Fast Repetition Detection in TV Streams using Repetition Patterns - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2013

Fast Repetition Detection in TV Streams using Repetition Patterns

Résumé

This paper presents a new method to detect video repetitions in a TV stream. This method aims at reducing the number of image descriptors that have to be computed. First, shot durations are used as hash keys to propose a first set of potential repetitions. Second, a statistical test and visual descriptors are used to verify and complete these first guesses in order to improve the results by reducing the number of false detections and by retrieving the maximal length of the repeated segments. The method is tested in the context of a TV structuring application using one month of continuous TV stream.
Fichier principal
Vignette du fichier
carton_gros.pdf (214.54 Ko) Télécharger le fichier
Vignette du fichier
histogram_shotduration.png (10.27 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Format : Figure, Image
Loading...

Dates et versions

hal-00844099 , version 1 (12-07-2013)

Identifiants

  • HAL Id : hal-00844099 , version 1

Citer

Cérès Carton, Patrick Gros. Fast Repetition Detection in TV Streams using Repetition Patterns. Content-Based Multimedia Indexing, Jun 2013, Veszprem, Hungary. ⟨hal-00844099⟩
501 Consultations
178 Téléchargements

Partager

Gmail Facebook X LinkedIn More