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.
Document type :
Conference papers
Liste complète des métadonnées

Cited literature [48 references]  Display  Hide  Download


https://hal.inria.fr/hal-01020149
Contributor : Karteek Alahari <>
Submitted on : Monday, July 7, 2014 - 6:22:30 PM
Last modification on : Monday, December 17, 2018 - 11:22:02 AM
Document(s) archivé(s) le : Tuesday, October 7, 2014 - 5:00:07 PM

Files

tracking.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Yang Hua, Karteek Alahari, Cordelia Schmid. Occlusion and Motion Reasoning for Long-term Tracking. ECCV - European Conference on Computer Vision, Sep 2014, Zurich, Switzerland. pp.172-187, ⟨10.1007/978-3-319-10599-4_12⟩. ⟨hal-01020149⟩

Share

Metrics

Record views

1765

Files downloads

9606