Optical Flow-Based Vehicle Detection and Tracking

Only available on StudyMode
  • Topic: Tracking system, Tracking, OpenCV
  • Pages : 48 (10939 words )
  • Download(s) : 120
  • Published : April 30, 2013
Open Document
Text Preview
OPTICAL FLOW-BASED VEHICLE DETECTION AND TRACKING By Ong Hen Ching

A REPORT SUBMITTED TO University Tunku Abdul Rahman in partial fulfilment of the requirements for the degree of BACHELOR OF INFORMATION SYSTEMS (HONS) INFORMATION SYSTEMS ENGINEERING Faculty of Information and Communication Technology (Perak Campus) May 2010

DECLARATION OF ORIGINALITY

I declare

that

this

report

entitled

“OPTICAL

FLOW-BASED

VEHICLE

DETECTION AND TRACKING” is my own work except as cited in the references. The report has not been accepted for any degree and is not being submitted concurrently in candidature for any degree or other award.

Signature :

____________________________

Name

:

____________________________

Date

:

____________________________

ACKNOWLEDGEMENT

I would like to give my special thanks to my supervisor, Mr. Tou Jing Yi for guide and support me throughout my research on FYP. He has provided me a chance to engage in computer vision field, which is a very interesting IT field that yet to be discovered. Without his guidance and support, I would not be able to deliver this project. I really appreciate his guidance and support. Thanks. I would also like to thanks Mr. Ho Wing Teng for provided me very valuable comment and suggestion for my project. He has reviewed my project and suggested some solution that I have tried to seek for a long time. I also appreciate the data and information that he given to me, which is the video files that used in this research project. With his test video files, I managed to discover more fact about my project. A very sincere thank for my friend, Alvin Yeo Zong Yun for commented on my works. He is also enrolled in project that is related to computer vision field, and always willing to share his knowledge with me, and helped my project a lot. He has also been a good partner in my university life. Million thanks for him. A special thanks to my friend, Mr. Wang Hsin Jo for sharing his knowledge of computer programming. He even managed to provide me some information on computer vision field. And thanks my friends, Mr. Edward Cheang Kok Wei, Mr. Lim Sheng Peng and Mr.Yew Wei Hang, for lightening up my university life. And finally, I would like to express my greatest thanks to my parents, Mr Ong Ban Sing and Mrs Chang Siew Hiang. They have been keep supporting me and

encourage me throughout my university life. Their love, support, encouragement and patience, is and will be always the greatest treasure for my life.

BIS (Hons) Information Systems Engineering Falculty of Information and Communication Technology (Perak Campus), UTAR

iii

ABSTRACT

Motion tracking is one of the most active research titles in computer vision field. Tracking of motion can be informative and valuable, and motion information is very useful for traffic surveillance system. Many proposed motion tracking techniques involves using template matching, blob tracking and contour tracking. A famous motion tracking and estimation technique, optical flow, however, is not being widely used and tested for the practicability on traffic surveillance system. Thus, to analyze the reliability and practicability of it, this research project proposed the idea of implementing optical flow in traffic surveillance system, and will evaluate its performance. Another aim of this research project is to assess the ability of OpenCV, a famous open source computer library, in traffic surveillance system. Three experiments were carried out in this research project to test the practicability of optical flow, and also to find the fact about optical flow. Also background subtraction technique available in OpenCV was assessed to assist on problem identification. The results of tracking using Lucas-Kanade (LK) optical flow is proving that optical flow is a great technique to track the motion of moving object, and has great potential to implement it into traffic surveillance system.

BIS...
tracking img