Online Parameter Tuning for Object Tracking Algorithms

Abstract : Object tracking quality usually depends on video scene conditions (e.g. illumination, density of objects, object occlusion level). In order to overcome this limitation, this article presents a new control approach to adapt the object tracking process to the scene condition variations. More precisely, this approach learns how to tune the tracker parameters to cope with the tracking context variations. The tracking context, or context, of a video sequence is defined as a set of six features: density ofmobile objects, their occlusion level, their contrastwith regard to the surrounding background, their contrast variance, their 2D area and their 2D area variance. In an offline phase, training video sequences are classified by clustering their contextual features. Each context cluster is then associated to satisfactory tracking parameters. In the online control phase, once a context change is detected, the tracking parameters are tuned using the learned values. The approach has been experimentedwith three different tracking algorithms and on long, complex video datasets. This article brings two significant contributions: (1) a classification method of video sequences to learn offline tracking parameters and (2) a newmethod to tune online tracking parameters using tracking context.
Type de document :
Article dans une revue
Image and Vision Computing, Elsevier, 2014, 32 (4), pp.287-302
Liste complète des métadonnées

Littérature citée [36 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-00976594
Contributeur : Duc Phu Chau <>
Soumis le : jeudi 10 avril 2014 - 10:24:33
Dernière modification le : mardi 24 juillet 2018 - 15:48:05
Document(s) archivé(s) le : jeudi 10 juillet 2014 - 11:06:29

Fichier

phu_imavis12.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-00976594, version 1

Collections

Citation

Duc Phu Chau, Monique Thonnat, François Bremond, Etienne Corvee. Online Parameter Tuning for Object Tracking Algorithms. Image and Vision Computing, Elsevier, 2014, 32 (4), pp.287-302. 〈hal-00976594〉

Partager

Métriques

Consultations de la notice

411

Téléchargements de fichiers

282