Zones quasi-plates spatio-temporelles et segmentation morphologique de s equences vid eo

Abstract : Segmentation quality often depends on the problem under consideration. In order to face the various needs for which it is involved, segmentation may be dri- ven by the user, instead of being fully automatic. Mathematical Morphology has provided several user- driven segmentation approaches, mostly relying on the watershed transform. Nevertheless, Soille has re- cently suggested another solution consisting in ga- thering puzzle pieces computed as Quasi-Flat Zones (QFZ) of an image. In this paper, we study more deeply this user-driven segmentation scheme in the context of video data. Thus we introduce the concept of Spatio-Temporal QFZ and propose several methods for extracting such zones from a video sequence.
Document type :
Conference papers
Complete list of metadatas

Cited literature [14 references]  Display  Hide  Download

https://hal.inria.fr/inria-00595251
Contributor : Peter Sturm <>
Submitted on : Tuesday, May 24, 2011 - 11:35:47 AM
Last modification on : Thursday, January 11, 2018 - 6:22:39 AM
Long-term archiving on : Friday, November 9, 2012 - 12:05:35 PM

File

paper09.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : inria-00595251, version 1

Collections

Citation

Jonathan Weber, Sébastien Lefèvre, Pierre Gancarski. Zones quasi-plates spatio-temporelles et segmentation morphologique de s equences vid eo. ORASIS - Congrès des jeunes chercheurs en vision par ordinateur, INRIA Grenoble Rhône-Alpes, Jun 2011, Praz-sur-Arly, France. ⟨inria-00595251⟩

Share

Metrics

Record views

267

Files downloads

159