Applying image matching algorithm in stereo vision based navigation system

Pao Yue-kong Library Electronic Theses Database

Applying image matching algorithm in stereo vision based navigation system

 

Author: Li, Wenbin
Title: Applying image matching algorithm in stereo vision based navigation system
Degree: M.Sc.
Year: 2013
Subject: Image processing -- Mathematical models.
Computer vision.
Motor vehicles.
Hong Kong Polytechnic University -- Dissertations
Department: Faculty of Construction and Environment
Pages: vi, 68 p. : ill. ; 30 cm.
Language: English
InnoPac Record: http://library.polyu.edu.hk/record=b2627069
URI: http://theses.lib.polyu.edu.hk/handle/200/7395
Abstract: A simplified stereo vision based navigation device has been developed in this dissertation. The stereo vision based navigation device is made by two cameras and one laptop. By using the cameras and no other sensors, the stereo vision based navigation device can provide the distance travelled by the device during the driving. The cameras are set as binocular vision system to capture the stereopsis. The stereopsis is used by the navigation device to determine the distance travelled. The major step of data processing of navigation is achieved by image matching algorithm. Candidate image matching algorithms, SIFT 64, SIFT 128 and SURF, are tested of their performances in different experiments. As a result, SIFT 64 was selected as the image matching algorithm for the stereo vision based navigation device. The field tests of the stereo vision based navigation device are made to test the navigation performances of the device. Experiments results show that the integrity of the device developed in this dissertation is about 85.7%, and the error generated by the device is about 16% of its travelled distance in the direction of its movement and 7% in the perpendicular direction. Some discussion of potential application and improvement are also made.

Files in this item

Files Size Format
b26270699.pdf 3.183Mb 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

Browse

More Information