Vehicle classification using advanced technologies

Chien-Hung Wei, Cheng Chih Chang, Sheng Shih Wang

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

Applying advanced technologies to existing problem domains is a highly desirable approach in many research areas. Among these techniques, image processing has been shown useful in transportation fields for such tasks as traffic pattern recognition, data collection, accident detection, and pavement evaluation. The integrated model with artificial neural networks (ANNs) has promising potential applications. The image processing and ANN model are combined to explore the feasibility of vehicle classification in real-world situations. Three methods were developed during the research process: ground segmentation, background subtraction, and window segmentation. The first two methods were used to separate the objects of scene and nonscene from the actual traffic image. To reduce the complexity of neural networks, the image was divided into 16 windows and three characteristics (occupation rates of vehicles, of horizontal image lines, and of vertical image lines) of each window were extracted to generate 48 factors as the input units of the neural network. The backpropagation ANN model with one hidden layer is employed. The experiments show that the accurate recognition rates of heavy vehicles, small cars, and motorcycles are 98.5, 96.92, and 91.94 percent, respectively. The result implies the remarkable applicability of the proposed methods in transportation areas.

Original languageEnglish
Pages (from-to)45-50
Number of pages6
JournalTransportation Research Record
Issue number1551
DOIs
Publication statusPublished - 1996 Jan 1

Fingerprint

Neural networks
Image processing
Motorcycles
Backpropagation
Pavements
Pattern recognition
Accidents
Railroad cars
Experiments

All Science Journal Classification (ASJC) codes

  • Civil and Structural Engineering
  • Mechanical Engineering

Cite this

Wei, Chien-Hung ; Chang, Cheng Chih ; Wang, Sheng Shih. / Vehicle classification using advanced technologies. In: Transportation Research Record. 1996 ; No. 1551. pp. 45-50.
@article{94fbac3032034e3e818240e5bcdbcf15,
title = "Vehicle classification using advanced technologies",
abstract = "Applying advanced technologies to existing problem domains is a highly desirable approach in many research areas. Among these techniques, image processing has been shown useful in transportation fields for such tasks as traffic pattern recognition, data collection, accident detection, and pavement evaluation. The integrated model with artificial neural networks (ANNs) has promising potential applications. The image processing and ANN model are combined to explore the feasibility of vehicle classification in real-world situations. Three methods were developed during the research process: ground segmentation, background subtraction, and window segmentation. The first two methods were used to separate the objects of scene and nonscene from the actual traffic image. To reduce the complexity of neural networks, the image was divided into 16 windows and three characteristics (occupation rates of vehicles, of horizontal image lines, and of vertical image lines) of each window were extracted to generate 48 factors as the input units of the neural network. The backpropagation ANN model with one hidden layer is employed. The experiments show that the accurate recognition rates of heavy vehicles, small cars, and motorcycles are 98.5, 96.92, and 91.94 percent, respectively. The result implies the remarkable applicability of the proposed methods in transportation areas.",
author = "Chien-Hung Wei and Chang, {Cheng Chih} and Wang, {Sheng Shih}",
year = "1996",
month = "1",
day = "1",
doi = "10.3141/1551-06",
language = "English",
pages = "45--50",
journal = "Transportation Research Record",
issn = "0361-1981",
publisher = "US National Research Council",
number = "1551",

}

Vehicle classification using advanced technologies. / Wei, Chien-Hung; Chang, Cheng Chih; Wang, Sheng Shih.

In: Transportation Research Record, No. 1551, 01.01.1996, p. 45-50.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Vehicle classification using advanced technologies

AU - Wei, Chien-Hung

AU - Chang, Cheng Chih

AU - Wang, Sheng Shih

PY - 1996/1/1

Y1 - 1996/1/1

N2 - Applying advanced technologies to existing problem domains is a highly desirable approach in many research areas. Among these techniques, image processing has been shown useful in transportation fields for such tasks as traffic pattern recognition, data collection, accident detection, and pavement evaluation. The integrated model with artificial neural networks (ANNs) has promising potential applications. The image processing and ANN model are combined to explore the feasibility of vehicle classification in real-world situations. Three methods were developed during the research process: ground segmentation, background subtraction, and window segmentation. The first two methods were used to separate the objects of scene and nonscene from the actual traffic image. To reduce the complexity of neural networks, the image was divided into 16 windows and three characteristics (occupation rates of vehicles, of horizontal image lines, and of vertical image lines) of each window were extracted to generate 48 factors as the input units of the neural network. The backpropagation ANN model with one hidden layer is employed. The experiments show that the accurate recognition rates of heavy vehicles, small cars, and motorcycles are 98.5, 96.92, and 91.94 percent, respectively. The result implies the remarkable applicability of the proposed methods in transportation areas.

AB - Applying advanced technologies to existing problem domains is a highly desirable approach in many research areas. Among these techniques, image processing has been shown useful in transportation fields for such tasks as traffic pattern recognition, data collection, accident detection, and pavement evaluation. The integrated model with artificial neural networks (ANNs) has promising potential applications. The image processing and ANN model are combined to explore the feasibility of vehicle classification in real-world situations. Three methods were developed during the research process: ground segmentation, background subtraction, and window segmentation. The first two methods were used to separate the objects of scene and nonscene from the actual traffic image. To reduce the complexity of neural networks, the image was divided into 16 windows and three characteristics (occupation rates of vehicles, of horizontal image lines, and of vertical image lines) of each window were extracted to generate 48 factors as the input units of the neural network. The backpropagation ANN model with one hidden layer is employed. The experiments show that the accurate recognition rates of heavy vehicles, small cars, and motorcycles are 98.5, 96.92, and 91.94 percent, respectively. The result implies the remarkable applicability of the proposed methods in transportation areas.

UR - http://www.scopus.com/inward/record.url?scp=0030287666&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030287666&partnerID=8YFLogxK

U2 - 10.3141/1551-06

DO - 10.3141/1551-06

M3 - Article

SP - 45

EP - 50

JO - Transportation Research Record

JF - Transportation Research Record

SN - 0361-1981

IS - 1551

ER -