In this paper we present a semantic video indexing algorithm based on finite-state machines and low-level motion indices extracted from the MPEG compressed bit-stream. The problem of semantic video indexing is actually of great interest due to the wide diffusion of large video databases. In literature we can find many video indexing algorithms, based on various types of low-level features, but the problem of semantic indexing is less studied and surely it is a great challenging one. The proposed algorithm is an example of solution to the problem of finding a semantic relevant event (e.g., scoring of a goal in a soccer game) in case of specific categories of audio-visual programmes. The simulation results show that the proposed algorithm can effectively detect the presence of goals and other relevant events in sport programs.

EVENT RECOGNITION IN SPORT PROGRAMS USING LOW-LEVEL MOTION INDICES

LEONARDI, Riccardo;MIGLIORATI, Pierangelo
2001-01-01

Abstract

In this paper we present a semantic video indexing algorithm based on finite-state machines and low-level motion indices extracted from the MPEG compressed bit-stream. The problem of semantic video indexing is actually of great interest due to the wide diffusion of large video databases. In literature we can find many video indexing algorithms, based on various types of low-level features, but the problem of semantic indexing is less studied and surely it is a great challenging one. The proposed algorithm is an example of solution to the problem of finding a semantic relevant event (e.g., scoring of a goal in a soccer game) in case of specific categories of audio-visual programmes. The simulation results show that the proposed algorithm can effectively detect the presence of goals and other relevant events in sport programs.
2001
0769511988
File in questo prodotto:
File Dimensione Formato  
BLM_ICME-2001_full-text.pdf

solo utenti autorizzati

Descrizione: BLM_ICME-2001_full-text
Tipologia: Full Text
Licenza: NON PUBBLICO - Accesso privato/ristretto
Dimensione 50.81 kB
Formato Adobe PDF
50.81 kB Adobe PDF   Visualizza/Apri   Richiedi una copia
BLM_ICME-2001_pre-print.pdf

accesso aperto

Descrizione: BLM_ICME-2001_pre-print
Tipologia: Documento in Pre-print
Licenza: PUBBLICO - Creative Commons 3.6
Dimensione 55.2 kB
Formato Adobe PDF
55.2 kB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11379/10114
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 17
  • ???jsp.display-item.citation.isi??? ND
social impact