Adaptive Feature Selection for Object Tracking with Particle Filter

Darshan Venkatrayappa; Désiré Sidibé; Fabrice Meriaudeau; Philippe Montesinos

Adaptive Feature Selection for Object Tracking with Particle Filter

Darshan Venkatrayappa ¹ Désiré Sidibé ² Fabrice Meriaudeau ² Philippe Montesinos ¹

1 LGI2P - Laboratoire de Génie Informatique et Ingénierie de Production

2 Le2i - Laboratoire Electronique, Informatique et Image [UMR6303]

Abstract : Object tracking is an important topic in the field of computer vision. Commonly used color-based trackers are based on a fixed set of color features such as RGB or HSV and, as a result, fail to adapt to changing illumination conditions and background clutter. These drawbacks can be overcome to an extent by using an adaptive framework which selects for each frame of a sequence the features that best discriminate the object from the background. In this paper, we use such an adaptive feature selection method embedded into a particle filter mechanism and show that our tracking method is robust to lighting changes and background distractions. Different experiments also show that the proposed method outperform other approaches.

Keywords : Tracking Particle filter Mean-shift filter Feature selection

Type de document :

Communication dans un congrès

Domaine :

Informatique [cs] / Vision par ordinateur et reconnaissance de formes [cs.CV]

Liste complète des métadonnées

Littérature citée [14 références] Voir Masquer Télécharger

https://hal-univ-bourgogne.archives-ouvertes.fr/hal-01145635
Contributeur : Désiré Sidibé <>
Soumis le : vendredi 24 avril 2015 - 18:28:06
Dernière modification le : vendredi 26 avril 2019 - 14:44:03
Document(s) archivé(s) le : mercredi 19 avril 2017 - 06:02:18

2014_darshan_iciar.pdf

Fichiers produits par l'(les) auteur(s)

Adaptive Feature Selection for Object Tracking with Particle Filter

Fichier

Identifiants

Collections

Citation

Exporter

Métriques

333

352

Contact

Adaptive Feature Selection for Object Tracking with Particle Filter

Fichier

Identifiants

Collections

Citation

Exporter

Partager

Métriques

333

352

Contact