Traffic parameters estimation based on video images

Pao Yue-kong Library Electronic Theses Database

Traffic parameters estimation based on video images


Author: Liu, Ye
Title: Traffic parameters estimation based on video images
Degree: M.Sc.
Year: 2011
Subject: Traffic flow
Traffic monitoring
Automatic tracking
Hong Kong Polytechnic University -- Dissertations
Department: Dept. of Land Surveying and Geo-Informatics
Pages: viii, 63 leaves : ill. ; 30 cm.
InnoPac Record:
Abstract: This thesis presents the methodologies for extracting the traffic parameters which refer to the average speed, occupancy and the vehicle flowrate using real-time video image processing. It provides the speed, occupancy and the vehicle count with a given period of time. Background subtraction is used for detecting the moving objects. In average speed calculation, virtual loops are applied. For the occupancy, a new idea, using histogram, is showed in this test. The proposed method for counting vehicles is tracking, a popular method in the study area. In this study, tracking is based on the centroids of the detected box which includes the cars on the road. To increase the accuracy of tracking, average speed is added to predict position in the next frame. The results of traffic parameters calculation show a good performance in this study.

Files in this item

Files Size Format
b24453043.pdf 1.668Mb PDF
Copyright Undertaking
As a bona fide Library user, I declare that:
  1. I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
  2. I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
  3. I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.
By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.


Quick Search


More Information