SciSports: Learning football kinematics through two-dimensional tracking data

08/14/2018
by   Anatoliy Babic, et al.
0

SciSports is a Dutch startup company specializing in football analytics. This paper describes a joint research effort with SciSports, during the Study Group Mathematics with Industry 2018 at Eindhoven, the Netherlands. The main challenge that we addressed was to automatically process empirical football players' trajectories, in order to extract useful information from them. The data provided to us was two-dimensional positional data during entire matches. We developed methods based on Newtonian mechanics and the Kalman filter, Generative Adversarial Nets and Variational Autoencoders. In addition, we trained a discriminator network to recognize and discern different movement patterns of players. The Kalman-filter approach yields an interpretable model, in which a small number of player-dependent parameters can be fit; in theory this could be used to distinguish among players. The Generative-Adversarial-Nets approach appears promising in theory, and some initial tests showed an improvement with respect to the baseline, but the limits in time and computational power meant that we could not fully explore it. We also trained a Discriminator network to distinguish between two players based on their trajectories; after training, the network managed to distinguish between some pairs of players, but not between others. After training, the Variational Autoencoders generated trajectories that are difficult to distinguish, visually, from the data. These experiments provide an indication that deep generative models can learn the underlying structure and statistics of football players' trajectories. This can serve as a starting point for determining player qualities based on such trajectory data.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/07/2017

Triple Generative Adversarial Nets

Generative Adversarial Nets (GANs) have shown promise in image generatio...
research
08/09/2023

Tracking Players in a Badminton Court by Two Cameras

This study proposes a simple method for multi-object tracking (MOT) of p...
research
11/06/2014

Conditional Generative Adversarial Nets

Generative Adversarial Nets [8] were recently introduced as a novel way ...
research
02/02/2022

Structure-preserving GANs

Generative adversarial networks (GANs), a class of distribution-learning...
research
08/31/2022

Group Activity Recognition in Basketball Tracking Data – Neural Embeddings in Team Sports (NETS)

Like many team sports, basketball involves two groups of players who eng...
research
09/27/2022

Observation Centric and Central Distance Recovery on Sports Player Tracking

Multi-Object Tracking over humans has improved rapidly with the developm...
research
06/27/2019

Detecting and classifying moments in basketball matches using sensor tracked data

Data analytics in sports is crucial to evaluate the performance of singl...

Please sign up or login with your details

Forgot password? Click here to reset