Title :
Feature extraction in vehicle classification
Author :
Górski, Maksymilian ; Zarzycki, Jan
Author_Institution :
Wroclaw Univ. of Technol., Wroclaw, Poland
Abstract :
Vehicle classification based on their acoustic emission is a complex problem. Vehicle consist of many noise sources, and environmental noise can also be significant. The key to efficient vehicle classification is choosing the optimal feature extraction method. In this article three methods are presented, each relating to properties of vehicle noise. Methods are compared in context of their separability and generalization.
Keywords :
acoustic emission; acoustic noise; acoustic signal processing; feature extraction; road vehicles; signal classification; traffic engineering computing; acoustic emission; environmental noise; noise source; optimal feature extraction method; vehicle classification; Engines; Harmonic analysis; Noise; Roads; Support vector machines; Vectors; Vehicles;
Conference_Titel :
Signals and Electronic Systems (ICSES), 2012 International Conference on
Conference_Location :
Wroclaw
Print_ISBN :
978-1-4673-1710-8
Electronic_ISBN :
978-1-4673-1709-2
DOI :
10.1109/ICSES.2012.6382264
