Artificial intelligence application for automatic cameras piloting
Théate, Thibaut
Promotor(s) : Ernst, Damien
Date of defense : 25-Jun-2018/26-Jun-2018 • Permalink : http://hdl.handle.net/2268.2/4674
Details
Title : | Artificial intelligence application for automatic cameras piloting |
Translated title : | [fr] Application de l'intelligence artificielle pour le pilotage automatisé de caméras |
Author : | Théate, Thibaut |
Date of defense : | 25-Jun-2018/26-Jun-2018 |
Advisor(s) : | Ernst, Damien |
Committee's member(s) : | Van Droogenbroeck, Marc
Louppe, Gilles |
Language : | English |
Number of pages : | 112 |
Keywords : | [en] Artificial Intelligence [en] Reinforcement Learning [en] Robotique [en] Computer Vision |
Discipline(s) : | Engineering, computing & technology > Computer science |
Commentary : | The Master Thesis is linked with a 80 days internship in EVS Broadcast Equipment. |
Funders : | EVS Broadcast Equipment |
Research unit : | EVS Broadcast Equipment |
Target public : | Professionals of domain |
Complementary URL : | https://evs.com/en |
Institution(s) : | Université de Liège, Liège, Belgique EVS Broadcast Equipment, Ougrée, Belgique |
Degree: | Master en ingénieur civil électricien, à finalité spécialisée en "electrical engineering" |
Faculty: | Master thesis of the Faculté des Sciences appliquées |
Abstract
[en] The purpose of the Master Thesis/Internship is to evaluate/prove that the automatic
framing technology currently under development in EVS Broadcast Equipment can not
only be applied to select the interesting part of an image, but also to automatically pilot
robotic cameras. With the help of articial intelligence (Machine Learning + Computer
Vision techniques + Reinforcement Learning), the program will automatically indicate a new position to the camera, which will then focus to this new direction. The finality of this Master Thesis/Internship is to develop a first prototype which pilots a robot or a simulation, while taking care of the robot characteristics, especially its reactivity.
File(s)
Document(s)
MasterThesisThibautTheate.pdf
Description: Master Thesis
Size: 39.76 MB
Format: Adobe PDF
Description: Master Thesis
Size: 39.76 MB
Format: Adobe PDF
SummaryMasterThesis.pdf
Description: Master Thesis Summary
Size: 2.27 MB
Format: Adobe PDF
Description: Master Thesis Summary
Size: 2.27 MB
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.