Motion Tracking With Web Camera Images Based On Spatial Properties

Lee, Andrew Choon Guan (2003) Motion Tracking With Web Camera Images Based On Spatial Properties. Masters thesis, Universiti Putra Malaysia.

[img] PDF
790Kb

Abstract

Machine Vision provides a cheap and flexible mean of tracking objects in motion when implemented by a web Camera. The low resolution digital images, capturing the different instances of the scene of object in motion yields information which can be used to lay a historical track of the object. The implementation of such a system. involved the separation of the objects from the background using threshold segmentation techniques. Although it accepted the variation of natural lighting, it assumed that the background was lighter than the objects. By that method, the objects which have the potential to move, were separated from the stationary background.The segmentation scheme implemented was a robust automated scheme, and form the preprocessing stage of the whole system.

Item Type:Thesis (Masters)
Chairman Supervisor:Abdul Rahman Ramli, PhD
Call Number:FK 2003 21
Faculty or Institute:Faculty of Engineering
ID Code:12162
Deposited By: Mohd Nezeri Mohamad
Deposited On:15 Jul 2011 03:25
Last Modified:15 Jul 2011 03:25

Repository Staff Only: item control page

Document Download Statistics

This item has been downloaded for since 15 Jul 2011 03:25.

View statistics for "Motion Tracking With Web Camera Images Based On Spatial Properties "


Universiti Putra Malaysia Institutional Repository

Universiti Putra Malaysia Institutional Repository is an on-line digital archive that serves as a central collection and storage of scientific information and research at the Universiti Putra Malaysia.

Currently, the collections deposited in the IR consists of Master and PhD theses, Master and PhD Project Report, Journal Articles, Journal Bulletins, Conference Papers, UPM News, Newspaper Cuttings, Patents and Inaugural Lectures.

As the policy of the university does not permit users to view thesis in full text, access is only given to the first 24 pages only.