Date of Award

7-29-2020

Publication Type

Master Thesis

Degree Name

M.A.Sc.

Department

Electrical and Computer Engineering

First Advisor

Xiang Chen

Keywords

camera, coverage, modeling, optimization, sensor, visual networks

Rights

info:eu-repo/semantics/embargoedAccess

Creative Commons License

Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.

Abstract

When it comes to visual sensor networks deployment and optimization, modeling the coverage of a given camera network is a vital step. Due to many complex parameters and criteria that governs coverage quality of a given visual network, modeling such coverage accurately and efficiently represents a real challenge. This thesis explores the idea of simplifying the mathematical interpretation that describes a given visual sensor without incurring a cost on coverage measurement accuracy. In this thesis, coverage criteria are described in image space, in contrast to some of the more advanced models found in literature, that are formulated in 3D space, which in turn will have a direct impact on efficiency and time cost. In addition, this thesis also proposes a novel sensor deployment approach that examines the surface topology of the target object to be covered by means of a mesh segmentation algorithm, which is that a different way to tackle the problem other than the exhaustive search methods employed in the examined literature. There are two main contributions in this thesis. Firstly, a new coverage model that takes partial occlusion criterion into account is proposed, which is shown to be more accurate and more efficient than the competition. Next, a new sensor deployment method was presented that takes the target object shape topological properties into account, an approach that is to the best of our knowledge, was not attempted in literature before at the time of publication. This thesis attempts to support all of claims made above, the proposed model is validated and compared to an existing state of art coverage model. In addition, simulations and experiments were carried out to demonstrate the accuracy and time cost efficiency of the proposed work.

Available for download on Monday, January 25, 2021

Share

COinS