A Camera-Based Remote Sensor for Physical Therapy in Parkinson’s Disease

The present chapter shows a camera-based remote sensor for monitoring postural disorders. In recent years, several systems have been developed to capture human motion in real time using common RGB cameras. We analyze the performance of the sensor for the detection of basic body parts under a different exercise routine clinically proposed for Parkinson’s disease patients. In this study, we evaluate the ability of the OpenPose algorithm to detect specific keypoints of anatomical landmarks and estimate rotation, rate, and amplitude for head, shoulders, back, and pelvis. Based on our findings, we can say that OpenPose is a sufficiently robust algorithm that is capable of detecting slight motion parameters of a specific rehabilitation therapy, which could facilitate their use in a home environment specially in follow-up and management of the motor rehabilitation therapy for Parkinson’s disease.