Automatic event detection in football using tracking data

Abstract

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 computational framework to automatically extract football events using tracking data, namely the coordinates of all players and the ball. Our approach consists of two models: (1) the possession model evaluates which player was in possession of the ball at each time, as well as the distinct player configurations in the time intervals where the ball is not in play; (2) the event detection model relies on the changes in ball possession to determine in-game events, namely passes, shots, crosses, saves, receptions and interceptions, as well as set pieces. First, analyze the accuracy of tracking data for determining ball possession, as well as the accuracy of the time annotations for the manually collected events. Then, we benchmark the auto-detected events with a dataset of manually annotated events to show that in most categories the proposed method achieves +90% detection rate. Lastly, 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.

Challenges and considerations in determining the quality of electronic performance & tracking systems for team sports

“…These could include the combination of additional sensors but also limb tracking which has become more feasible given the rise of vision-based markerless tracking. This potentially permits new insights into aspects such as gait parameters (79), limb tracking for informing adjudication and even automated classification of events based on spatiotemporal data (80). All of this has the potential to be good news for the end-user.…”

Integrating physical and tactical factors in football using positional data: a systematic review

“…The players and ball positioning can be computed by Cartesian and Euclidian coordinates (xx, yy) contextualizing the physical demands on the tactical behaviour ( Carrilho et al, 2020 ; Clemente et al, 2013 ; Low et al, 2019 ; Memmert, Lemmink & Sampaio, 2017 ). However, some of the above mentioned tracking methods do not allow to gather information on the player-ball-goal position ( Carrilho et al, 2020 ; Vidal-Codina et al, 2022 ), opponent-adaptive play strategy ( Memmert, 2021 ; Ranjitha, Nathan & Joseph, 2020 ) and individual tactical behavior ( Laakso et al, 2022 ; Reis & Almeida, 2020 ).…”

Re-enacting Football Matches in VR using Virtual Agents’ Realistic Behaviours

“…the virtual players, an AI model is adopted, which is built upon the work in [3], to perform real movements of the virtual players. The overall framework (see Figure 1) aims to transform positional tracking data captured during sporting events (here, a live football match) into a VR simulation which can be replayed for the purpose of the review of the re-enactments [4]. The simulation allows users (e.g.…”