VAR-YOLOv8s: IoT-based automatic foul detection in soccer matches
The application of Internet of Things (IoT) technology and its ongoing evolution have drawn a lot of interest to the field of intelligent sports referee system research. In this article, we present a novel VAR-YOLOv8 model that significantly improves the accuracy and robustness of error detection in...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-01-01
|
| Series: | Alexandria Engineering Journal |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1110016824011876 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | The application of Internet of Things (IoT) technology and its ongoing evolution have drawn a lot of interest to the field of intelligent sports referee system research. In this article, we present a novel VAR-YOLOv8 model that significantly improves the accuracy and robustness of error detection in football matches by combining MPDIoU, a residual local feature network (RLFN), and a video assistant referee system “VARS” module. Experimental results show how well the model can handle dense gates and rapidly changing parameters. It also does a good job of recognizing and classifying different types of faults in difficult situations. The concept uses Internet of Things (IoT) technology to enable real-time data collection and processing, providing strong technical support for smart sports refereeing systems, significant practical application value and many advancement opportunities. Through testing utilizing the SoccerNet dataset, the VAR-YOLOv8s demonstrate accomplished an normal IoU@0.5 of 80.5 and mAP@0.5 of 31.0 amid the testing handle. To move forward the insights and productivity of shrewd arbitrage frameworks, future investigate will center on optimizing show execution and exploring unused information enlargement and combination procedures. |
|---|---|
| ISSN: | 1110-0168 |