A novel object position coding for multi-object tracking using sparse representation - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue International Journal of Image, Graphics and Signal Processing Année : 2015

A novel object position coding for multi-object tracking using sparse representation

Résumé

Multi-object tracking is a challenging task, especially when the persistence of the identity of objects is required. In this paper, we propose an approach based on the detection and the recognition. A classification system based on sparse representation is used to solve the recognition problem. Our main contribution is the representation of each object with a descriptor derived from a novel representation of its 2-D position, and a histogram-based feature, improved by using the silhouette of this object. Experimental results show that the approach proposed for describing moving objects, combined with the classification system based on sparse representation provides a robust multi-object tracker, in videos involving occlusions and illumination changes.
Fichier non déposé

Dates et versions

hal-01153263 , version 1 (19-05-2015)

Identifiants

  • HAL Id : hal-01153263 , version 1

Citer

Mohamed Elbahri, Kidiyo Kpalma, Nasreddine Taleb, Miloud Chikr El-Mezouar. A novel object position coding for multi-object tracking using sparse representation. International Journal of Image, Graphics and Signal Processing , 2015, 11 p. ⟨hal-01153263⟩
9193 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More