VR Rehabilitation @ Home

MYONABLER@VR is a Virtual Reality (VR) that provides patients the opportunity to perform gait retraining exercises (Exergames) at home and keep up with their intervention program with low-cost equipment, even in quarantine.

Rehabilitation patients often do not adhere to and follow their treatment plan – especially in rural areas and quarantine conditions. This can be attributed to:

• The lack of technical equipment at home (treadmills, robotic exoskeletons, biofeedback monitors and sensors)
• The absence of reliable medical condition assessment methods and advice
• Motivation shortage in prolonged periods at home

MYONABLER@VR uses affordable and portable equipment coupled with deep interdisciplinary knowledge to provide advice and promote engagement for rehabilitation at home. Specifically, it employs:

• A VR headset + An ElectroMyoGraphy (EMG) sensor equipment (one-time purchase)
• The MYONABLER@VR software that provides guidance and re-training individuals to change coordination of redundant muscles and reduce load (subscription service)

The Myo EMG device (8 EMG channels, 3-axis Gyroscope-Accelerometer-Magnetic sensor) was used to capture gestures of a pottery craftsman, recognise and compare them, while also evaluating the usability of the platform.

The study is available as a publication at:

D. Ververidis, S. Karavarsamis, S. Nikolopoulos, and I. Kompatsiaris, “Pottery gestures style comparison by exploiting Myo sensor and forearm anatomy,” in Proc. ACM International Symposium on Movement and Computing (MOCO), Thessaloniki, 2016.

Kinect and IMU devices were used to capture and compare dancing steps, skeletal poses and style of a professional dancer and many amateur dancers, focusing on lower limbs.

The annotator developed to support the study is available as open-source here.

The study is available here:

S. Karavarsamis, D. Ververidis, G. Chantas, S. Nikolopoulos and Y. Kompatsiaris, “Classification of Salsa Dance Steps from Skeletal Poses,” in Proc. Intern. WS on Content Based Multimedia Indexing (CBMI), Bucharest, 2016.

The Myo EMG device (8 EMG channels, 3-axis Gyroscope-Accelerometer-Magnetic sensor) was used to reverse-engineer a 3D model of human upper limbs (to 15 muscle activation levels), using Physics and WebGL implemented using the Three.js framework.

The MyoWebToolkit web application is available as:

• A live demo here
• A video on YouTube
• Open-source here