MULTI-TARGET TRACKING BY DISCRIMINATIVE ANALYSIS ON RIEMANNIAN MANIFOLD

Abstract : This paper addresses the problem of multi-target tracking in crowded scenes from a single camera. We propose an algorithm for learning discriminative appearance models for different targets. These appearance models are based on covariance descriptor extracted from tracklets given by a short-term tracking algorithm. Short-term tracking relies on object descriptors tuned by a controller which copes with context variation over time. We link tracklets by using discriminative analysis on a Riemannian manifold. Our evaluation shows that by applying this discriminative analysis, we can reduce false alarms and identity switches, not only for tracking in a single camera but also for matching object appearances between non-overlapping cameras.
Type de document :
Communication dans un congrès
ICIP - International Conference on Image Processing - 2012, Sep 2012, Orlando, United States. IEEE Computer Society, 1, pp.1-4, 2012, People re-identification and tracking from multiple cameras
Liste complète des métadonnées

Littérature citée [12 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-00703633
Contributeur : Slawomir Bak <>
Soumis le : jeudi 7 juin 2012 - 13:52:57
Dernière modification le : jeudi 11 janvier 2018 - 16:21:50
Document(s) archivé(s) le : lundi 10 septembre 2012 - 11:25:36

Fichier

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

Identifiants

  • HAL Id : hal-00703633, version 1

Collections

Citation

Slawomir Bak, Duc Phu Chau, Julien Badie, Etienne Corvee, François Bremond, et al.. MULTI-TARGET TRACKING BY DISCRIMINATIVE ANALYSIS ON RIEMANNIAN MANIFOLD. ICIP - International Conference on Image Processing - 2012, Sep 2012, Orlando, United States. IEEE Computer Society, 1, pp.1-4, 2012, People re-identification and tracking from multiple cameras. 〈hal-00703633〉

Partager

Métriques

Consultations de la notice

357

Téléchargements de fichiers

264