Abstract—This paper proposes a novel approach to detect and
evaluate players in football using Voronoi diagrams and a set of
metrics devised by the author. The proposed method is based on
the idea that the performance of a player can be evaluated by
analyzing the area of the field they cover during a match. To
achieve this, the positions of all players on the field are first
detected using computer vision techniques. Then, Voronoi
diagrams are used to partition the field into regions that are
closer to a particular player than any other. The area of each
player's Voronoi region is calculated and compared to the
average area of all regions to determine their level of play.
The set of metrics used to evaluate a player's performance is
based on the time spent in different regions of the field, the
distance covered, and the number of successful passes, among
others. The proposed method is evaluated on a dataset of
football matches and compared with existing methods for player
evaluation. The results show that the proposed approach
outperforms existing methods in terms of accuracy and
efficiency. Overall, this paper provides a promising new
direction for player evaluation in football using computer vision
and Voronoi diagrams.
Index Terms—Player detection, player tracking, voronoi,
opencv, YOLOv5
The authors are with Department of Information Technology Dwarkadas
J. Sanghvi College of Engineering, Mumbai, India,
*Correspondence: chiragrohra06@gmail.com (C.R.)
Cite: Shlok Asher, Monika Mangla, Chirag Rohra, Soham Desai, and Neha Agarwal, "Footy Forecast – Measuring Performance in Football," International Journal of Future Computer and Communication, vol. 12, no. 4, pp. 77-83, 2023.
Copyright © 2023 by the authors. This 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 (CC BY 4.0)
Copyright © 2008-2024. International Journal of Future Computer and Communication. All rights reserved.
E-mail: ijfcc@ejournal.net