Abnormal sound analytical surveillance system using microcontroller

Abstract

Analytical surveillance can perform the surveillance tasks much more efficient comparing to operator manual monitoring. This had made it getting increased market's interest in recent years. Commonly, closed circuit television (CCTV) is used for security surveillance. However, CCTVs are purely vision output. These silent videos may not provide complete picture of the happening. Sound detection is incorporate into vision surveillance for enhancement. Sound detection is able to detect abnormal sound although happen at camera blind spots or due to intentional blocking. In this paper, we propose to use microcontroller embedded system to enhance current CCTV system. Proposed abnormal sound embedded system is to carry out the sound detection, audio processing and analysis. This study is using only single microphone for sound detection. Audio amplitude and frequency range are targeted feature extracted from Fast Fourier Transform (FFT). Abnormal sound of human screaming and glass breaking were classified using decision tree. From experiment, proposed abnormal sound analytical surveillance system test yield average of 88% accuracy detection. We can consider our work is simple and cost effective for field implementation.