An OpenPose-based System for Evaluating Rehabilitation Actions in Parkinson's Disease

With the Covid-19 raging around the world, economic and social problems are facing a considerable impact. Many patients who have undertaken rehabilitation treatment in hospitals must be forced to rehabilitate at home. To solve the problems, this paper presents a rehabilitation assistance system combining artificial intelligence and humanoid robots. First, the humanoid robot can play the role of a physical therapist, demonstrating rehabilitation movements and leading patients to rehabilitate. Second, OpenPose model is used to track the human skeleton during rehabilitation. Finally, we compare with the pre-set standard actions, calculate their similarity, and then convert them into quantitative scores for subsequent recording and tracking. The proposed method is verified on the COCO 2017 dataset and self-collected LSVT dataset, and achieves an average precision of 85.5% for skeleton detection. Experiment results from 9 subjects show that the more the non-standard actions are, the lower the score is. This proved that the presented work can provide an effective monitoring method for home rehabilitation.