Yuriy Luzanov

Abstract

There are many existing multicamera systems that perform object identification and track ing. Some applications include but are not limited to security surveillance and smart rooms. Yet there is still much work to be done in improving such systems to achieve a high level of automation while obtaining reasonable performance. Thus far design and implementation of these systems has been done using heuristic methods, primarily due to the complexity of the problem. Most importantiy, the performance of these systems is assessed by evaluating subjective quantities. The goal of this work is to take the first step in structured analysis and design of multicamera systems, that is, to introduce a model of a single camera with asso ciated image processing algorithms capable of tracking a target. A single camera model is developed such that it could be easily used as a building block for a multicamera system.

Library of Congress Subject Headings

Computer vision--Mathematical models; Camcorders--Mathematical models; Motion control devices; Automatic control; Automatic tracking

Publication Date

2006

Document Type

Thesis

Student Type

Graduate

Degree Name

Computer Engineering (MS)

Department, Program, or Center

Computer Engineering (KGCOE)

Advisor

Juan Cockburn

Advisor/Committee Member

Marcin Lukowiak

Advisor/Committee Member

Muhammad Shaaban

Comments

Physical copy available from RIT's Wallace Library at TA1634 .L89 2006

Campus

RIT – Main Campus

Download

Share

COinS