Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{179276,
        author = {Vishnu priya and Mythili D and Jefflin Biniksha V.S and Dhanya S.S},
        title = {Utilising deep learning techniques for football analysis},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {12},
        pages = {7689-7698},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=179276},
        abstract = {Football analysis has evolved significantly with the integration of deep learning and computer vision, enabling real-time player tracking and tactical evaluation. This paper presents a comprehensive football analytics system utilizing the You Only Look Once (YOLOv8) object detection algorithm, implemented with Python 3.x, Ultralytics, Supervision, OpenCV, NumPy, Matplotlib, and Pandas. The proposed system achieves high accuracy in detecting and tracking players, the ball, and key match events, thereby enhancing performance evaluation and strategic decision-making.
Our approach incorporates deep learning-based object detection to improve accuracy, facilitating precise monitoring of player positions, team formations, and dynamic events such as goals, passes, and fouls. Real-time frame-by-frame processing ensures efficient analysis, reducing dependency on manual annotation and enabling immediate tactical feedback. Experimental results demonstrate robust detection performance across various match scenarios, making the system applicable for professional coaching, sports broadcasting, and data-driven performance analysis.
This research contributes to the advancement of AI-powered sports analytics by providing a scalable, open-source solution for real-time football tracking and visualization. Future enhancements include multi-camera video fusion, integration of predictive analytics models, and adaptation to other team-based sports. The system empowers teams, analysts, and broadcasters with actionable insights, promoting more informed and timely decision-making in competitive sports environments.},
        keywords = {Football Analysis, YOLOv8, Object Detection, Deep Learning, Player Tracking, OpenCV, NumPy, Matplotlib, Pandas, Sports Analytics.},
        month = {May},
        }