Paper published in a book (Scientific congresses and symposiums)
Camera Calibration and Player Localization in SoccerNet-v2 and Investigation of their Representations for Action Spotting
Cioppa, Anthony; Deliège, Adrien; Magera, Floriane et al.
2021In IEEE International Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
Peer reviewed
 

Files


Full Text
Camera-calibration.pdf
Author preprint (6.34 MB)
Download

All documents in ORBi are protected by a user license.

Send to



Details



Keywords :
camera calibration; localization; soccer player; SoccerNet; action spotting; deep learning; computer vision; Sport; Sports; Football
Abstract :
[en] Soccer broadcast video understanding has been drawing a lot of attention in recent years within data scientists and industrial companies. This is mainly due to the lucrative potential unlocked by effective deep learning techniques developed in the field of computer vision. In this work, we focus on the topic of camera calibration and on its current limitations for the scientific community. More precisely, we tackle the absence of a large-scale calibration dataset and of a public calibration network trained on such a dataset. Specifically, we distill a powerful commercial calibration tool in a recent neural network architecture on the large-scale SoccerNet dataset, composed of untrimmed broadcast videos of 500 soccer games. We further release our distilled network, and leverage it to provide 3 ways of representing the calibration results along with player localization. Finally, we exploit those representations within the current best architecture for the action spotting task of SoccerNet-v2, and achieve new state-of-the-art performances.
Research center :
Montefiore Institute - Montefiore Institute of Electrical Engineering and Computer Science - ULiège
Telim
Disciplines :
Computer science
Author, co-author :
Cioppa, Anthony ;  Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Télécommunications
Deliège, Adrien ;  Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Télécommunications
Magera, Floriane ;  Université de Liège - ULiège > Montefiore Institute
Giancola, Silvio
Barnich, Olivier
Ghanem, Bernard
Van Droogenbroeck, Marc  ;  Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Télécommunications
Language :
English
Title :
Camera Calibration and Player Localization in SoccerNet-v2 and Investigation of their Representations for Action Spotting
Publication date :
June 2021
Event name :
IEEE International Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), CVsports
Event organizer :
IEEE
Event place :
Nashville, TN, United States
Event date :
du 19 juin 2021 au 25 juin 2021
Audience :
International
Main work title :
IEEE International Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
Publisher :
IEEE
Peer reviewed :
Peer reviewed
Name of the research project :
DeepSport
Funders :
FRIA - Fonds pour la Formation à la Recherche dans l'Industrie et dans l'Agriculture [BE]
DGTRE - Région wallonne. Direction générale des Technologies, de la Recherche et de l'Énergie [BE]
Commentary :
Paper accepted for the CVsports Workshop at CVPR2021.
Available on ORBi :
since 20 April 2021

Statistics


Number of views
164 (28 by ULiège)
Number of downloads
290 (11 by ULiège)

Scopus citations®
 
30
Scopus citations®
without self-citations
25
OpenCitations
 
27

Bibliography


Similar publications



Contact ORBi