Abstract

Background: Markerless human pose estimation has the potential to revolutionize sports analytics by providing detailed insights into athlete movement. The research presented in this thesis explores how open source pose estimation can be utilized to identify goalkeeper dive initiation during soccer penalty kicks.

Purpose: The purpose of this study is to provide an accessible, low-cost heuristic methodology for identifying goalkeeper dive initiation.

Methods: This study uses high-definition single camera broadcast footage (1080p resolution, 50 frames per second) of all 41 penalty kicks attempted during the 2022 FIFA Men’s World Cup. We isolated each penalty kick from kicker run-up to kick outcome and recorded frames of goalkeeper dive initiation and flight. After creating and applying a homography matrix derived by identifying goalpost corners, we identified the goalkeeper’s skeletal keypoints through pose estimation. From these keypoints, we derived frontal plane kinematics for the torso and legs. Using a heuristic methodology, we identified local extrema for each kinematic variable. We isolated the last observed extrema prior to goalkeeper flight for each variable and used OLS regression to identify the most significant predictor of labeled dive initiation.

Results: We found that the last local extrema of the centroid’s y-value was the strongest predictor of labeled commitment to the dive side with an R2 of .998 and a p-value of 0.00. The results of this research are preliminary, but they demonstrate the effectiveness of pose estimation in identifying the initiation of goalkeeper movement during live game play using single camera broadcast footage.

Date of publication

Spring 2024

Document Type

Thesis

Language

english

Persistent identifier

http://hdl.handle.net/10950/4688

Committee members

Woohyoung Jeon, Ph.D.; Alwathiqbellah Ibrahim, Ph.D.; X. Neil Dong, Ph.D.

Degree

Masters in Kinesiology

Download

Share

COinS