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{187988,
        author = {Mihir Gahukar and Sagar Janokar and Vedant Divate and Omkar Jagtap and Prajwal Gidde and Aarya Gondikar},
        title = {Real Time Football Analytics System},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {7},
        pages = {697-700},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=187988},
        abstract = {post-match analytics in association football enables coaches and analysts to identify strengths, weaknesses, and tacti- cal opportunities. However, existing professional tools are costly and often require multi-camera setups or proprietary sensors. We present the Real Time Football Analytics Sys- tem (RTFAS), a low-cost, single-camera, post-match anal- ysis pipeline built entirely with open-source Python tool- ing (OpenCV, Pandas, Matplotlib). RTFAS ingests recorded match video and automatically extracts player trajectories, team assignments, ball events, and tactical structure through:
(i) camera-to-pitch registration via homography, (ii) motion- and appearance-based multi-object tracking with Kalman filtering and global data association, (iii) possession and pass inference with graph construction, and (iv) report generation comprising player heatmaps, team formation maps, pass- ing networks, shot charts with a distance/angle-based goal- probability proxy, and possession timelines. We describe the complete architecture, algorithms, and engineering trade- offs that allow deployment on commodity hardware without GPUs. Qualitative case studies indicate that RTFAS pro- duces coherent tactical artefacts (heatmaps, pass networks, and shot maps) that align with human analyst expectations. We discuss limitations (occlusiosn, jersey-color overlap, fast ball motion) and outline extensions (multi-camera fusion, learned xG).},
        keywords = {Computer Vision, Sports Analytics, Player Tracking, Passing Network, Heatmaps, Football (Soccer), OpenCV, Data Visualization},
        month = {December},
        }