Dynamic texture segmentation
Doretto, G., Cremers, D., Favaro, P., and Soatto, S.
Dynamic texture segmentation. In Proceedings of IEEE International Conference on Computer Vision, pp. 1236–1242, Nice, France, October 2003.
Download
PDF (241.2kB )
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.
BibTeX
@INPROCEEDINGS{dorettoCFS03iccv,
author = {Doretto, G. and Cremers, D. and Favaro, P. and Soatto, S.},
title = {Dynamic texture segmentation},
booktitle = iccv,
year = {2003},
volume = {2},
pages = {1236--1242},
address = {Nice, France},
month = oct,
note = {\btohremove{\textsf{\textbf{SCC: 7, GSCC: 15, AR: 20.6\%}}}},
bib2html_pubtype = {Refereed Conferences},
bib2html_rescat = {Dynamic Textures, Visual Motion Segmentation},
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.},
file = {dorettoCFS03iccv.pdf:doretto\\conference\\dorettoCFS03iccv.pdf:PDF},
owner = {doretto},
pdf = {doretto\conference\dorettoCFS03iccv.pdf}
}
Generated by bib2html.pl (written by Patrick Riley )