Multi-Observations Newscast EM for Distributed Appearance Based Tracking - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2007

Multi-Observations Newscast EM for Distributed Appearance Based Tracking

Ben Kröse
  • Fonction : Auteur
  • PersonId : 853721

Résumé

Visual surveillance in wide areas (e.g. airports) relies on cameras that observe non-overlapping scenes. Multi-person tracking requires re-identification of people, when they leave one field of view and later enter another. For this we use appearance cues. Under the assumption that all observations of a single person are Gaussian distributed, the observation model in our approach consists of a Mixture of Gaussians: one component for each person. In this paper we propose a distributed approach for learning this MoG, where every camera learns from its own observations and the communication with other cameras. We propose a modified version of the recently developed Newscast EM algorithm for this. We test our alogithm on artificial generated data and on a collection of real-world observations gathered by a system of cameras in an office building.
Fichier principal
Vignette du fichier
BNAIC2007.pdf (1.65 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

inria-00548677 , version 1 (20-12-2010)

Identifiants

  • HAL Id : inria-00548677 , version 1

Citer

Thomas Mensink, Wojciech Zajdel, Ben Kröse. Multi-Observations Newscast EM for Distributed Appearance Based Tracking. 19th Belgian-Dutch Conference on Artificial Intelligence (BNAIC '07), Nov 2007, Utrecht, Netherlands. ⟨inria-00548677⟩
50 Consultations
42 Téléchargements

Partager

Gmail Facebook X LinkedIn More