The high availability of video streams is making necessary mechanisms for indexing such contents in the Web world. In this paper we focus on news programs and we propose a mechanism that integrates low and high level video features to provide a high level semantic description. A color/lumi- nance analysis is coupled with audio analysis to provide a better identification of all the video segments that compose the video stream. Each video segment is subject to speech detection and is described through MPEG7 so that the resulting metadata description can be used to index the video stream. An experimental evaluation shows the benefits of integrating audio and video analysis.
An Audio/Video Analysis Mechanism for Web Indexing / Furini, Marco; M., Aragone. - STAMPA. - (2006), pp. 1025-1026. (Intervento presentato al convegno 15th International Conference on World Wide Web tenutosi a Edinburgh, Scotland nel 23-26 Maggio 2006) [10.1145/1135777.1135997].
An Audio/Video Analysis Mechanism for Web Indexing
FURINI, Marco;
2006
Abstract
The high availability of video streams is making necessary mechanisms for indexing such contents in the Web world. In this paper we focus on news programs and we propose a mechanism that integrates low and high level video features to provide a high level semantic description. A color/lumi- nance analysis is coupled with audio analysis to provide a better identification of all the video segments that compose the video stream. Each video segment is subject to speech detection and is described through MPEG7 so that the resulting metadata description can be used to index the video stream. An experimental evaluation shows the benefits of integrating audio and video analysis.
| File | Dimensione | Formato | |
|---|---|---|---|
|
p52.pdf
Accesso riservato
Descrizione: Articolo principale, versione dopo referaggio.
Tipologia:
AAM - Versione dell'autore revisionata e accettata per la pubblicazione
Dimensione
163.24 kB
Formato
Adobe PDF
|
163.24 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
Pubblicazioni consigliate
I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris
