Self-Supervised Learning for Human Pose Estimation in Sports

Katja Ludwig, Sebastian Scherer, Moritz Einfalt, Rainer Lienhart
2021 2021 IEEE International Conference on Multimedia & Expo Workshops (ICMEW)  
Human pose estimation (HPE) is a commonly used technique to determine derived parameters that are important to improve the performance of athletes in many sports disciplines. This paper proposes two methods to fine-tune a HPE system trained on general poses to a sports discipline specific HPE model using only a few labeled images. We show that 50 labeled 2D poses and additionally unlabeled videos are sufficient to achieve a Percentage of Correct Kexpoints (PCK) of 88.6% at a threshold of 0.1 in
more » ... the disciplines of triple and long jump, closing the gap between the supervised fine-tuning on the same 50 images and the fully supervised training on 60× more images by 60%. The first proposed method uses pseudo labels as a self-supervised training technique together with a filtering method of the pseudo labels. Furthermore, this paper shows that a mean teacher approach, which is based on consistency between a teacher and a student model, can also improve the results.
doi:10.1109/icmew53276.2021.9456000 fatcat:iebxmfrvibh53h2osn2mrsb3i4