Title :
One-Class SVM Based Approach for Detecting Anomalous Audio Events
Author :
Aurino, Francesco ; Folla, Mariano ; Gargiulo, Francesco ; Moscato, Vincenzo ; Picariello, Antonio ; Sansone, Carlo
Abstract :
The last generation automated security and surveillance systems call for new and advanced capabilities to automatically and reliably recognize suspicious events or activities in the monitored environments on the base of a real-time and combined analysis of different multimedia streams. In this paper we focus our attention on the analysis of audio signal and present a method based on one-class Support Vector Machine (1-SVM) classifiers. Such an approach is able to support the recognition of different kinds of burst-like anomalies (i.e. gun-shots, broken glasses and screams), on the base of their time and frequency domain characterization. Several experiments have been carried out, showing the potentiality of our method with respect to other approaches proposed in the recent literature.
Keywords :
audio signal processing; security; signal classification; signal detection; support vector machines; anomalous audio event detection; audio signal analysis; automated security; broken glasses detection; burst like anomalies; gun shot detection; multimedia stream; one class SVM; scream detection; support vector machine classifier; surveillance systems; Discrete wavelet transforms; Feature extraction; Glass; Mel frequency cepstral coefficient; Reliability; Support vector machines; Audio Events Detection; One-class SVM; Survelliance Systems;
Conference_Titel :
Intelligent Networking and Collaborative Systems (INCoS), 2014 International Conference on
Print_ISBN :
978-1-4799-6386-7
DOI :
10.1109/INCoS.2014.59
