One of the main shortcomings of event data in football, which has been extensively used for analytics in the recent years, is that it still requires manual collection, thus limiting its availability to a reduced number of tournaments. In this work, we propose a deterministic decision tree-based algorithm to automatically extract football events using tracking data, which consists of two steps: (1) a possession step that evaluates which player was in possession of the ball at each frame in the tracking data, as well as the distinct player configurations during the time intervals where the ball is not in play to inform set piece detection; (2) an event detection step that combines the changes in ball possession computed in the first step with the laws of football to determine in-game events and set pieces. The automatically generated events are benchmarked against manually annotated events and we show that in most event categories the proposed methodology achieves $$+90\%$$ detection rate across different tournaments and tracking data providers. Finally, we demonstrate how the contextual information offered by tracking data can be leveraged to increase the granularity of auto-detected events, and exhibit how the proposed framework may be used to conduct a myriad of data analyses in football.
Three-dimensional motion capture systems such as Vicon have been used to validate commercial electronic performance and tracking systems. However, three-dimensional motion capture cannot be used for large capture areas such as a full football pitch due to the need for many fragile cameras to be placed around the capture volume and a lack of suitable depth of field of those cameras. There is a need, therefore, for a hybrid testing solution for commercial electronic performance and tracking systems using highly precise three-dimensional motion capture in a small test area and a computer vision system in other areas to test for full-pitch coverage by the commercial systems. This study aimed to establish the validity of VisionKit computer vision system against three-dimensional motion capture in a stadium environment. Ten participants undertook a series of football-specific movement tasks, including a circuit, small-sided games and a 20 m sprint. There was strong agreement between VisionKit and three-dimensional motion capture across each activity undertaken. The root mean square difference for speed was 0.04 m·s−1 and for position was 0.18 m. VisionKit had strong agreement with the criterion three-dimensional motion capture system three-dimensional motion capture for football-related movements tested in stadium environments. VisionKit can thus be used to establish the concurrent validity of other electronic performance and tracking systems in circumstances where three-dimensional motion capture cannot be used.
The visco-elastic properties of a football influence how it bounces and therefore its performance in a game. Previously, high-speed camera footage has been used to quantify deformation, coefficient of restitution and contact time for an impact between a football and a rigid surface but these systems do not provide any information on the forces acting on the football during the impact. The aim of this study was to determine the repeatability of measuring the peak impact force, impulse, rise time and loading rate for four samples of the same model of football using a commercial force platform (Kistler 9281EA). A football impacted the floor-mounted piezoelectric-type force platform at 6.04 and 19.4 m s−1. High absolute (coefficient of variation (CV) ≤ 10%) and relative (intraclass correlation coefficient (ICC) ≥ 0.94) repeatability was observed for repeated impacts at both velocities. The minimal detectable differences were calculated to evaluate the ability for the force platform to be used to make meaningful comparisons between footballs. For all metrics, the minimum detectable difference accounted for less than 5% of the mean value. Therefore, it can be concluded that provided the difference in impact metrics between football models exceeds the minimal detectable difference, the commercial force platform can be used to measure and detect differences in physical impact metrics between models of footballs.
The playing surface in football plays a pivotal role in player performance, safety, and overall game quality. With evolving regulations and continuous technological advances in football surfaces (natural, hybrid, and artificial turf), understanding their performance characteristics is essential. This study evaluated the vertical compliance and rotational stiffness of football surfaces using two test devices adopted by the FIFA Quality Programme: the Advanced Artificial Athlete and the Rotational Traction Athlete. Measurements were taken from 126 football pitches and turf samples, assessed in-situ and in the laboratory, respectively, which encompassed various natural, hybrid, and artificial turf systems. Results indicated significant differences in vertical compliance, with artificial turfs exhibiting higher peak shock absorption, greater peak deformation, and increased energy return compared to natural and hybrid turfs, suggesting that artificial turfs are more compressible and more elastic. Rotational stiffness measurements revealed that while peak torque values were similar across most surface types, natural and hybrid turfs demonstrated significantly higher resistive torque at 10 degrees of rotation than artificial systems. The findings of this study informed revisions of the performance thresholds adopted within the FIFA Quality Programme, which specify the global quality requirements for football playing surfaces.