Scalable spatio-temporal video indexing using sparse multiscale patches - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2009

Scalable spatio-temporal video indexing using sparse multiscale patches

Résumé

In this paper we address the problem of scalable video indexing. We propose a new framework combining sparse spatial multiscale patches and Group of Pictures (GoP) motion patches. The distributions of these sets of patches are compared via the Kullback-Leibler divergence estimated in a non-parametric framework using a k-th Nearest Neighbor (kNN) estimator. We evaluated this similarity measure on selected videos from the ICOS-HD ANR project, probing in particular its robustness to resampling and compression and thus showing its scalability on heterogeneous networks.
Fichier principal
Vignette du fichier
piro_cbmi09_preprint.pdf (436.62 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00417411 , version 1 (15-09-2009)

Identifiants

Citer

Paolo Piro, Sandrine Anthoine, Eric Debreuve, Michel Barlaud. Scalable spatio-temporal video indexing using sparse multiscale patches. CBMI '09, Jun 2009, Chania, Greece. pp.95-100, ⟨10.1109/CBMI.2009.48⟩. ⟨hal-00417411⟩
88 Consultations
113 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More