Unsupervised dynamic texture segmentation using local spatiotemporal descriptors

Jie Chen; Guoying Zhao; Matti Pietikäinen

doi:10.1109/icpr.2008.4761119

Unsupervised dynamic texture segmentation using local spatiotemporal descriptors

Jie Chen^*, Guoying Zhao, Matti Pietikäinen

^*Corresponding author for this work

University of Oulu

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

6 Citations (Scopus)

Abstract

Dynamic texture (DT) is an extension of texture to the temporal domain. In this paper, we address the problem of segmenting DT into disjoint regions in an unsupervised way. Each region is characterized by histograms of local binary patterns and contrast in a spatiotemporal mode. It combines the motion and appearance of DT together. Experimental results show that our method is effective in segmenting regions that differ in their dynamics.

Original language	English
Title of host publication	2008 19th International Conference on Pattern Recognition, ICPR 2008
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Print)	9781424421756
DOIs	https://doi.org/10.1109/icpr.2008.4761119
Publication status	Published - 2008
Externally published	Yes

Publication series

Name	Proceedings - International Conference on Pattern Recognition
ISSN (Print)	1051-4651

Access to Document

10.1109/icpr.2008.4761119

Cite this

Chen, J., Zhao, G., & Pietikäinen, M. (2008). Unsupervised dynamic texture segmentation using local spatiotemporal descriptors. In 2008 19th International Conference on Pattern Recognition, ICPR 2008 Article 4761119 (Proceedings - International Conference on Pattern Recognition). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/icpr.2008.4761119

@inproceedings{5ae2ae356fdf4d19bf22446f4267f56b,

title = "Unsupervised dynamic texture segmentation using local spatiotemporal descriptors",

abstract = "Dynamic texture (DT) is an extension of texture to the temporal domain. In this paper, we address the problem of segmenting DT into disjoint regions in an unsupervised way. Each region is characterized by histograms of local binary patterns and contrast in a spatiotemporal mode. It combines the motion and appearance of DT together. Experimental results show that our method is effective in segmenting regions that differ in their dynamics.",

author = "Jie Chen and Guoying Zhao and Matti Pietik{\"a}inen",

year = "2008",

doi = "10.1109/icpr.2008.4761119",

language = "English",

isbn = "9781424421756",

series = "Proceedings - International Conference on Pattern Recognition",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2008 19th International Conference on Pattern Recognition, ICPR 2008",

address = "United States",

}

Unsupervised dynamic texture segmentation using local spatiotemporal descriptors. / Chen, Jie; Zhao, Guoying; Pietikäinen, Matti.
2008 19th International Conference on Pattern Recognition, ICPR 2008. Institute of Electrical and Electronics Engineers Inc., 2008. 4761119 (Proceedings - International Conference on Pattern Recognition).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Unsupervised dynamic texture segmentation using local spatiotemporal descriptors

AU - Chen, Jie

AU - Zhao, Guoying

AU - Pietikäinen, Matti

PY - 2008

Y1 - 2008

N2 - Dynamic texture (DT) is an extension of texture to the temporal domain. In this paper, we address the problem of segmenting DT into disjoint regions in an unsupervised way. Each region is characterized by histograms of local binary patterns and contrast in a spatiotemporal mode. It combines the motion and appearance of DT together. Experimental results show that our method is effective in segmenting regions that differ in their dynamics.

AB - Dynamic texture (DT) is an extension of texture to the temporal domain. In this paper, we address the problem of segmenting DT into disjoint regions in an unsupervised way. Each region is characterized by histograms of local binary patterns and contrast in a spatiotemporal mode. It combines the motion and appearance of DT together. Experimental results show that our method is effective in segmenting regions that differ in their dynamics.

UR - http://www.scopus.com/inward/record.url?scp=77957938064&partnerID=8YFLogxK

U2 - 10.1109/icpr.2008.4761119

DO - 10.1109/icpr.2008.4761119

M3 - Conference contribution

AN - SCOPUS:77957938064

SN - 9781424421756

T3 - Proceedings - International Conference on Pattern Recognition

BT - 2008 19th International Conference on Pattern Recognition, ICPR 2008

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Unsupervised dynamic texture segmentation using local spatiotemporal descriptors

Abstract

Publication series

Access to Document

Other files and links

Fingerprint

Cite this