Abnormal events detection using unsupervised One-Class SVM - Application to audio surveillance and evaluation

This paper proposes an unsupervised method for real time detection of abnormal events in the context of audio surveillance. Based on training a One-Class Support Vector Machine (OC-SVM) to model the distribution of the normality (ambience), we propose to construct sets of decision functions. This mo...

Full description

Saved in:
Bibliographic Details
Published in2011 8th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) pp. 124 - 129
Main Authors Lecomte, S., Lengelle, R., Richard, C., Capman, F., Ravera, B.
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.08.2011
Subjects
Detectors
Kernel
Signal to noise ratio
Support vector machines
Surveillance
Training
Online AccessGet full text

Cover

More Information
Summary:This paper proposes an unsupervised method for real time detection of abnormal events in the context of audio surveillance. Based on training a One-Class Support Vector Machine (OC-SVM) to model the distribution of the normality (ambience), we propose to construct sets of decision functions. This modification allows controlling the trade-off between false-alarm and miss probabilities without modifying the trained OC-SVM that best capture the ambience boundaries, or its hyperparameters. Then we present an adaptive online scheme of temporal integration of the decision function output in order to increase performance and robustness. We also introduce a framework to generate databases based on real signals for the evaluation of audio surveillance systems. Finally, we present the performances obtained on the generated database.
ISBN:9781457708442
1457708442
DOI:10.1109/AVSS.2011.6027306