Aggregation Methods for Optical Flow Computation

Abstract : Global variational methods for optical flow estimation suffer from an over-smoothing effect due to the use of coarse-to-fine schemes. We propose a semi-local estimation framework designed to integrate and improve any variational method. The idea is to implicitly segment the minimization domain into coherently moving patches. First, semi-local variational estimations are performed in overlapping square patches. Then, a global discrete optimization, based on an aggregation scheme and not prone to over-smoothing, selects for each pixel the optimal motion vector from the ones estimated at the preceding stage. The overall computation framework is simple and can be straightforwardly parallelized. Experiments demonstrate that this novel approach yields better results than the baseline global variational method: more accurate registration is globally achieved and motion discontinuities are sharpened.
Type de document :
Communication dans un congrès
Society for Industrial and Applied Mathematics. SIAM Conference on Imaging Science, May 2012, Philadelphia, United States. 2012
Liste complète des métadonnées

https://hal.inria.fr/hal-00763845
Contributeur : Charles Kervrann <>
Soumis le : mardi 11 décembre 2012 - 16:08:57
Dernière modification le : mercredi 11 avril 2018 - 01:54:04

Identifiants

  • HAL Id : hal-00763845, version 1

Collections

Citation

Charles Kervrann, Denis Fortun, Patrick Bouthemy. Aggregation Methods for Optical Flow Computation. Society for Industrial and Applied Mathematics. SIAM Conference on Imaging Science, May 2012, Philadelphia, United States. 2012. 〈hal-00763845〉

Partager

Métriques

Consultations de la notice

148