Unsupervised self-rehabilitation exercises and physical training can cause serious injuries if performed incorrectly. We introduce a learning-based framework that identifies the mistakes made by a user and proposes corrective measures for easier and safer individual training. Our framework does not rely on hard-coded, heuristic rules. Instead, it learns them from data, which facilitates its adaptation to specific user needs. To this end, we use a Graph Convolutional Network (GCN) architecture acting on the user's pose sequence to model the relationship between the body joints trajectories. To evaluate our approach, we introduce a dataset with 3 different physical exercises. Our approach yields 90.9% mistake identification accuracy and successfully corrects 94.2% of the mistakes.
@article{arxiv.2208.03257,
title = {3D Pose Based Feedback for Physical Exercises},
author = {Ziyi Zhao and Sena Kiciroglu and Hugues Vinzant and Yuan Cheng and Isinsu Katircioglu and Mathieu Salzmann and Pascal Fua},
journal= {arXiv preprint arXiv:2208.03257},
year = {2022}
}