Change detection in audio data streams has become an efficient way for online notification of events. An interesting application is audio surveillance, including road traffic monitoring and online car crash alarms. However, in the particular case of crash alarms, most of the collected sounds are background noises, with various sub-classes, such as talking pedestrians, engine sounds, horn blowing, etc., whereas those corresponding to the event of interest are much less abundant. Therefore, it is difficult to apply classical tools of classification or clustering to detect crash sounds as a particular class or as outliers. To tackle this problem, we propose an ensemble classifier based on one-class SVM in order to separate outliers from normal data first, and deep neural networks to classify event-related data. Finally the results of both outlier detection and classification outputs are aggregated in such a way that outliers are considered as a novel class, a priori unknown by the DNN classifier. The application of this method on an audio traffic monitoring database confirms its ability to detect, (a) non-events (background noise), nonhazardous and hazardous event, and (b) non-accidents and accidents, from a stream of audio data.

Detection of Hazardous Road Events from Audio Streams: An Ensemble Outlier Detection Approach

Rovetta S.;Mnasri Z.;Masulli F.
2020-01-01

Abstract

Change detection in audio data streams has become an efficient way for online notification of events. An interesting application is audio surveillance, including road traffic monitoring and online car crash alarms. However, in the particular case of crash alarms, most of the collected sounds are background noises, with various sub-classes, such as talking pedestrians, engine sounds, horn blowing, etc., whereas those corresponding to the event of interest are much less abundant. Therefore, it is difficult to apply classical tools of classification or clustering to detect crash sounds as a particular class or as outliers. To tackle this problem, we propose an ensemble classifier based on one-class SVM in order to separate outliers from normal data first, and deep neural networks to classify event-related data. Finally the results of both outlier detection and classification outputs are aggregated in such a way that outliers are considered as a novel class, a priori unknown by the DNN classifier. The application of this method on an audio traffic monitoring database confirms its ability to detect, (a) non-events (background noise), nonhazardous and hazardous event, and (b) non-accidents and accidents, from a stream of audio data.
File in questo prodotto:
File Dimensione Formato  
09122704.pdf

accesso chiuso

Descrizione: Contributo in atti di convegno
Tipologia: Documento in versione editoriale
Dimensione 263.66 kB
Formato Adobe PDF
263.66 kB Adobe PDF   Visualizza/Apri   Richiedi una copia

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/11567/1036615
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 16
  • ???jsp.display-item.citation.isi??? 8
social impact