Simultaneous learning of motion and appearance

Abstract : A new learning method for motion estimation of objects with significantly varying appearance is proposed. Varying object appearance is represented by a low dimensional space of appearance parameters. The appearance mapping and motion estimation method are optimized simultaneously. Appearance parameters are estimated by unsupervised learning. The method is experimentally verified by a tracking application on sequences which exhibit strong variable illumination, non-rigid deformations and self-occlusions.
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 [12 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00326712
Contributeur : Peter Sturm <>
Soumis le : dimanche 5 octobre 2008 - 12:23:12
Dernière modification le : lundi 6 octobre 2008 - 09:20:34
Document(s) archivé(s) le : lundi 8 octobre 2012 - 13:56:12

Fichier

mlvma08_submission_28.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : inria-00326712, version 1

Collections

Citation

Karel Zimmermann, Tomas Svoboda, Jiri Matas. Simultaneous learning of motion and appearance. The 1st International Workshop on Machine Learning for Vision-based Motion Analysis - MLVMA'08, Oct 2008, Marseille, France. 2008. 〈inria-00326712〉

Partager

Métriques

Consultations de la notice

67

Téléchargements de fichiers

104