A Probabilistic Framework Based on KDE-GMM Hybrid Model for Moving Object Segmentation in Dynamic Scenes

Abstract : In real scenes, dynamic background and moving cast shadow always make accurate moving object detection difficult. In this paper, a probabilistic framework for moving object segmentation in dynamic scenes is proposed. Under this framework, we deal with foreground detection and shadow removal simultaneously by constructing probability density functions (PDFs) of moving objects and non-moving objects. Here, these PDFs are constructed based on KDEGMMhybrid model (KGHM) which has advantages of KDE and GMM. This KGHM models the spatial dependencies of neighboring pixel colors to deal with highly dynamic scenes. Moreover, in this framework, tracking information is used to refine the PDF of moving objects. Experimental results demonstrate the effectiveness of our method.
Type de document :
Communication dans un congrès
The Eighth International Workshop on Visual Surveillance - VS2008, Oct 2008, Marseille, France. 2008
Liste complète des métadonnées

Littérature citée [15 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00325761
Contributeur : Peter Sturm <>
Soumis le : mardi 30 septembre 2008 - 11:16:32
Dernière modification le : mardi 30 septembre 2008 - 11:58:21
Document(s) archivé(s) le : lundi 8 octobre 2012 - 13:42:08

Fichier

VS2008-Poster-g.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : inria-00325761, version 1

Collections

Citation

Zhou Liu, Wei Chen, Kaiqi Huang, Tieniu Tan. A Probabilistic Framework Based on KDE-GMM Hybrid Model for Moving Object Segmentation in Dynamic Scenes. The Eighth International Workshop on Visual Surveillance - VS2008, Oct 2008, Marseille, France. 2008. 〈inria-00325761〉

Partager

Métriques

Consultations de la notice

158

Téléchargements de fichiers

215