Vehicle-classification algorithm for single-loop detectors using neural networks

Yong Kul Ki, Doo Kwon Baik

Research output: Contribution to journalArticle

64 Citations (Scopus)

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.

Original languageEnglish
Pages (from-to)1704-1711
Number of pages8
JournalIEEE Transactions on Vehicular Technology
Volume55
Issue number6
DOIs
Publication statusPublished - 2006 Nov 1

Fingerprint

Classification Algorithm
Detector
Neural Networks
Detectors
Neural networks
Traffic Measurement
Image Sensor
Back-propagation Neural Network
Backpropagation
Image sensors
Waveform
Output

Keywords

  • Back-propagation neural networks
  • Inductive-loop detectors (ILD)
  • Pattern recognition
  • Vehicle classification

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Networks and Communications

Cite this

Vehicle-classification algorithm for single-loop detectors using neural networks. / Ki, Yong Kul; Baik, Doo Kwon.

In: IEEE Transactions on Vehicular Technology, Vol. 55, No. 6, 01.11.2006, p. 1704-1711.

Research output: Contribution to journalArticle

@article{11b25f6e579d4f0985372a4dcf2bca1b,
title = "Vehicle-classification algorithm for single-loop detectors using neural networks",
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 = "Back-propagation neural networks, Inductive-loop detectors (ILD), Pattern recognition, Vehicle classification",
author = "Ki, {Yong Kul} and Baik, {Doo Kwon}",
year = "2006",
month = "11",
day = "1",
doi = "10.1109/TVT.2006.883726",
language = "English",
volume = "55",
pages = "1704--1711",
journal = "IEEE Transactions on Vehicular Technology",
issn = "0018-9545",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "6",

}

TY - JOUR

T1 - Vehicle-classification algorithm for single-loop detectors using neural networks

AU - Ki, Yong Kul

AU - Baik, Doo Kwon

PY - 2006/11/1

Y1 - 2006/11/1

N2 - 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.

AB - 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.

KW - Back-propagation neural networks

KW - Inductive-loop detectors (ILD)

KW - Pattern recognition

KW - Vehicle classification

UR - http://www.scopus.com/inward/record.url?scp=37849188637&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=37849188637&partnerID=8YFLogxK

U2 - 10.1109/TVT.2006.883726

DO - 10.1109/TVT.2006.883726

M3 - Article

VL - 55

SP - 1704

EP - 1711

JO - IEEE Transactions on Vehicular Technology

JF - IEEE Transactions on Vehicular Technology

SN - 0018-9545

IS - 6

ER -