}},
  author    = {Kanatani, Ken-ichi},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {2001},
  pages     = {586-591},
  doi       = {10.1109/ICCV.2001.937679},
  url       = {https://mlanthology.org/iccv/2001/kanatani2001iccv-motion/}
}