| Title |
Basketball board detection using YOLO algorithms / |
| Authors |
Širmenis, Juozas ; Lukoševičius, Mantas |
| DOI |
10.15388/Proceedings.2024.44 |
| Full Text |
|
| Is Part of |
IVUS2024: 29th international conference "Information society and university studies", Vilnius University, Kaunas Faculty, Kaunas, Lithuania, May 17th, 2024: abstracts.. Vilnius : Vilniaus universiteto leidykla. 2024, p. 33 |
| Abstract [eng] |
This research aims to detect basketball board, rim, net, and shooting box using different versions of the YOLO algorithm: YOLOv5, YOLOv7, and YOLOv9. The study found that the YOLOv9-C model provided the best performance with a precision of 0.996, recall of 1, mAP_0.5 of 0.995, and mAP_0.5-0.95 of 0.899. The YOLOv9 models also demonstrated fast training times with a low number of epochs. Meanwhile, YOLOv5 showed the fastest inference time for the detection task, and YOLOv7 was the smallest model in terms of size. |
| Published |
Vilnius : Vilniaus universiteto leidykla |
| Type |
Conference paper |
| Language |
English |
| Publication date |
2024 |
| CC license |
|
