Broadcast analytics - an evaluation of video-based tracking systems with constrained player visibility.

Abstract

Advancements in recent years have enabled the generation of tracking data from broadcast videos. However, regardless of the quality of these systems, off-screen actions cannot be monitored since the athletes are not visible. The present study investigates the influence of player visibility in soccer broadcast videos on typical data analysis routines in soccer. To this end, we emulate broadcast player tracking data from two video sources (scouting feed, SF; broadcast television, TV) and compare the quality of physical and tactical performance metrics to the official player tracking data (GT) in two experiments. Experiment 1 analyzes the impact of player visibility on total distance and high-speed distance covered, while experiment 2 investigates its effect on tactical formation detection through template matching. The results show that overall 97% but less than 50% of player activity is visible in SF and TV, respectively. Experiment 1 indicates that visibility in SF and TV significantly affects the assessment of physical match intensity. Experiment 2 shows that SF visibility has no meaningful effect on formation recognition accuracy, while limited visibility in TV results in minor accuracy reductions. The findings suggest that while some tactical analysis can be reliably conducted using broadcast tracking data, physical metrics may be more susceptible to inaccuracies caused by missing data. Although data quality may be improved through interpolation of missing player trajectories, researchers and practitioners rely on transparency from data providers regarding their methods to assess the sufficiency of their data to the task at hand.