Assessment of deep learning pose estimates for sports collision tracking

Injury assessment during sporting collisions requires estimation of the associated kinematics. While marker-based solutions are widely accepted as providing accurate and reliable measurements, setup times are lengthy and it is not always possible to outfit athletes with restrictive equipment in sporting situations. A new generation of markerless motion capture based on deep learning techniques holds promise for enabling measurement of movement in the wild. The aim of this work is to evaluate the performance of a popular deep learning model "out of the box" for human pose estimation, on a dataset of ten staged rugby tackle movements performed in a marker-based motion capture laboratory with a system of three high-speed video cameras. An analysis of the discrepancy between joint positions estimated by the marker-based and markerless systems shows that the deep learning approach performs acceptably well in most instances, although high errors exist during challenging intervals of heavy occlusion and self-occlusion. In total, 75.6% of joint position estimates are found to have a mean absolute error (MAE) of less than or equal to 25 mm, 17.8% with MAE between 25 and 50 mm and 6.7% with MAE greater than 50 mm. The mean per joint position error is 47 mm.