A Time-Consistent Video Segmentation Algorithm for Real-Time Implementation

Abstract : In this paper, we propose a time consistent video segmentation algorithm designed for real-time implementation. Our algorithm is based on a region merging process that combines both spatial and motion information. The spatial segmentation takes benefit of an adaptive decision rule and a specific order of merging. Our method has proven to be efficient for the segmentation of natural images with few parameters to be set. Temporal consistency of the segmentation is ensured by incorporating motion information through the use of an improved change detection mask. This mask is designed using both illumination differences between frames, and region segmentation of the previous frame. By considering both pixel and region levels, we obtain a particularly efficient algorithm at a low computational cost, allowing its implementation in real-time on the TriMedia processor for CIF image sequences.
Liste complète des métadonnées

Littérature citée [30 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00315959
Contributeur : David Tschumperlé <>
Soumis le : mardi 2 septembre 2008 - 09:16:09
Dernière modification le : jeudi 12 avril 2018 - 10:50:36
Document(s) archivé(s) le : jeudi 3 juin 2010 - 17:31:34

Fichier

VLSI_final_08.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Citation

Mohammed Elhassani, Stéphanie Jehan-Besson, Luc Brun, Marinette Revenu, Marc Duranton, et al.. A Time-Consistent Video Segmentation Algorithm for Real-Time Implementation. VLSI Design, Hindawi Publishing Corporation, 2008, 11 pp. 〈10.1155/2008/892370〉. 〈inria-00315959〉

Partager

Métriques

Consultations de la notice

252

Téléchargements de fichiers

102