A Multi-Kinect System for Serious Game Development Using ROS and Unity

Game-based rehabilitation systems are often proposed as an appropriate technology for improving patients’ motivation during the therapy. They have potential to increase the intensity and frequency of physical activity of stroke patients. In this work we present a Unity integrated ROS-based multi-Kinect system for serious game development. A multi-camera setup offers the advantages of enabling the player (patient) to walk along a wider area and minimizes the risk of occlusion due to people moving along the camera’s detection area or even to the patient’s own body. The proposed system merges the user joint position provided by multiple Kinect V2 sensors and delivers the results to Unity. A linking mechanism was used so that Unity can listen to and inject messages into ROS environment. We present data from a preliminary technical validation, which consists of an interface controlled by hand movements. The results show that 98.8% of the data obtained by the system were consistent with the user’s actions.

[1]  P. Mojiri Forooshani,et al.  From ROS to unity: Leveraging robot and virtual environment middleware for immersive teleoperation , 2014, 2014 IEEE International Conference on Information and Automation (ICIA).

[2]  George A. Mensah,et al.  The atlas of heart disease and stroke , 2005 .

[3]  Greg Welch,et al.  An Introduction to Kalman Filter , 1995, SIGGRAPH 2001.

[4]  Robert Teasell,et al.  Efficacy and safety of non-immersive virtual reality exercising in stroke rehabilitation (EVREST): a randomised, multicentre, single-blind, controlled trial , 2016, The Lancet Neurology.

[5]  Bin He,et al.  Brain-Computer Interface Control in a Virtual Reality Environment and Applications for the Internet of Things , 2018, IEEE Access.

[6]  J. McComas,et al.  Benefits of activity and virtual reality based balance exercise programmes for adults with traumatic brain injury: Perceptions of participants and their caregivers , 2005, Brain injury.

[7]  R. E. Kalman,et al.  A New Approach to Linear Filtering and Prediction Problems , 2002 .

[8]  Réjean Hébert,et al.  Impact of Motor, Cognitive, and Perceptual Disorders on Ability to Perform Activities of Daily Living After Stroke , 2001, Stroke.

[9]  Diego Torricelli,et al.  Hybrid robotic systems for upper limb rehabilitation after stroke: A review. , 2016, Medical engineering & physics.

[10]  N B Lincoln,et al.  An investigation of factors affecting progress of patients on a stroke unit. , 1989, Journal of neurology, neurosurgery, and psychiatry.

[11]  Il Hong Suh,et al.  Multiple Kinect Sensor Fusion for Human Skeleton Tracking Using Kalman Filtering , 2016 .

[12]  J. A. Stevens,et al.  Using motor imagery in the rehabilitation of hemiparesis. , 2003, Archives of physical medicine and rehabilitation.

[13]  Dae-Sung Park,et al.  Effects of Virtual Reality Training using Xbox Kinect on Motor Function in Stroke Survivors: A Preliminary Study. , 2017, Journal of stroke and cerebrovascular diseases : the official journal of National Stroke Association.

[14]  Matei Mancas,et al.  Robotic-assisted serious game for motor and cognitive post-stroke rehabilitation , 2017, 2017 IEEE 5th International Conference on Serious Games and Applications for Health (SeGAH).

[15]  A. Fugl-Meyer,et al.  Motor and perceptual impairments in acute stroke patients: effects on self-care ability. , 1987, Stroke.

[16]  Olivier Lambercy,et al.  Assessment-driven arm therapy at home using an IMU-based virtual reality system , 2015, 2015 IEEE International Conference on Rehabilitation Robotics (ICORR).