Dictionary Learning for a Sparse Appearance Model in Visual Tracking

Sylvain Rousseau (1, 2) , Pierre Chainais (2, 1) , Christelle Garnier (1, 3)

1 CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189
2 Centrale Lille
3 Institut TELECOM/TELECOM Lille1

This paper presents a novel approach to visual object tracking based on particle filtering. The tracked object is modelled by a sparse representation provided by dictionary learning. Such an approach permits to describe the target by a model of reduced dimension. The likelihood of a candidate region is built on a similarity measure between the sparse representations of a set of patches (at known positions) in the dictionary learnt from the reference template. Experimental validation is performed on various video sequences and shows the robustness of the proposed approach.

Mots clés: dictionary learning; sparse coding; particle filtering; object tracking

Domaines: Traitement du signal et de l'image [eess.SP]

Sylvain Rousseau, Pierre Chainais, Christelle Garnier. Dictionary Learning for a Sparse Appearance Model in Visual Tracking. ICIP, Sep 2015, Québec City, Canada. ⟨hal-01211263⟩