Bayesian inference of models and hyper-parameters for robust optic-flow estimation

Abstract : Selecting optimal models and hyper-parameters is crucial for accurate optic-flow estimation. This paper provides a solution to the problem in a generic Bayesian framework. The method is based on a conditional model linking the image intensity function, the unknown velocity field, hyper-parameters and the prior and likelihood motion models. Inference is performed on each of the three-level of this so-defined hierarchical model by maximization of marginalized \textit{a posteriori} probability distribution functions. In particular, the first level is used to achieve motion estimation in a classical a posteriori scheme. By marginalizing out the motion variable, the second level enables to infer regularization coefficients and hyper-parameters of non-Gaussian M-estimators commonly used in robust statistics. The last level of the hierarchy is used for selection of the likelihood and prior motion models conditioned to the image data. The method is evaluated on image sequences of fluid flows and from the ''Middlebury" database. Experiments prove that applying the proposed inference strategy yields better results than manually tuning smoothing parameters or discontinuity preserving cost functions of the state-of-the-art methods.
Type de document :
Article dans une revue
IEEE Transactions on Image Processing, Institute of Electrical and Electronics Engineers, 2012, 21 (4), pp.1437-1451
Liste complète des métadonnées

Littérature citée [46 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-00670375
Contributeur : Patrick Héas <>
Soumis le : mercredi 15 février 2012 - 11:54:48
Dernière modification le : mercredi 29 novembre 2017 - 15:59:35
Document(s) archivé(s) le : mercredi 14 décembre 2016 - 06:38:40

Fichier

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

Identifiants

  • HAL Id : hal-00670375, version 1

Collections

Citation

Patrick Héas, Cédric Herzet, Etienne Memin. Bayesian inference of models and hyper-parameters for robust optic-flow estimation. IEEE Transactions on Image Processing, Institute of Electrical and Electronics Engineers, 2012, 21 (4), pp.1437-1451. 〈hal-00670375〉

Partager

Métriques

Consultations de la notice

437

Téléchargements de fichiers

132