Mixture Densities for Video Objects Recognition

Riad Hammoud 1 Roger Mohr 1
1 MOVI - Modeling, localization, recognition and interpretation in computer vision
GRAVIR - IMAG - Graphisme, Vision et Robotique, Inria Grenoble - Rhône-Alpes, CNRS - Centre National de la Recherche Scientifique : FR71
Abstract : The appearance of non-rigid objects detected and tracked in video streams is highly variable and therefore makes the identification of similar objects very complex. Furthermore, indexing and searching of them represent a very challenging problem in computer vision. This paper presents a framework for object-based matching that increases the robustness of existing feature detectors used for object recognition. The Gaussian mixture densities are used to model intra-shot variations of observed features of tracked objects. This process is achieved by the EM algorithm which separates feature distributions given by a tracked object into homogeneous clusters. We use seven different variants of Gaussian mixtures and the Bayes information criterion to identify the best structure of the data (model and parameters). Experiments are conducted on a video sequence of fifteen different tracked objects and comparison in the performance of the mixture approach and the two key-frame methods is analyzed and reported.
Type de document :
Communication dans un congrès
15th International Conference on Pattern Recognition (ICPR '00), Sep 2000, Barcelona, Spain. IEEE Computer Society, 2, pp.71--75, 2000, 〈http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=906020〉. 〈10.1109/ICPR.2000.906020〉
Liste complète des métadonnées

Littérature citée [10 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00548296
Contributeur : Thoth Team <>
Soumis le : lundi 20 décembre 2010 - 08:42:57
Dernière modification le : jeudi 11 janvier 2018 - 06:20:04
Document(s) archivé(s) le : lundi 21 mars 2011 - 02:52:21

Fichier

HM00a.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

IMAG | INRIA | UGA

Citation

Riad Hammoud, Roger Mohr. Mixture Densities for Video Objects Recognition. 15th International Conference on Pattern Recognition (ICPR '00), Sep 2000, Barcelona, Spain. IEEE Computer Society, 2, pp.71--75, 2000, 〈http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=906020〉. 〈10.1109/ICPR.2000.906020〉. 〈inria-00548296〉

Partager

Métriques

Consultations de la notice

146

Téléchargements de fichiers

113