Faculté des Sciences appliquées
Faculté des Sciences appliquées

Master thesis : Depth estimation from sports broadcast videos

Liesse, Valentine ULiège
Promotor(s) : Van Droogenbroeck, Marc ULiège
Date of defense : 27-Jun-2022/28-Jun-2022 • Permalink :
Title : Master thesis : Depth estimation from sports broadcast videos
Author : Liesse, Valentine ULiège
Date of defense  : 27-Jun-2022/28-Jun-2022
Advisor(s) : Van Droogenbroeck, Marc ULiège
Committee's member(s) : Barnich, Olivier 
Cioppa, Anthony ULiège
Language : English
Number of pages : 109
Keywords : [en] Deep learning
[en] computer vision
[en] depth estimation
[en] self-supervised
[en] monodepth2
[en] stereo vision
[en] monocular vision
Discipline(s) : Engineering, computing & technology > Computer science
Institution(s) : Université de Liège, Liège, Belgique
Degree: Master : ingénieur civil électricien, à finalité spécialisée en "signal processing and intelligent robotics"
Faculty: Master thesis of the Faculté des Sciences appliquées


[en] Nowadays, broadcasters must continually innovate to create compelling content that evokes emotions in viewers. Photo-realistic depth of field effect, augmented reality, or even 3D reconstruction could be one way to achieve this. Depth estimation is one of the steps to video understanding that allows these applications.

In this master thesis, methods to estimate a depth map from a single image were explored. Especially, deep learning methods were preferred to those based on geometry or the use of sensors. Thus, the solution provided by this work is entirely software-based.

In particular, a custom model has been created for a sports broadcast dataset. However, this dataset does not contain any ground truth depth map. Hence, self-supervised monocular depth estimation methods were investigated in this document. Specifically, trainings were performed with non-rectified and synchronized stereo images captured with uncalibrated cameras. In contrast to trainings based on monocular sequences, the scenes are static and the only movement is that of the camera. This is the ideal configuration for training with self-supervised methods. However, to our knowledge, we are the only ones to have attempted to train self-supervised monocular depth estimation methods using non-rectified stereo images captured with uncalibrated cameras. More precisely, in this work, the intrinsic and extrinsic parameters of the cameras are estimated during training along with the depth map.

During the course of this research, we were able to demonstrate the ability of self-supervised methods to predict coherent depth maps when trained on non-rectified stereo sports broadcast videos captured with uncalibrated cameras. Moreover, we addressed the limitations regarding the generation of depth maps under those conditions.



Access Master_thesis_LIESSE_Valentine.pdf
Size: 172.19 MB
Format: Adobe PDF


Access Images_LIESSE_Valentine.pdf
Size: 1.91 MB
Format: Adobe PDF
Access Abstract_LIESSE_Valentine.pdf
Size: 174.93 kB
Format: Adobe PDF


  • Liesse, Valentine ULiège Université de Liège > Master ingé. civ. électr., à fin.


Committee's member(s)

  • Barnich, Olivier EVS, rue Bois Saint Jean 13, 4102 SERAING
  • Cioppa, Anthony ULiège Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Robotique intelligente
    ORBi View his publications on ORBi
  • Total number of views 27
  • 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.