Statistical motion-based object indexing using optic flow field - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2000

Statistical motion-based object indexing using optic flow field

Résumé

In this paper, we propose an original approach for content-based video indexing and retrieval. It relies on the tracking of entities of interest and the analysis of their apparent motion. To characterize the dynamic information attached to these objects, we consider a probabilistic modeling of the spatio-temporal distribution of the optic flow field computed within the tracked area after canceling the estimated dominant motion due to camera movement. This leads to a general statistical framework for motion-based video classification and retrieval. We have obtained promising results on a set of various real image sequences
Fichier principal
Vignette du fichier
Fablet2000.pdf (481.85 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-02283239 , version 1 (19-12-2022)

Licence

Paternité - Pas d'utilisation commerciale

Identifiants

Citer

Ronan Fablet, Patrick Bouthemy. Statistical motion-based object indexing using optic flow field. ICPR 2000: 15th international conference on pattern recognition, Sep 2000, Barcelone, Spain. pp.287-290, ⟨10.1109/ICPR.2000.902915⟩. ⟨hal-02283239⟩
33 Consultations
11 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More