Tampere University of Technology

TUTCRIS Research Portal

Real-Time Vehicle Recognition and Improved Traffic Congestion Resolution

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Details

Original languageEnglish
Title of host publication13th International Conference on Frontiers of Information Technology (FIT), 2015
PublisherIEEE
Pages228-233
Number of pages6
ISBN (Electronic)978-1-4673-9666-0
DOIs
Publication statusPublished - 14 Dec 2015
Externally publishedYes
Publication typeA4 Article in a conference publication

Abstract

An intelligent traffic management system (E-Traffic
Warden) is proposed, using image processing
techniques along with smart traffic control algorithm. Traffic
recognition was achieved using cascade classifier for vehicle
recognition utilizing Open CV and Visual Studio C/C++. The
classifier was trained on 700 positive samples and 1140
negative samples. The results show that the accuracy of vehicle
detection is approximately 93 percent. The count of vehicles at
all approaches of intersection is used to estimate traffic. Traffic
build up is then avoided or resolved by passing the extracted
data to traffic control algorithm. The control algorithm shows
approximately 86 % improvement over Fixed-Delay controller
in worst case scenarios