Analysis of Skeletal Shape Trajectories for Person Re-Identification

Amani Elaoud (1) , Walid Barhoumi (2) , Hassen Drira (3) , Ezzeddine Zagrouba (1)

1 UTM - Université de Tunis El Manar
2 UCAR - Université de Carthage (Tunisie)
3 CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189

In this paper, we are interested in people re-identification using skeleton information provided by a consumer RGB-D sensor. We perform the modelling and the analysis of human motion by focusing on 3D human joints given by skeletons. In fact, the motion dynamic is modeled by projecting skeleton information on Grassmann manifold. Moreover, in order to define the identity of a test trajectory, we compare it against a labeled trajectory database while using an unsupervised similarity assessment procedure. Indeed, the main contribution of this work resides in the introduced distance that combines temporal information as well as global and local geometrical ones. Realized experiments on standard datasets prove that the proposed method performs accurately even though it does not assume any prior knowledge.

Mots clés: Skeleton information; Similarity evaluation; Person re-identification; RGB-D sensors; Grassmann manifold

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]

Amani Elaoud, Walid Barhoumi, Hassen Drira, Ezzeddine Zagrouba. Analysis of Skeletal Shape Trajectories for Person Re-Identification. ACIVS 2017 - 18th International Conference on Advanced Concepts for Intelligent Vision Systems, Sep 2017, Anvers, Belgium. pp.138-149, ⟨10.1007/978-3-319-70353-4_12⟩. ⟨hal-01703945⟩