Learning from the Pros: Extracting Professional Goalkeeper Technique from Broadcast Footage

Over the past few years there has been an increase in research into improving sports analytics using artificial intelligence (AI)-based techniques [1]. Much of this research has focused on extracting contributions of outfield players [2,3] or around team tactics [4,5]. However, there are fewer examples of research focused on the analysis of player technique, and in particular the technique of goalkeepers in soccer. This is especially the case when it comes to looking at lowerlevel players in grassroots sports where there are millions of players across the world rather than just creating models for the top 1% in the professional game.