Developing and validating a real time video based traffic counting and classification

Research output: Contribution to journalArticle

Abstract

An algorithm program was developed to detect vehicles in traffic videos and get the vehicle count for the small time period as a tool that can assist researchers who seek vehicle counting. This system approach has been presented for extracting traffic data using video image processing. Meanwhile, an offline program focuses on extracting vehicles, tracking them and providing the vehicle count for a short period of time. It uses background subtraction, shadow removal, and pixel analysis for extracting moving objects. The results show that the algorithm is capable of counting 95% of the vehicles due to some shaking in the video feed. These data have been analysed by the paired samples t-test to show the credibility of the results which have been approved to be useful according to the values of correlation and P-value compared with the values of the observation method. Also, the classification of vehicles was performed using the improfile command in Matlab-Video Image Processing that computes the colours intensity values along a line or a multiline path in an image.

Original languageEnglish
Pages (from-to)3215-3225
Number of pages11
JournalJournal of Engineering Science and Technology
Volume12
Issue number12
Publication statusPublished - 1 Jan 2017

Fingerprint

Image processing
Pixels
Color

Keywords

  • Algorithm system
  • Matlab
  • Optical flow model
  • Vehicles classification
  • Video image processing

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Developing and validating a real time video based traffic counting and classification. / Jehad, Ali E.; O.K. Rahmat, Riza Atiq Abdullah.

In: Journal of Engineering Science and Technology, Vol. 12, No. 12, 01.01.2017, p. 3215-3225.

Research output: Contribution to journalArticle

@article{b6c20659109740c48f8fd8c67546fdb8,
title = "Developing and validating a real time video based traffic counting and classification",
abstract = "An algorithm program was developed to detect vehicles in traffic videos and get the vehicle count for the small time period as a tool that can assist researchers who seek vehicle counting. This system approach has been presented for extracting traffic data using video image processing. Meanwhile, an offline program focuses on extracting vehicles, tracking them and providing the vehicle count for a short period of time. It uses background subtraction, shadow removal, and pixel analysis for extracting moving objects. The results show that the algorithm is capable of counting 95{\%} of the vehicles due to some shaking in the video feed. These data have been analysed by the paired samples t-test to show the credibility of the results which have been approved to be useful according to the values of correlation and P-value compared with the values of the observation method. Also, the classification of vehicles was performed using the improfile command in Matlab-Video Image Processing that computes the colours intensity values along a line or a multiline path in an image.",
keywords = "Algorithm system, Matlab, Optical flow model, Vehicles classification, Video image processing",
author = "Jehad, {Ali E.} and {O.K. Rahmat}, {Riza Atiq Abdullah}",
year = "2017",
month = "1",
day = "1",
language = "English",
volume = "12",
pages = "3215--3225",
journal = "Journal of Engineering Science and Technology",
issn = "1823-4690",
publisher = "Taylor's University College",
number = "12",

}

TY - JOUR

T1 - Developing and validating a real time video based traffic counting and classification

AU - Jehad, Ali E.

AU - O.K. Rahmat, Riza Atiq Abdullah

PY - 2017/1/1

Y1 - 2017/1/1

N2 - An algorithm program was developed to detect vehicles in traffic videos and get the vehicle count for the small time period as a tool that can assist researchers who seek vehicle counting. This system approach has been presented for extracting traffic data using video image processing. Meanwhile, an offline program focuses on extracting vehicles, tracking them and providing the vehicle count for a short period of time. It uses background subtraction, shadow removal, and pixel analysis for extracting moving objects. The results show that the algorithm is capable of counting 95% of the vehicles due to some shaking in the video feed. These data have been analysed by the paired samples t-test to show the credibility of the results which have been approved to be useful according to the values of correlation and P-value compared with the values of the observation method. Also, the classification of vehicles was performed using the improfile command in Matlab-Video Image Processing that computes the colours intensity values along a line or a multiline path in an image.

AB - An algorithm program was developed to detect vehicles in traffic videos and get the vehicle count for the small time period as a tool that can assist researchers who seek vehicle counting. This system approach has been presented for extracting traffic data using video image processing. Meanwhile, an offline program focuses on extracting vehicles, tracking them and providing the vehicle count for a short period of time. It uses background subtraction, shadow removal, and pixel analysis for extracting moving objects. The results show that the algorithm is capable of counting 95% of the vehicles due to some shaking in the video feed. These data have been analysed by the paired samples t-test to show the credibility of the results which have been approved to be useful according to the values of correlation and P-value compared with the values of the observation method. Also, the classification of vehicles was performed using the improfile command in Matlab-Video Image Processing that computes the colours intensity values along a line or a multiline path in an image.

KW - Algorithm system

KW - Matlab

KW - Optical flow model

KW - Vehicles classification

KW - Video image processing

UR - http://www.scopus.com/inward/record.url?scp=85039807820&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85039807820&partnerID=8YFLogxK

M3 - Article

VL - 12

SP - 3215

EP - 3225

JO - Journal of Engineering Science and Technology

JF - Journal of Engineering Science and Technology

SN - 1823-4690

IS - 12

ER -