Dynamic texture segmentation

Gianfranco Doretto; Daniel Cremers; Paolo Favaro; Stefano Soatto

doi:10.1109/iccv.2003.1238632

Dynamic texture segmentation

Gianfranco Doretto, Daniel Cremers, Paolo Favaro, Stefano Soatto

Publikation: Beitrag in Fachzeitschrift › Konferenzartikel › Begutachtung

150 Zitate (Scopus)

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.

Originalsprache	Englisch
Seiten (von - bis)	1236-1242
Seitenumfang	7
Fachzeitschrift	Proceedings of the IEEE International Conference on Computer Vision
Jahrgang	2
DOIs	https://doi.org/10.1109/iccv.2003.1238632
Publikationsstatus	Veröffentlicht - 2003
Extern publiziert	Ja
Veranstaltung	NINTH IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION - Nice, Frankreich Dauer: 13 Okt. 2003 → 16 Okt. 2003

Zugriff auf Dokument

10.1109/iccv.2003.1238632

Andere Dateien und Links

Verknüpfung zur Publikation in Scopus

Dieses zitieren

@article{7e36b989d9574720ba0ed658abd4c8bf,

title = "Dynamic texture 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.",

author = "Gianfranco Doretto and Daniel Cremers and Paolo Favaro and Stefano Soatto",

year = "2003",

doi = "10.1109/iccv.2003.1238632",

language = "English",

volume = "2",

pages = "1236--1242",

journal = "Proceedings of the IEEE International Conference on Computer Vision",

issn = "1550-5499",

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

note = "NINTH IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION ; Conference date: 13-10-2003 Through 16-10-2003",

}

TY - JOUR

T1 - Dynamic texture segmentation

AU - Doretto, Gianfranco

AU - Cremers, Daniel

AU - Favaro, Paolo

AU - Soatto, Stefano

PY - 2003

Y1 - 2003

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=0344120639&partnerID=8YFLogxK

U2 - 10.1109/iccv.2003.1238632

DO - 10.1109/iccv.2003.1238632

M3 - Conference article

AN - SCOPUS:0344120639

SN - 1550-5499

VL - 2

SP - 1236

EP - 1242

JO - Proceedings of the IEEE International Conference on Computer Vision

JF - Proceedings of the IEEE International Conference on Computer Vision

T2 - NINTH IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION

Y2 - 13 October 2003 through 16 October 2003

ER -

Dynamic texture segmentation

Abstract

Zugriff auf Dokument

Andere Dateien und Links

Fingerprint

Dieses zitieren