Constrained multiscale Markov random fields and the analysis of visual motion

Fabrice Heitz 1 Patrick Bouthemy 1 Patrick Perez 1
1 TEMIS - Advanced Image Sequence Processing
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, INRIA Rennes
Abstract : The use of markov random field (MRF) models within the framework of global bayesian decision has recently brought new powerful solutions to most of static and dynamic image analysis issues. Use of MRF models with the maximum a posteriori criterion leads to the minimization of a global energy function which may exhibit local minima. This minimization is generally performed using deterministic or stochastic relaxation algorithms which can be sped up significantly by using multigrid techniques. In this paper we investigate a new approach to multigrid image analysis based on MRF models. The multigrid algorithm under concern relies on constrained optimization. The global optimization problem associated to MRF modeling is solved over a sequence of nested subsets of the original configuration space. Those subsets consist of allowed configurations constraining the desired solution at different scales. The constrained optimization can be implemented via a coarse-to-fine multigrid algorithm defined on a sequence of consistent multiscale MRF models. The proposed multiscale paradigm yields fast convergence towards high quality estimates when compared to standard monoresolution or multigrid relaxation schemes. It reveals also far less sensitive to local minima than standard relaxation algorithms. The efficiency of the approach is demonstrated on several relevant problems in image sequence analysis : motion detection, optical flow measurement and motion-based segmentation. Results are presented on real world sequences including several moving objects and camera motion.
Type de document :
Rapport
[Research Report] RR-1615, INRIA. 1992
Liste complète des métadonnées

https://hal.inria.fr/inria-00074945
Contributeur : Rapport de Recherche Inria <>
Soumis le : mercredi 24 mai 2006 - 17:02:11
Dernière modification le : jeudi 11 janvier 2018 - 06:20:10
Document(s) archivé(s) le : mardi 12 avril 2011 - 20:13:47

Fichiers

Identifiants

  • HAL Id : inria-00074945, version 1

Collections

Citation

Fabrice Heitz, Patrick Bouthemy, Patrick Perez. Constrained multiscale Markov random fields and the analysis of visual motion. [Research Report] RR-1615, INRIA. 1992. 〈inria-00074945〉

Partager

Métriques

Consultations de la notice

274

Téléchargements de fichiers

62