FUSION OF MOTION SEGMENTATION WITH ONLINE ADAPTIVE NEURAL CLASSIFIER FOR ROBUST TRACKING

Abstract : This paper presents a method to fuse the information from motion segmentation with online adaptive neural classifier for robust object tracking. The motion segmentation with object classification identify new objects present in the video sequence. This information is used to initialize the online adaptive neural classifier which is learned to differentiate the object from its local background. The neural classifier can adapt to illumination variations and changes in appearance. Initialized objects are tracked in following frames using the fusion of their neural classifiers with the feedback from the motion segmentation. Fusion is used to avoid drifting problems due to similar appearance in the local background region. We demonstrate the approach in several experiments using benchmark video sequences with different level of complexity.
Type de document :
Communication dans un congrès
Int. Joint Conf. on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISAPP), Feb 2009, Lisbon, Portugal. 2009
Liste complète des métadonnées

Littérature citée [15 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00496120
Contributeur : Slawomir Bak <>
Soumis le : vendredi 16 juillet 2010 - 12:13:10
Dernière modification le : mardi 24 juillet 2018 - 15:48:06
Document(s) archivé(s) le : jeudi 1 décembre 2016 - 16:39:38

Fichier

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

Identifiants

  • HAL Id : inria-00496120, version 2

Collections

Citation

Slawomir Bak, Sundaram Suresh, François Bremond, Monique Thonnat. FUSION OF MOTION SEGMENTATION WITH ONLINE ADAPTIVE NEURAL CLASSIFIER FOR ROBUST TRACKING. Int. Joint Conf. on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISAPP), Feb 2009, Lisbon, Portugal. 2009. 〈inria-00496120v2〉

Partager

Métriques

Consultations de la notice

263

Téléchargements de fichiers

167