Feedback

Faculté des Sciences appliquées
Faculté des Sciences appliquées
MASTER THESIS
VIEW 173 | DOWNLOAD 3

Master thesis : Automatic identification of football players based on game video sequences for the production of metadata

Download
Michel, Tom ULiège
Promotor(s) : Wehenkel, Louis ULiège ; Van Droogenbroeck, Marc ULiège
Date of defense : 26-Jun-2017/27-Jun-2017 • Permalink : http://hdl.handle.net/2268.2/2550
Details
Title : Master thesis : Automatic identification of football players based on game video sequences for the production of metadata
Translated title : [fr] Identification automatique de joueurs de football basée sur des séquences vidéo de match pour la production de métadonnées
Author : Michel, Tom ULiège
Date of defense  : 26-Jun-2017/27-Jun-2017
Advisor(s) : Wehenkel, Louis ULiège
Van Droogenbroeck, Marc ULiège
Committee's member(s) : Geurts, Pierre ULiège
Barnich, Olivier 
Language : English
Number of pages : 133
Keywords : [en] Football
[en] Deep learning
[en] Machine learning
[en] Computer vision
[en] Player identification
Discipline(s) : Engineering, computing & technology > Electrical & electronics engineering
Funders : EVS Broadcast Equipment
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] For the broadcast of live football games, a lot of people are required: the director chooses at any time the most interesting camera to show on TV while the so-called loggers encode the statistics of the match. More and more, we try to help those people by automating their tasks. To do so, artificial intelligence methods must be developed for computers to understand what happens on the pitch. In order to achieve this goal, many subproblems must be solved separately. Automatic identification of players is one of them. This master thesis tries to handle this specific problem by focusing on the players numbers. The whole work is separated into 3 main parts: player detection, digit detection and digit recognition. Those different tasks are tackled with the help of computer vision and deep learning techniques. In particular, a segmentation semantic method is implemented. This allows us to know whether a pixel in the image belongs to a player or a digit with an accuracy higher than 98%. Digit recognition also obtains very promising performances. On the whole, this master thesis offers an array of techniques for each individual task. With more training data, those techniques would give robust models that could be applied to any football game.


File(s)

Document(s)

File
Access Master thesis report - Tom MICHEL.pdf
Description:
Size: 55.42 MB
Format: Adobe PDF

Annexe(s)

File
Access Codes.zip
Description: Folder containing the source code developed in this master thesis.
Size: 56.22 kB
Format: Unknown
File
Access Videos.zip
Description: Folder containing some videos of the main results of this master thesis.
Size: 78.37 MB
Format: Unknown
File
Access Abstract.pdf
Description: One page summary with illustrations.
Size: 1.75 MB
Format: Adobe PDF

Author

  • Michel, Tom ULiège Université de Liège > Master ingé. civ. électr., à fin.

Promotor(s)

Committee's member(s)

  • Geurts, Pierre ULiège Université de Liège - ULg > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Algorith. des syst. en interaction avec le monde physique
    ORBi View his publications on ORBi
  • Barnich, Olivier EVS, rue Bois Saint Jean 13, 4102 SERAING
  • Total number of views 173
  • Total number of downloads 3










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.