Towards event detection in an audio-based sensor network

Abstract

In this paper, we describe an experiment where we gathered audio information from a series of conventional wired microphones installed in a typical university setting. We also obtained visual information from cameras located in the same area. We set out to see if audio analysis could be used to assist our existing visual event detection system, and to note any improvements. We were not concerned with identifying or classifying what was detected in the audio. Our aim was to keep audio processing to a minimum, as this would enable wireless sensor networks to be used in the future. We present the results of analysis of audio information based on the mean of the volume, the zero-crossing rate, and the frequency. We found that detecting events based on their volume returned satisfactory results.