Formation Analysis Method for Team Sports Using Deep Graph Convolutional Neural Network with Geometric Formation Features as Input

In the last decade, player and ball tracking data have increasingly been gathered and employed in various team sports, in particular invasion team sports, such as soccer, basketball, rugby, and American football. Additionally, the effectiveness of geometric analysis of formations using such tracking data has been demonstrated. Moreover, deep neural network-based methods for analyzing such tracking data have also been proposed. However, to the best of our knowledge, no research has been found that combines both, even though the benefits are seemingly apparent. In this study, against this background, we propose a formation analysis method for team sports using a deep graph neural network with geometric formation features. This method uses geometric formation features derived from a geometric formation analysis for tracking data. For initial validation, we also conduct an experiment applying this method to a soccer shooting scene classification problem with real soccer tracking data in Japan. Based on the results, we will discuss the method’s effectiveness.

I. Introduction

In the last decade, player and ball tracking data have increasingly been gathered and employed in various team sports. This trend is particularly evident in invasion team sports, such as soccer, basketball, rugby, and American football. In response to this trend, there has been an increase in research on geometric formation analysis [1]–[4], primarily focusing on computing players’ dominant areas or the adjacency information related to those dominant areas. Moreover, methods employing geometric formation features via such analysis have also gained attention [5]–[9]. Additionally, the effectiveness of both the analysis and the methods has been demonstrated with real tracking data. Meanwhile, there has been an emerging interest in exploring methods using deep neural networks for tracking data in team sports [10]–[15]. However, to the best of our knowledge, no research has been found that combines geometric formation analysis and deep neural network-based methods, even though the benefits are seemingly apparent.