Exercise Monitoring System Using Hybrid Intelligence: Feature Space

Formation of the feature space for a system that monitors physical exercises and generates personalized recommendations for corrections on the basis of rules used by an expert trainer is described. Human pose estimation (HPE) methods are used to digitally represent exercise performance. The feature space should represent HPE data (coordinates of human body parts) as a set of feature values for generating recommendations (such as exercise intensity and user endurance). The feature space plays a central role in the development of such systems: the richer the space is, the better the recommendations can be implemented.