Time-of-Flight Camera Based Virtual Reality Interaction for Balance Rehabilitation Purposes

The 3D Human Body Models (3D HBMs) and the 3D Virtual Reality Environments (3D VREs) enable users to interact with simulated scenarios in an engaging and natural way. The Computer Vision (CV) based Motion Capture (MoCap) systems allow us to obtain user models (i.e., self-avatars) without using cumbersome and uncomfortable physical tools (e.g., sensor suites) which could adversely affect user experience. This last point is of great importance in developing interactive applications for balance rehabilitation purposes where the recovery of lost skills is related to different factors (e.g., patient motivation) including spontaneity of the interaction during the virtual rehabilitative exercises. This paper presents an overview of the Customized Rehabilitation Framework (CRF), a single range imaging sensor based system oriented to patients who experienced with brain strokes, head traumas or neurodegenerative disorders. In particular, the paper is focused on the implementation of two new ad-hoc virtual exercises (i.e., Surfboard and Swing) supporting patients in recovering physical and functional balance. Observations on accuracy of user body models and their real-time interaction ability within rehabilitative simulated environments are presented. In addition, basic experiments concerning usefulness of the proposed exercises to support balance rehabilitation purposes are also reported.