Master Thesis Online
Superimposing perimeter banners dynamic content on soccer game videos pre-recorded from the main camera feed
Gaspar, Victor 
Promotor(s) :
Van Droogenbroeck, Marc
Date of defense : 5-Sep-2024/6-Sep-2024 • Permalink : http://hdl.handle.net/2268.2/21033
Details
| Title : | Superimposing perimeter banners dynamic content on soccer game videos pre-recorded from the main camera feed |
| Translated title : | [fr] Superposition de bannières de périmètre avec contenu dynamique sur des vidéos de matchs de football préenregistrées à partir du flux de la caméra principale |
| Author : | Gaspar, Victor
|
| Date of defense : | 5-Sep-2024/6-Sep-2024 |
| Advisor(s) : | Van Droogenbroeck, Marc
|
| Committee's member(s) : | Cioppa, Anthony
Deliège, Adrien
Hoyoux, Thomas |
| Language : | English |
| Number of pages : | 88 |
| Keywords : | [en] Banner [en] Replacement [en] Semantic segmentation [en] banner replacement [en] Superimposing [en] Compositing [en] camera calibration [en] soccer games [en] soccer [en] dynamic content [en] main camera feed [en] high resolution videos |
| Discipline(s) : | Engineering, computing & technology > Computer science |
| Research unit : | Montefiore |
| Name of the research project : | Telim |
| Target public : | Researchers Professionals of domain |
| Institution(s) : | Université de Liège, Liège, Belgique |
| Degree: | Master : ingénieur civil en informatique, à finalité spécialisée en "management" |
| Faculty: | Master thesis of the Faculté des Sciences appliquées |
Abstract
[en] Advertisement billboards around a sports field have a fixed frame but most of the time a dynamic content. This makes a precise segmentation complex.
This thesis comprises the developments of (1) a neural network capable to precisely segment billboards in a single image, (2) a temporally consistent camera calibration procedure able to reproject the billboard on the field, and (3) a compositing method for a seamless superimposition of the reprojected billboard on the field. Non-public annotations were used to train and test algorithms.
File(s)
Document(s)
TFE_Victor_Gaspar.pdf
Description:
Size: 121.05 MB
Format: Adobe PDF
Annexe(s)
banner-replacement-codes.zip
Description:
Size: 1.78 MB
Format: Unknown
videos_Qualitative_Analysis.zip
Description:
Size: 55.73 MB
Format: Unknown
summary.pdf
Description:
Size: 44.95 kB
Format: Adobe PDF
Cite this master thesis
All documents available on MatheO are protected by copyright and subject to the usual rules for fair use.
The University of Liège does not guarantee the scientific quality of these students' works or the accuracy of all the information they contain.
The University of Liège does not guarantee the scientific quality of these students' works or the accuracy of all the information they contain.