Reference : Multimodal and multiview distillation for real-time player detection on a football field
Scientific congresses and symposiums : Paper published in a journal
Engineering, computing & technology : Electrical & electronics engineering
http://hdl.handle.net/2268/246668
Multimodal and multiview distillation for real-time player detection on a football field
English
Cioppa, Anthony* mailto [Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Télécommunications >]
Deliège, Adrien* mailto [Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Télécommunications >]
Noor, Ul Huda [> >]
Gade, Rikke [> >]
Van Droogenbroeck, Marc mailto [Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Télécommunications >]
Moeslund, Thomas B. [> >]
* These authors have contributed equally to this work.
Jun-2020
IEEE Conference on Computer Vision and Pattern Recognition. Proceedings
3846-3855
Yes
No
International
1063-6919
2575-7075
IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) - CVSports
from 14-06-2020 to 19-06-2020
IEEE
Seattle
Washington, USA
[en] multiview distillation ; multimodal distillation ; knowledge distillation ; deep learning ; player detection ; thermal camera ; fisheye camera ; real-time detection ; football ; ViBe
[en] Monitoring the occupancy of public sports facilities is essential to assess their use and to motivate their construction in new places. In the case of a football field, the area to cover is large, thus several regular cameras should be used, which makes the setup expensive and complex. As an alternative, we developed a system that detects players from a unique cheap and wide-angle fisheye camera assisted by a single narrow-angle thermal camera. In this work, we train a network in a knowledge distillation approach in which the student and the teacher have different modalities and a different view of the same scene. In particular, we design a custom data augmentation combined with a motion detection algorithm to handle the training in the region of the fisheye camera not covered by the thermal one. We show that our solution is effective in detecting players on the whole field filmed by the fisheye camera. We evaluate it quantitatively and qualitatively in the case of an online distillation, where the student detects players in real time while being continuously adapted to the latest video conditions.
Montefiore Institute of Electrical Engineering and Computer Science - Montefiore Institute ; Telim
Fonds pour la formation à la Recherche dans l'Industrie et dans l'Agriculture (Communauté française de Belgique) - FRIA ; Région wallonne : Direction générale des Technologies, de la Recherche et de l'Energie - DGTRE
DeepSport
Researchers ; Professionals
http://hdl.handle.net/2268/246668
10.1109/CVPRW50498.2020.00448
Best CVSports paper award 2020

File(s) associated to this reference

Fulltext file(s):

FileCommentaryVersionSizeAccess
Open access
Cioppa2020Multimodal.pdfMultimodal and multiview distillation for real-time player detection on a football fieldAuthor postprint5.14 MBView/Open

Bookmark and Share SFX Query

All documents in ORBi are protected by a user license.