Recognition of Full-Body Movements in VR-based Exergames using Hidden Markov Models
Key: CTF+18
Author: Polona Caserman, Thomas Tregel, Marco Fendrich, Moritz Kolvenbach, Markus Stabel, Stefan Göbel
Date: November 2018
Kind: In proceedings
Publisher: Springer
Book title: Joint International Conference on Serious Games
Keywords: Full-body tracking, Motion recognition, Machine learning, Hidden Markov model, Virtual reality, Exergames, Serious games
Abstract: Due to recent improvements in Virtual Reality (VR) regarding the potential of full-body tracking, the number of VR-based exergames has been increasing. However, such applications often depend on additional tracking technology, e.g., markerless or marker-based. On the one hand, tracking approaches, such as the Kinect device are limited by either high latency or insufficient accuracy. On the other hand, motion capture suits are expensive and create discomfort. In this paper we present an accurate motion recognition approach, using only the HTC Vive HMD with their associated Controllers and Trackers. The recognition is based on an Hidden Markov Model, that has been trained in advance for a specific movement. The results suggest that our system is capable of detecting a complex full-body gesture, such as yoga Warrior I pose, with an accuracy of 88%. In addition, audible feedback is provided, so that the user can immediately hear if the particular exercise has been executed correctly. Such a system can be used to assist players in learning a particular movement and can be applied in various serious games applications, e.g., for training purposes or rehabilitation.
View Full paper (PDF) | Download Full paper (PDF)
Official URL

The documents distributed by this server have been provided by the contributing authors as a means to ensure timely dissemination of scholarly and technical work on a non-commercial basis. Copyright and all rights therein are maintained by the authors or by other copyright holders, not withstanding that they have offered their works here electronically. It is understood that all persons copying this information will adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.