ML Anthology

Dynamic Texture Segmentation

Gianfranco Doretto, Daniel Cremers, Paolo Favaro, Stefano Soatto
ICCV 2003 pp. 1236-1242
doi:10.1109/ICCV.2003.1238632 /iccv/2003/doretto2003iccv-dynamic/

Abstract

We address the problem of segmenting a sequence of images of natural scenes into disjoint regions that are characterized by constant spatio-temporal statistics. We model the spatio-temporal dynamics in each region by Gauss-Markov models, and infer the model parameters as well as the boundary of the regions in a variational optimization framework. Numerical results demonstrate that - in contrast to purely texture-based segmentation schemes - our method is effective in segmenting regions that differ in their dynamics even when spatial statistics are identical.

PDF ICCV Semantic Scholar

Cite

Text

Doretto et al. "Dynamic Texture Segmentation." IEEE/CVF International Conference on Computer Vision, 2003. doi:10.1109/ICCV.2003.1238632

Markdown

[Doretto et al. "Dynamic Texture Segmentation." IEEE/CVF International Conference on Computer Vision, 2003.](https://mlanthology.org/iccv/2003/doretto2003iccv-dynamic/) doi:10.1109/ICCV.2003.1238632

BibTeX

@inproceedings{doretto2003iccv-dynamic,
  title     = {{Dynamic Texture Segmentation}},
  author    = {Doretto, Gianfranco and Cremers, Daniel and Favaro, Paolo and Soatto, Stefano},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {2003},
  pages     = {1236-1242},
  doi       = {10.1109/ICCV.2003.1238632},
  url       = {https://mlanthology.org/iccv/2003/doretto2003iccv-dynamic/}
}