Vehicle-Classification Algorithm for Single-Loop Detectors Using Neural Networks

Author

Ki, Yong-Kul ; Baik, Doo-Kwon

Author_Institution

Dept. of Comput. Sci., Korea Univ., Seoul

Volume

55

Issue

6

fYear

2006

Firstpage

1704

Lastpage

1711

Abstract

Vehicle class is an important parameter in the process of road-traffic measurement. Currently, inductive-loop detectors (ILD) and image sensors are rarely used for vehicle classification because of their low accuracy. To improve the accuracy, the authors suggest a new algorithm for ILD using back-propagation neural networks. In the developed algorithm, the inputs to the neural networks are the variation rate of frequency and frequency waveform. The output is five classified vehicles. The developed algorithm was assessed at test sites, and the recognition rate was 91.5%. The results verified that the proposed algorithm improves the vehicle-classification accuracy compared to the conventional method based on ILD

Keywords

backpropagation; image classification; image sensors; neural nets; road traffic; road vehicles; traffic engineering computing; ILD; back-propagation neural networks; frequency waveform; image sensor; inductive-loop detector; pattern recognition; road-traffic measurement; vehicle-classification algorithm; Backpropagation algorithms; Coils; Detectors; Frequency; Neural networks; Pattern recognition; Pollution measurement; Telecommunication traffic; Vehicle detection; Vehicles; Back-propagation neural networks; inductive-loop detectors (ILD); pattern recognition; vehicle classification;

fLanguage

English

Journal_Title

Vehicular Technology, IEEE Transactions on

Publisher

ieee

ISSN

0018-9545

Type

jour

DOI

10.1109/TVT.2006.883726

Filename

4012533