Self-similar regularization of optic-flow for turbulent motion estimation

Patrick Héas 1, 2 Etienne Memin 1 Dominique Heitz 2
1 VISTA - Vision spatio-temporelle et active
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, Inria Rennes – Bretagne Atlantique
Abstract : Based on self-similar models of turbulence, we propose in this paper a multi-scale regularizer in order to provide a closure to the optic-flow estimation problem. Regularization is achieved by constraining motion increments to behave as a self-similar process. The associate constrained minimization problem results in a collection of first-order optic-flow regularizers acting at the different scales. The problem is optimally solved by taking advantage of lagrangian duality. Furthermore, an advantage of using a dual formulation, is that we also infer the regularization parameters. Since, the self-similar model parameters observed in real cases can deviate from theory, we propose to add in the algorithm a bayesian learning stage. The performance of the resulting optic-flow estimator is evaluated on a particle image sequence of a simulated turbulent flow. The self-similar regularizer is also assessed on a meteorological image sequence.
Type de document :
Communication dans un congrès
The 1st International Workshop on Machine Learning for Vision-based Motion Analysis - MLVMA'08, Oct 2008, Marseille, France. 2008
Liste complète des métadonnées

Littérature citée [15 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00325807
Contributeur : Peter Sturm <>
Soumis le : mardi 30 septembre 2008 - 13:46:42
Dernière modification le : mercredi 16 mai 2018 - 11:23:06
Document(s) archivé(s) le : lundi 8 octobre 2012 - 13:45:21

Fichier

mlvma08_submission_9.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : inria-00325807, version 1

Citation

Patrick Héas, Etienne Memin, Dominique Heitz. Self-similar regularization of optic-flow for turbulent motion estimation. The 1st International Workshop on Machine Learning for Vision-based Motion Analysis - MLVMA'08, Oct 2008, Marseille, France. 2008. 〈inria-00325807〉

Partager

Métriques

Consultations de la notice

397

Téléchargements de fichiers

103