Continuous football player tracking from discrete broadcast data

TL;DR

This paper introduces a method to estimate continuous player tracking data from low-quality broadcast footage, making it accessible for teams that lack high-quality video feeds.

Contribution

The novel method enables affordable and scalable player tracking using discrete broadcast data, bridging the gap for teams without high-quality video.

Findings

The method was tested successfully using open-source tracking data.

A version of the method can be applied to over 200 games with discrete data.

The approach offers a cost-effective alternative to traditional high-quality tracking systems.

Abstract

Player tracking data remain out of reach for many professional football teams, as their video feeds are not sufficiently high quality for computer vision technologies to be used. To help bridge this gap, we present a method that can estimate continuous full-pitch tracking data from discrete data made from broadcast footage. Such data could be collected by clubs or players at a similar cost to event data, which are widely available down to the semi-professional level. We test our method using open-source tracking data and include a version that can be applied to a large set of over 200 games with such discrete data.

Figures