Vehicle sound classification. Application and low pass filtering influence

The aim of this paper is to present a vehicle sound classification system, implemented on the Matlab platform. Then we focus on the results of the classification system when low pass filtering is performed. The system uses time encoded signal processing and recognition (TESPAR) method combined with the archetypes technique. For low pass filtering, different Butterworth low pass filters were implemented. The experimental results show the efficiency of the TESPAR method when dealing with vehicle sounds.

I. Introduction

Any engine of a vehicle that is turned on makes some kind of a noise. Vehicles of the same class and working in similar conditions will theoretically generate similar noises, or one may say they will have some kind of noise signature [1]. In conclusion, the noise coming from the running engine gives an important clue, e.g., for military reconnaissance or a surveillance mission robot to detect a vehicle and recognize its class.