Feedback

Faculté des Sciences appliquées
Faculté des Sciences appliquées
MASTER THESIS
VIEW 25 | DOWNLOAD 0

Master thesis : How to use deep learning techniques to create a high framerate video feeds from a regular camera, allowing to generate supermotion replays based on regular camera feeds

Download
Pitz, Adrien ULiège
Promotor(s) : Van Droogenbroeck, Marc ULiège
Date of defense : 25-Jun-2018/26-Jun-2018 • Permalink : http://hdl.handle.net/2268.2/4520
Details
Title : Master thesis : How to use deep learning techniques to create a high framerate video feeds from a regular camera, allowing to generate supermotion replays based on regular camera feeds
Translated title : [fr] Comment, depuis une caméra régulière, générer une vidéo avec un grand nombre d'images par seconde, permettant ainsi de générer des ralentis
Author : Pitz, Adrien ULiège
Date of defense  : 25-Jun-2018/26-Jun-2018
Advisor(s) : Van Droogenbroeck, Marc ULiège
Committee's member(s) : Louveaux, Quentin ULiège
Van Lishout, François ULiège
Boigelot, Bernard ULiège
Language : English
Number of pages : 105
Keywords : [fr] Interpolation
[fr] Image
[fr] Deep Learning
[fr] Machine Learning
[fr] Video
[fr] Frame
[fr] Convolution
[fr] EVS
[en] Interpolation
[en] Image
[en] Deep Learning
[en] Machine Learning
[en] Video
[en] Frame
[en] Convolution
[en] EVS
Discipline(s) : Engineering, computing & technology > Computer science
Institution(s) : Université de Liège, Liège, Belgique
EVS, Liège, Belgique
Degree: Master en sciences informatiques, à finalité spécialisée en "intelligent systems"
Faculty: Master thesis of the Faculté des Sciences appliquées

Abstract

[fr] The objective is to start from existing techniques and test those techniques in the case of fast moving sports images, and to propose / implement / test extensions where needed


File(s)

Document(s)

File
Access Adrien PITZ - Deep Learning to create Slow Motion videos - Summary.pdf
Description: Summary
Size: 132.59 kB
Format: Adobe PDF
File
Access Adrien PITZ - Deep Learning to create Slow Motion videos - Master Thesis.pdf
Description: Actual master thesis
Size: 26.21 MB
Format: Adobe PDF

Annexe(s)

File
Access 00- Original Pre-Trained SepConv slowx4.mp4
Description: Slow mo video with the original Adaptive Separable Convolution project
Size: 38.67 MB
Format: Unknown
File
Access 01- Customized SepConv - 24000 general slowx4.mp4
Description: Slow motion video x4 with the customized Adaptive Separable Convolution using 24.000 patches at random
Size: 37.89 MB
Format: Unknown
File
Access 02- Customized SepConv - general and balls slow x4 - FINAL RESULT.mp4
Description: Slow motion x4 with the customized Adaptive Separable Convolution with random patches and tennis balls patches
Size: 37.23 MB
Format: Unknown

Author

  • Pitz, Adrien ULiège Université de Liège > Master sc. informatiques, à fin.

Promotor(s)

Committee's member(s)

  • Louveaux, Quentin ULiège Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Systèmes et modélisation : Optimisation discrète
    ORBi View his publications on ORBi
  • Van Lishout, François ULiège Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Systèmes et modélisation
    ORBi View his publications on ORBi
  • Boigelot, Bernard ULiège Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Informatique
    ORBi View his publications on ORBi
  • Total number of views 25
  • Total number of downloads 0










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.