Bachtiar, Fayza Aqila (2025) Implementation and Analysis of a Soccer Match Analysis Program (via Video). Project Report. [s.n], [s.l.]. (Unpublished)
|
Text
5025221087-Project_Report.pdf - Accepted Version Restricted to Repository staff only Download (859kB) | Request a copy |
Abstract
This study presents a real-time soccer player tracking system utilizing fine-tuned YOLO11n and YOLO12n object detection models on England Premier League match footage from
2014-2016. The system employs automatic frame extraction, COCO-pretrained auto-labeling, and data augmentation techniques including HSV adjustments, geometric transformations, and mosaic augmentation. Evaluation on 2,000 validation images containing 17,468 labeled instances demonstrates that YOLO11n outperforms YOLO12n, achieving mAP50 of 0.9624, mAP50-95 of 0.7848, precision of 0.9192, and recall of 0.9193. The implementation features IoU-based identity tracking and interactive player spotlight visualization with near-real-time performance. Despite strong detection accuracy, persistent challenges include ID assignment inconsistencies during goalkeeper detection and occlusion scenarios, indicating architectural limitations requiring future enhancement beyond preprocessing refinements
| Item Type: | Monograph (Project Report) |
|---|---|
| Uncontrolled Keywords: | Object Detection, Player Tracking, Soccer, YOLO |
| Subjects: | T Technology > T Technology (General) T Technology > T Technology (General) > T385 Visualization--Technique T Technology > T Technology (General) > T57.5 Data Processing T Technology > T Technology (General) > T57.62 Simulation T Technology > T Technology (General) > T58.62 Decision support systems T Technology > T Technology (General) > T59.7 Human-machine systems. |
| Divisions: | Faculty of Industrial Technology > Informatics Engineering > 55201-(S1) Undergraduate Thesis |
| Depositing User: | Fayza Aqila Bachtiar |
| Date Deposited: | 12 Jan 2026 08:54 |
| Last Modified: | 12 Jan 2026 08:54 |
| URI: | http://repository.its.ac.id/id/eprint/129514 |
Actions (login required)
![]() |
View Item |
