Soccer video retrival using adaptive time-frequency methods

Abstract : The retrieval of soccer highlights is a suitable technique for video indexation, required by the multimedia database management or by the development of television on demand. For these purposes, it should be interesting to have an automatic annotation of events happening in soccer games. On of the solutions consists in analyzing the audio soundtrack associated with the soccer video and to detect and index the interesting frames. In this paper we use the adaptive time-frequency decomposition of the soundtrack as a feature extraction procedure. This decomposition is based on the Matching Pursuit concept and a dictionary composed by Gabor function. [4] The parameters provided by these transformations constitute the input of the classification stage. The results provided for real soccer video will prove the efficiency of the adaptive time-frequency representation as a feature extraction stage.
Type de document :
Communication dans un congrès
ICASSP 2006, May 2006, Toulouse, France. pp.509-512, 2006
Liste complète des métadonnées

http://hal.univ-brest.fr/hal-00485835
Contributeur : Emanuel Radoi <>
Soumis le : vendredi 21 mai 2010 - 18:26:29
Dernière modification le : mardi 16 janvier 2018 - 15:54:25

Identifiants

  • HAL Id : hal-00485835, version 1

Citation

Marchal Jonathan, Cornel Ioana, Emanuel Radoi, André Quinquis, Krishnan Sridhar. Soccer video retrival using adaptive time-frequency methods. ICASSP 2006, May 2006, Toulouse, France. pp.509-512, 2006. 〈hal-00485835〉

Partager

Métriques

Consultations de la notice

152