Automatic Edge Error Judgment in Figure Skating Using 3D Pose Estimation from Inertial Sensors

Objective evaluation of athletes’ skills is fundamental in scoring sports such as figure skating. However, previous studies have evaluated skaters’ skills only in two-dimensional analysis. In this study, we propose an automatic edge error judgment system with three-dimensional analysis using inertial sensors, which is one of the most challenging and significant scoring items. The results show that the model using the left ice skate angle as the input feature had the highest accuracy at 74% for unknown skaters’ data, not in the training data. These results indicate that inertial sensors can be used to judge edge errors automatically.