Automatic vehicle classification using fast neural network and classical neural network for traffic monitoring

Hannan M A, Chew Teik Gee, Mohammad Saleh Javadi

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

This paper introduces an automatic vehicle classification for traffic monitoring using image processing. In this technique the fast neural network (FNN) as a primary classifier and then the classical neural network (CNN) as a final classifier are applied to achieve high classification performance. The FNN gains a useful correlation between the input and the weighted neurons using a multilayer perceptron to provide detection with a high level of accuracy. The Fourier transform is used to speed up the procedure. In the CNN, a lighting normalization method is employed to reduce the effect of variations in illumination. The combination of the FNN and CNN is used to verify and classify the vehicle regions. False detection is added to the training procedure using a bootstrap algorithm to get nonvehicle images. Experimental results demonstrate that the proposed system performs accurately with a low false positive rate in both simple and complex scenarios in detecting vehicles in comparison with previous vehicle classification systems.

Original languageEnglish
Pages (from-to)2031-2042
Number of pages12
JournalTurkish Journal of Electrical Engineering and Computer Sciences
Volume23
DOIs
Publication statusPublished - 2015

Fingerprint

Neural networks
Monitoring
Classifiers
Lighting
Multilayer neural networks
Neurons
Fourier transforms
Image processing

Keywords

  • Automatic vehicle classification
  • Classical neural network
  • Fast fourier transform
  • Fast neural network

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Science(all)

Cite this

Automatic vehicle classification using fast neural network and classical neural network for traffic monitoring. / M A, Hannan; Gee, Chew Teik; Javadi, Mohammad Saleh.

In: Turkish Journal of Electrical Engineering and Computer Sciences, Vol. 23, 2015, p. 2031-2042.

Research output: Contribution to journalArticle

@article{afddecd03e224c4db79f87f3e5f94768,
title = "Automatic vehicle classification using fast neural network and classical neural network for traffic monitoring",
abstract = "This paper introduces an automatic vehicle classification for traffic monitoring using image processing. In this technique the fast neural network (FNN) as a primary classifier and then the classical neural network (CNN) as a final classifier are applied to achieve high classification performance. The FNN gains a useful correlation between the input and the weighted neurons using a multilayer perceptron to provide detection with a high level of accuracy. The Fourier transform is used to speed up the procedure. In the CNN, a lighting normalization method is employed to reduce the effect of variations in illumination. The combination of the FNN and CNN is used to verify and classify the vehicle regions. False detection is added to the training procedure using a bootstrap algorithm to get nonvehicle images. Experimental results demonstrate that the proposed system performs accurately with a low false positive rate in both simple and complex scenarios in detecting vehicles in comparison with previous vehicle classification systems.",
keywords = "Automatic vehicle classification, Classical neural network, Fast fourier transform, Fast neural network",
author = "{M A}, Hannan and Gee, {Chew Teik} and Javadi, {Mohammad Saleh}",
year = "2015",
doi = "10.3906/elk-1211-46",
language = "English",
volume = "23",
pages = "2031--2042",
journal = "Turkish Journal of Electrical Engineering and Computer Sciences",
issn = "1300-0632",
publisher = "Turkiye Klinikleri",

}

TY - JOUR

T1 - Automatic vehicle classification using fast neural network and classical neural network for traffic monitoring

AU - M A, Hannan

AU - Gee, Chew Teik

AU - Javadi, Mohammad Saleh

PY - 2015

Y1 - 2015

N2 - This paper introduces an automatic vehicle classification for traffic monitoring using image processing. In this technique the fast neural network (FNN) as a primary classifier and then the classical neural network (CNN) as a final classifier are applied to achieve high classification performance. The FNN gains a useful correlation between the input and the weighted neurons using a multilayer perceptron to provide detection with a high level of accuracy. The Fourier transform is used to speed up the procedure. In the CNN, a lighting normalization method is employed to reduce the effect of variations in illumination. The combination of the FNN and CNN is used to verify and classify the vehicle regions. False detection is added to the training procedure using a bootstrap algorithm to get nonvehicle images. Experimental results demonstrate that the proposed system performs accurately with a low false positive rate in both simple and complex scenarios in detecting vehicles in comparison with previous vehicle classification systems.

AB - This paper introduces an automatic vehicle classification for traffic monitoring using image processing. In this technique the fast neural network (FNN) as a primary classifier and then the classical neural network (CNN) as a final classifier are applied to achieve high classification performance. The FNN gains a useful correlation between the input and the weighted neurons using a multilayer perceptron to provide detection with a high level of accuracy. The Fourier transform is used to speed up the procedure. In the CNN, a lighting normalization method is employed to reduce the effect of variations in illumination. The combination of the FNN and CNN is used to verify and classify the vehicle regions. False detection is added to the training procedure using a bootstrap algorithm to get nonvehicle images. Experimental results demonstrate that the proposed system performs accurately with a low false positive rate in both simple and complex scenarios in detecting vehicles in comparison with previous vehicle classification systems.

KW - Automatic vehicle classification

KW - Classical neural network

KW - Fast fourier transform

KW - Fast neural network

UR - http://www.scopus.com/inward/record.url?scp=84946750518&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84946750518&partnerID=8YFLogxK

U2 - 10.3906/elk-1211-46

DO - 10.3906/elk-1211-46

M3 - Article

VL - 23

SP - 2031

EP - 2042

JO - Turkish Journal of Electrical Engineering and Computer Sciences

JF - Turkish Journal of Electrical Engineering and Computer Sciences

SN - 1300-0632

ER -