Static human body postures recognition in video sequences using the belief theory - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2005

Static human body postures recognition in video sequences using the belief theory

Vincent Girondel
  • Fonction : Auteur
  • PersonId : 840802
Laurent Bonnaud
Alice Caplier
Michèle Rombaut

Résumé

This paper presents a system that can automatically recognize four different static human body postures in video sequences. The considered postures are standing, sitting, squatting, and lying. The recognition is based on data fusion using the belief theory. The data come from the persons 2D segmentation and from their face localization. It consists in distance measurements relative to a reference posture (“Da Vinci posture”: standing, arms stretched horizontally). The segmentation is based on an adaptive background removal algorithm. The face localization process uses skin detection based on color information with an adaptive thresholding. The efficiency and the limits of the recognition system are highlighted thanks to the analysis of a great number of results. This system allows real-time processing.
Fichier principal
Vignette du fichier
Girondel_ICIP_2005.pdf (384.79 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-00156548 , version 1 (21-06-2007)

Identifiants

  • HAL Id : hal-00156548 , version 1

Citer

Vincent Girondel, Laurent Bonnaud, Alice Caplier, Michèle Rombaut. Static human body postures recognition in video sequences using the belief theory. IEEE International Conference on Image Processing - ICIP, Sep 2005, Genoa, Italy. pp.45-48. ⟨hal-00156548⟩

Collections

UGA CNRS LIS
287 Consultations
181 Téléchargements

Partager

Gmail Facebook X LinkedIn More