Image enhancement strategies for land weapon systems
Portelange, Laurent
Promotor(s) : Verly, Jacques
Date of defense : 26-Jun-2017/27-Jun-2017 • Permalink : http://hdl.handle.net/2268.2/2563
Details
Title : | Image enhancement strategies for land weapon systems |
Author : | Portelange, Laurent |
Date of defense : | 26-Jun-2017/27-Jun-2017 |
Advisor(s) : | Verly, Jacques |
Committee's member(s) : | Van Droogenbroeck, Marc
Delporte, Guillaume |
Language : | English |
Discipline(s) : | Engineering, computing & technology > Electrical & electronics engineering |
Target public : | Professionals of domain |
Institution(s) : | Université de Liège, Liège, Belgique |
Degree: | Master en ingénieur civil électricien, à finalité spécialisée en "electrical engineering" |
Faculty: | Master thesis of the Faculté des Sciences appliquées |
Abstract
[en] Image enhancement is a fascinating and complex subject because there are no known optimal resolution methods. For one picture, one person may find it too dark, while another may find it too bright. Image enhancement is very subjective.
People may want to improve image quality for a variety of causes. Blurring, fog, snow, rain and night are the main factors in image degradation.
For many years, many image enhancement techniques have been developed. Image enhancement is a powerful tool to reveal relevant data that were not, at first glance, available to the user.
On the one hand, the master's thesis proposed by CMI Defence consists in researching, studying and comparing different solutions to improve the visual quality of images from various cameras situated on weapon systems placed on military vehicles. These solutions improve the image quality by means of global and local corrections of parameters of the image (histogram, contrast, gain, hue and saturation).
On the other hand, this master's thesis consists in developing and integrating one or more solutions in a real-time video processing box.
An automation of the chosen solution is then carried out in order to be integrated into an automatic application.
This automation is based on the image quality assessment with different types of errors between original images from a personal database and corresponding blurred images by means of filters.
The main results show that the quality of an image can actually be enhanced but my conclusion is that there is no optimal choice : quality of the image is subjective and there are no better ways than the human eye to judge whether an image is better than another.
File(s)
Document(s)
Description: -
Size: 1.84 MB
Format: Adobe PDF
Description: Rapport du travail de fin d'études
Size: 17.72 MB
Format: Adobe PDF
Annexe(s)
Description: -
Size: 12.69 kB
Format: Unknown
Cite this master thesis
The University of Liège does not guarantee the scientific quality of these students' works or the accuracy of all the information they contain.