Object Based Optical Flow Estimation with an Affine Prior Model

Résumé : We investigate an original method to compute the optical flow on image sequences. Instead of assuming invariance principles applied to individual pixels, this method considers objects as a whole, by constraining their total intensity during their motion. A variational implementation of this method has already been studied. We propose here a parametric implementation of this method using an affine prior model. A combined method between the variational method and the affine method is proposed in order to capture both affine components and non-affine components. Results on meteorological infrared data are presented
Type de document :
Communication dans un congrès
IAPR. Proceedings of the International Conference on Pattern Recognition (ICPR), Sep 2000, Barcelona, Spain. IEEE Computer Society, 3, pp.1048-1051, 2000, 〈10.1109/ICPR.2000.903725〉
Liste complète des métadonnées

https://hal.inria.fr/inria-00532745
Contributeur : Brigitte Briot <>
Soumis le : jeudi 4 novembre 2010 - 13:42:55
Dernière modification le : mardi 19 avril 2016 - 12:08:11

Identifiants

Collections

Citation

Dominique Béréziat, Isabelle Herlin. Object Based Optical Flow Estimation with an Affine Prior Model. IAPR. Proceedings of the International Conference on Pattern Recognition (ICPR), Sep 2000, Barcelona, Spain. IEEE Computer Society, 3, pp.1048-1051, 2000, 〈10.1109/ICPR.2000.903725〉. 〈inria-00532745〉

Partager

Métriques

Consultations de la notice

68