Learning Bayesian Tracking for Motion Estimation

Abstract : A common computer vision problem is to track a physical object through an image sequence. In general, the observations that are made in a single image determine the actual state only partially and information from several views has to be merged. A principled and wellestablished way of fusing information is the Bayesian framework. In this paper, we propose a novel way of doing Bayesian tracking called channelbased tracking. The method is related to grid-based tracking methods, but differs in two aspects: The applied sampling functions, i.e., the bins, are smooth and overlapping and the system and measurement models are learned from a training set. The results from the channel-based tracker are compared to state-of-the-art tracking methods based on particle filters, using a standard dataset from the literature. A simple computer vision experiment is shown to illustrate possible applications.
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 [22 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00321934
Contributeur : Peter Sturm <>
Soumis le : mardi 16 septembre 2008 - 11:19:12
Dernière modification le : mardi 16 septembre 2008 - 11:20:11
Document(s) archivé(s) le : vendredi 4 juin 2010 - 11:25:38

Fichier

mlvma08_submission_3.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : inria-00321934, version 1

Collections

Citation

Michael Felsberg, Fredrik Larsson. Learning Bayesian Tracking for Motion Estimation. The 1st International Workshop on Machine Learning for Vision-based Motion Analysis - MLVMA'08, Oct 2008, Marseille, France. 2008. 〈inria-00321934〉

Partager

Métriques

Consultations de la notice

56

Téléchargements de fichiers

109