Football analytics based on player tracking data using interpolation techniques for the prediction of missing coordinates
Keywords:Football Analytics, player tracking data, missing data, interpolation
In recent days we have seen an increasing interest in using tracking data for sports and especially for football. Such data can reveal the location of the players and the ball many times per second allowing for examining tactics, efficiency of players, formations, and many others characteristics of the game. Unfortunately, such systems are still expensive, and their data are not widely available. As an alternative, limited tracking data can be obtained from broadcasting videos. They are of less quality and of course the are censored in the sense that they do not provide information for all players but only those in the frame taken. Within this framework, the primary aim of this paper, is the exploration of the most suitable method for retrieving the missing information of players’ and ball’s positions and rectify as much as possible the effect of censoring which leads to discontinuous player tracks and unreliable player identification. In this paper we explored and compared different interpolation methodologies. Moreover, we tried to distinguish possible differences between the actual data, as they were tracked from the camera and the interpolated data that have been estimated from our best selected method, by extracting insights that are mainly based on tactical analyses as well as on players’ performances.
How to Cite
Copyright (c) 2023 Statistica Applicata - Italian Journal of Applied Statistics
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.