A tensor based on optical flow for global description of motion in videos

Abstract : Motion is one of the main characteristics that describe the semantic information of videos. In this work, a global video descriptor based on orientation tensors is proposed. This descriptor is obtained by combining polynomial coefficients calculated for each image in a video. The coefficients are found through the projection of the optical flow on Legendre polyno- mials, reducing the dimension of per frame motion estimations. The sequence of coefficients are then combined using orientation tensors. The global tensor descriptor created is evaluated by a classification of the KTH video database with a SVM classifier.
Type de document :
Communication dans un congrès
SIBGRAPI 2012, Aug 2012, Ouro Preto, Brazil. pp.4, 2012
Liste complète des métadonnées


https://hal.archives-ouvertes.fr/hal-00753159
Contributeur : Philippe-Henri Gosselin <>
Soumis le : samedi 17 novembre 2012 - 19:15:07
Dernière modification le : mardi 28 octobre 2014 - 18:41:56
Document(s) archivé(s) le : lundi 18 février 2013 - 03:42:44

Fichier

mota12sibgrapi.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-00753159, version 1

Collections

Citation

Virginia Fernandes Mota, Eder de Almeida Perez, Marcelo Bernardes Vieira, Silva Maciel Luiz Maurílio Da, Frédéric Precioso, et al.. A tensor based on optical flow for global description of motion in videos. SIBGRAPI 2012, Aug 2012, Ouro Preto, Brazil. pp.4, 2012. <hal-00753159>

Partager

Métriques

Consultations de
la notice

313

Téléchargements du document

219