Vehicles sound recognition using wavelet transform, fast Fourier transform and neural networks

Abstract EN

Vehicles may be recognized from the sound they make when engine moving from their acoustic signature.

In this paper, investigated two feature extraction methods for acoustic signals, Fast Fourier Transform (FFT) and Wavelet Packet Transform (WPT) and used for recognition.

To reduce the number of features extracted used Principal Component Analysis algorithm.

And used Artificial neural networks as a classifier for Vehicles types.