Use this URL to cite or link to this record in EThOS: http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.579690
Title: Performance analysis of airport ground lighting using computer vision techniques
Author: Chowdhury, Shyama Prosad
Awarding Body: Queen's University Belfast
Current Institution: Queen's University Belfast
Date of Award: 2012
Availability of Full Text:
Full text unavailable from EThOS.
Please contact the current institution’s library for further details.
Abstract:
In the presented research, mobile camera technology is used to assess the performance of airport ground lighting. In particular, automated assessment of the performance of luminaires in the approach lighting system CALS) within an airport landing lighting system is proposed. To do this a camera must be installed in the cockpit of an aircraft. As the aircraft approaches the runway, the camera records image data of the lighting pattern. Subsequent image analysis, using the computer vision techniques proposed here, will allow a performance metric to be determined for the luminaires. The performance metric will rank the luminaires based on their performance. This is very useful information towards the maintenance strategy for the airport and to date, is the only method available to evaluate the performance of luminaires in the ALS pattern. In order to determine the performance metric for the ALS, the luminaires must be identified in each image in which they appear or tracked throughout the complete acquired image sequence. For each identified lurninaire, the pixel information representing that luminaire must be extracted and stored. A measure of the pixel grey level per luminaire per image is then used to estimate a performance measure for each luminaire. In addition, since mobile camera technology is used, some of the captured images can become corrupted with the effects of vibration. The effect that this vibration will have on the pixel grey level information recorded for a given luminaire is not known. Therefore a methodology to quantify this effect is proposed. In addition, since the quality of captured images can vary with vibration, a reliability factor is also automatically determined for each acquired performance measurement. Using the performance measurement data luminaires are ranked in a list and this list is then reported to the maintenance team at a given airport.
Supervisor: Not available Sponsor: Not available
Qualification Name: Thesis (Ph.D.) Qualification Level: Doctoral
EThOS ID: uk.bl.ethos.579690  DOI: Not available
Share: