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.