|Title:||Geometric positioning and mapping system by machine vision technology|
|Subject:||Hong Kong Polytechnic University -- Dissertations.|
Buildings -- Maintenance.
|Department:||Department of Electronic and Information Engineering|
|Pages:||132 leaves : ill. (some col.) ; 30 cm.|
|Abstract:||Building maintenance involves assessing the "health" of a building and repairing it. Such assessment employs different types of surveys which require instruments to test and measure the properties of a building. Most of the surveys are useful, powerful, recognized and standardized in the British Standards (BS) and the American Standards of Testing Materials (ASTM). Some of these surveys investigate the properties of the building against the corresponding spatial position. Unfortunately, the positioning system used in the industry is very rough and primitive - hand-drawn grids. This project proposes an image positioning system (IPS) for the building maintenance industries and investigates its overall feasibility, such that laborious hand-drawn grids can be eliminated. In this project, the IPS has been proved intrinsically the most suitable positioning system for the building maintenance industries. The algorithm of the IPS is essentially image pattern matching. It recognizes a pattern in the image and extracts its position. Fortunately, this algorithm can minimize risk of undetectable errors even when there are a lot of obstacles surrounding the area under test. For example, during a survey, the worker operating the instruments in the area under test, his body and instruments have minimal effects on the proposed IPS. The IPS is integrated with common equipment used in site investigation. These are the computer, the video camera and a special designed paper card - the target. Collaborating with a data acquisition interface device, the output of the instrument and the position of the probe are captured and processed in real time. The positioning information and the corresponding building properties are plotted onto a contour map. This map shows the trend and distribution of the building properties two-dimensionally such that the building's condition can be easily visualized.|
|Rights:||All rights reserved|
Files in This Item:
|b21101280.pdf||For All Users (off-campus access for PolyU Staff & Students only)||18.96 MB||Adobe PDF||View/Open|
As a bona fide Library user, I declare that:
- I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
- 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.
- 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.
Please use this identifier to cite or link to this item: