Object detection and camera correspondence for soccer games
Bindels, Quentin
Promoteur(s) : Van Droogenbroeck, Marc
Date de soutenance : 26-jui-2019/27-jui-2019 • URL permanente : http://hdl.handle.net/2268.2/6722
Détails
Titre : | Object detection and camera correspondence for soccer games |
Auteur : | Bindels, Quentin |
Date de soutenance : | 26-jui-2019/27-jui-2019 |
Promoteur(s) : | Van Droogenbroeck, Marc |
Membre(s) du jury : | Louppe, Gilles
Wehenkel, Louis Barnich, Olivier |
Langue : | Anglais |
Nombre de pages : | 56 |
Discipline(s) : | Ingénierie, informatique & technologie > Sciences informatiques |
Institution(s) : | Université de Liège, Liège, Belgique |
Diplôme : | Master : ingénieur civil électricien, à finalité spécialisée en "signal processing and intelligent robotics" |
Faculté : | Mémoires de la Faculté des Sciences appliquées |
Résumé
[en] A sensitive cost for the broadcast industry is the employment of many operators for man-
aging the production of video content. The automation of video production is the future
of the broadcast industry for reducing its cost as well as for enhancing the experience of
its costumers. Two of the major steps to understand a game are the localization of the
images from the cameras into the soccer field and the description of the image foreground.
To do so, a solution for image localization into the soccer field for close-up view cameras
has been implemented along with an object detector for soccer. To obtain such localiza-
tion, a correspondence has been made between the main camera that can be calibrated
and a close-up view camera that can not. Then, by using the concept of transitivity, the
content of the close-up view camera can be located in the soccer field.
The correspondence between an image from the main camera and one from a close-up view
camera is accomplished by the extraction of “very large features” that an object detector
outputs. As most of the object detected are players, a patch matching algorithm is used
to differentiate them so that the features from both images can be matched. The object
detector achieves more than 70 mAP-50 on a private dataset while the patch matching
algorithm reaches an accuracy of 90%.
The overall procedure predicts an accurate localization of close-up view camera content
for 90% of the frames without exploiting the time dimension.
Fichier(s)
Document(s)
Description: -
Taille: 47.51 MB
Format: Adobe PDF
Description: -
Taille: 186.19 kB
Format: Adobe PDF
Annexe(s)
Description: -
Taille: 92.59 MB
Format: Unknown
Citer ce mémoire
L'Université de Liège ne garantit pas la qualité scientifique de ces travaux d'étudiants ni l'exactitude de l'ensemble des informations qu'ils contiennent.