Acoustic intruder detection system for home security

Abstract

This paper propose a new algorithm to detect the intruder in room. The basic idea of the proposed method is to estimate the variation of features of the room acoustic transfer function (RTF). The room transfer function is computed by cross-correlation method. There are some methods to measure the RFT. For example there are the image methods, ray tracing method to measure actually the RFT. In this we estimated RTF using white Gaussian noise that is broadband signal. It is important to extract feature vectors. Feature extraction is the process of computing a numerical representation. We used various features to detect intruder. The features based on the short time Fourier transform (STFT) and the zero-crossing rates were used. Several simulations and actually tests show that the proposed method provides good performance for intruder detection.