Three kinds of vehicle acoustic signals: cars, jeeps, and trucks are studied. According to the analysis of vehicles acoustic signal signature in time-domain and frequency-domain, a feature extraction algorithm is proposed which take the time-domain energy of the acoustic signals in different scales after wavelet decomposition as the feature vectors. An improved BP neural network classifier for vehicle target classification is designed. Experiment results have shown that the proposed feature extraction algorithm can distinguish different types of vehicles with satisfactory rate of correct recognition, and feature vector is robust. The classification accuracies can reach as high as 92%.
Vehicle Classification Using Acoustic Energy Signature in Wavelet Scale Space and Neural Network
First International Conference on Transportation Engineering ; 2007 ; Southwest Jiaotong University, Chengdu, China
09.07.2007
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Vehicle Classification Using Acoustic Energy Signature in Wavelet Scale Space and Neural Network
British Library Conference Proceedings | 2007
|A field trial of acoustic signature analysis for vehicle classification
Online Contents | 1997
|Vehicle-Type Classification Using Capsule Neural Network
Springer Verlag | 2022
|Short-term forecasting of available parking space using wavelet neural network model
IET | 2015
|Real-Time Vehicle Classification Using Inductive Loop Signature Data
Transportation Research Record | 2008
|