Vehicle classification model for loop detectors using neural networks

Yong K. Ki, Doo Kwon Baik

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Vehicle class is an important parameter in the process of road traffic measurement. Inductive loop detectors (ILD) and image sensors are rarely used for vehicle classification because of their low accuracy. To improve their accuracy, a new algorithm is suggested for ILD using backpropagation neural networks. In the developed algorithm, inputs to the neural networks are the variation rate of frequency and occupancy time. The output is five classified vehicles. The developed algorithm was assessed at test sites, and the recognition rate was 91.7%. Results verified that, compared with the conventional method based on ILD, the proposed algorithm improves the vehicle classification accuracy.

Original languageEnglish
Pages (from-to)164-172
Number of pages9
JournalTransportation Research Record
Issue number1917
Publication statusPublished - 2005 Dec 1

Fingerprint

Detectors
Neural networks
Backpropagation
Image sensors

ASJC Scopus subject areas

  • Civil and Structural Engineering

Cite this

Vehicle classification model for loop detectors using neural networks. / Ki, Yong K.; Baik, Doo Kwon.

In: Transportation Research Record, No. 1917, 01.12.2005, p. 164-172.

Research output: Contribution to journalArticle

@article{fc1ab2227c1f44a5983ed2c6f6eb3efb,
title = "Vehicle classification model for loop detectors using neural networks",
abstract = "Vehicle class is an important parameter in the process of road traffic measurement. Inductive loop detectors (ILD) and image sensors are rarely used for vehicle classification because of their low accuracy. To improve their accuracy, a new algorithm is suggested for ILD using backpropagation neural networks. In the developed algorithm, inputs to the neural networks are the variation rate of frequency and occupancy time. The output is five classified vehicles. The developed algorithm was assessed at test sites, and the recognition rate was 91.7{\%}. Results verified that, compared with the conventional method based on ILD, the proposed algorithm improves the vehicle classification accuracy.",
author = "Ki, {Yong K.} and Baik, {Doo Kwon}",
year = "2005",
month = "12",
day = "1",
language = "English",
pages = "164--172",
journal = "Transportation Research Record",
issn = "0361-1981",
publisher = "US National Research Council",
number = "1917",

}

TY - JOUR

T1 - Vehicle classification model for loop detectors using neural networks

AU - Ki, Yong K.

AU - Baik, Doo Kwon

PY - 2005/12/1

Y1 - 2005/12/1

N2 - Vehicle class is an important parameter in the process of road traffic measurement. Inductive loop detectors (ILD) and image sensors are rarely used for vehicle classification because of their low accuracy. To improve their accuracy, a new algorithm is suggested for ILD using backpropagation neural networks. In the developed algorithm, inputs to the neural networks are the variation rate of frequency and occupancy time. The output is five classified vehicles. The developed algorithm was assessed at test sites, and the recognition rate was 91.7%. Results verified that, compared with the conventional method based on ILD, the proposed algorithm improves the vehicle classification accuracy.

AB - Vehicle class is an important parameter in the process of road traffic measurement. Inductive loop detectors (ILD) and image sensors are rarely used for vehicle classification because of their low accuracy. To improve their accuracy, a new algorithm is suggested for ILD using backpropagation neural networks. In the developed algorithm, inputs to the neural networks are the variation rate of frequency and occupancy time. The output is five classified vehicles. The developed algorithm was assessed at test sites, and the recognition rate was 91.7%. Results verified that, compared with the conventional method based on ILD, the proposed algorithm improves the vehicle classification accuracy.

UR - http://www.scopus.com/inward/record.url?scp=33645035917&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33645035917&partnerID=8YFLogxK

M3 - Article

SP - 164

EP - 172

JO - Transportation Research Record

JF - Transportation Research Record

SN - 0361-1981

IS - 1917

ER -