Semi-local variational optical flow estimation

Denis Fortun 1, * Charles Kervrann 1
* Auteur correspondant
Abstract : Global variational methods for optical flow estimation usually suffer from an over-smoothing effect. We propose a semilocal estimation framework designed to integrate and improve any variational method. The idea is to implicitly segment the minimization domain into coherently moving windows. In a first time, local variational estimations are performed in overlapping candidate square regions. Then, a global discrete optimization, non subject to the over-smoothing introduced by variational approaches, selects the optimal window for each pixel. Experimental results show an increasing of the sharpness of discontinuities and a significant improvement of global registration errors compared to the results of the baseline global variational method.
Type de document :
Communication dans un congrès
IEEE. IEEE International Conference on Image Processing, ICIP 2012, Sep 2012, Orlando, FL, United States. 2012
Liste complète des métadonnées

Littérature citée [9 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-00763806
Contributeur : Charles Kervrann <>
Soumis le : mardi 11 décembre 2012 - 15:11:33
Dernière modification le : mercredi 7 octobre 2015 - 01:15:04
Document(s) archivé(s) le : mardi 12 mars 2013 - 10:25:29

Fichier

DFortun_ICIP12.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-00763806, version 1

Collections

Citation

Denis Fortun, Charles Kervrann. Semi-local variational optical flow estimation. IEEE. IEEE International Conference on Image Processing, ICIP 2012, Sep 2012, Orlando, FL, United States. 2012. 〈hal-00763806〉

Partager

Métriques

Consultations de la notice

190

Téléchargements de fichiers

116