The present study presents a practical methodology for automatic space monitoring based solely on the perceived acoustic information. We consider the case where atypical situations such as screams, explosions and gunshots take place in a metro station environment. Our approach is based on a two stage recognition schema, each one exploiting HMMs for approximating the density function of the corresponding sound class. The main objective is to detect abnormal events that take place in a noisy environment. A thorough evaluation procedure is carried out under different SNR conditions and we report high detection rates with respect to false alarm and miss probabilities rates.
On acoustic surveillance of hazardous situations / S. Ntalampiras, I. Potamitis, N. Fakotakis (PROCEEDINGS OF THE ... IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING). - In: 2009 IEEE International Conference on Acoustics, Speech and Signal Processing[s.l] : IEEE, 2009. - ISBN 9781424423545. - pp. 165-168 (( convegno ICASSP tenutosi a Taipei nel 2009.
On acoustic surveillance of hazardous situations
S. Ntalampiras;
2009
Abstract
The present study presents a practical methodology for automatic space monitoring based solely on the perceived acoustic information. We consider the case where atypical situations such as screams, explosions and gunshots take place in a metro station environment. Our approach is based on a two stage recognition schema, each one exploiting HMMs for approximating the density function of the corresponding sound class. The main objective is to detect abnormal events that take place in a noisy environment. A thorough evaluation procedure is carried out under different SNR conditions and we report high detection rates with respect to false alarm and miss probabilities rates.File | Dimensione | Formato | |
---|---|---|---|
04959546.pdf
accesso riservato
Tipologia:
Publisher's version/PDF
Dimensione
701.52 kB
Formato
Adobe PDF
|
701.52 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.