Occlusion and Motion Reasoning for Long-term Tracking

Yang Hua 1, 2 Karteek Alahari 2 Cordelia Schmid 2
2 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : Object tracking is a reoccurring problem in computer vision. Tracking-by-detection approaches, in particular Struck (Hare et al., 2011), have shown to be competitive in recent evaluations. However, such approaches fail in the presence of long-term occlusions as well as severe viewpoint changes of the object. In this paper we propose a principled way to combine occlusion and motion reasoning with a tracking-by-detection approach. Occlusion and motion reasoning is based on state-of-the-art long-term trajectories which are labeled as object or background tracks with an energy-based formulation. The overlap between labeled tracks and detected regions allows to identify occlusions. The motion changes of the object between consecutive frames can be estimated robustly from the geometric relation between object trajectories. If this geometric change is significant, an additional detector is trained. Experimental results show that our tracker obtains state-of-the-art results and handles occlusion and viewpoints changes better than competing tracking methods.
Type de document :
Communication dans un congrès
David Fleet; Tomas Pajdla; Bernt Schiele; Tinne Tuytelaars. ECCV - European Conference on Computer Vision, Sep 2014, Zurich, Switzerland. Springer, 8694 (Part VI), pp.172-187, 2014, Lecture Notes in Computer Science. 〈10.1007/978-3-319-10599-4_12〉
Liste complète des métadonnées

Littérature citée [48 références]  Voir  Masquer  Télécharger


https://hal.inria.fr/hal-01020149
Contributeur : Karteek Alahari <>
Soumis le : lundi 7 juillet 2014 - 18:22:30
Dernière modification le : vendredi 11 août 2017 - 13:21:05
Document(s) archivé(s) le : mardi 7 octobre 2014 - 17:00:07

Fichiers

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

Identifiants

Collections

Citation

Yang Hua, Karteek Alahari, Cordelia Schmid. Occlusion and Motion Reasoning for Long-term Tracking. David Fleet; Tomas Pajdla; Bernt Schiele; Tinne Tuytelaars. ECCV - European Conference on Computer Vision, Sep 2014, Zurich, Switzerland. Springer, 8694 (Part VI), pp.172-187, 2014, Lecture Notes in Computer Science. 〈10.1007/978-3-319-10599-4_12〉. 〈hal-01020149〉

Partager

Métriques

Consultations de
la notice

1466

Téléchargements du document

8502