User-friendly computer vision based rehabilitation services (CV rehab)

Background and goals

Researchers have noted that telerehabilitation (TR) has been used more frequently in the last few years due to the COVID-19 pandemic, which has forced healthcare organisations to use
TR as part of healthcare professionals’ daily practices. For many healthcare professionals’, the rapid implementation of TR came with limited preparation and a lack of continuing education. TR refers to healthcare services delivered to clients
through information and communication technology (ICT), and it can improve the availability of healthcare services. Providing easily and equally achieved rehabilitation
services is a significant challenge due to, among others, the aging population and the concentration of healthcare services to urban areas. A significant advantage of TR for the
clients is that they do not need to travel to the therapy and hence saving both time and cost. A promising and new way of implementing automatic real-time TR is
through computer vision (CV) as the only technical equipment needed is one or more cameras and a computing device, such as laptop, tablet or smartphone. These applications can range from automatic rehabilitation aids giving real time feedback and instruction to clients performing therapeutic exercises to software analyzing the technical performance of a professional
athlete. Traditionally CV-based solutions for motion analysis though involved installation of markers (such as white dots or other reflective material) on different parts of the body. A significantly more practical, cost effective and easy-to- use solution is a CV based marker-less motion detection system. Collecting accurate motion data without the use of markers is a challenging and a relevant research topic.

Our vision in this long-term interdisciplinary research project is to, in close collaboration with students, companies, researchers and partner universities, develop CV-based rehabilitation applications that can be registered as health technology and implemented in e.g. hospitals and health
care clinics daily practice. These applications, shall provide automatic guidance, counselling and measurements for clients in the rehabilitation process by using a low-cost and easy to use device (such as a computer with a web camera, social robots or a mobile device) and will be integrated with Kanta Personal Health Record. (https://www.kanta.fi/en/system-develope… with-kanta-phr). This project started in august 2019 and so far, 38 publications (of which 17 are peer reviewed and accepted) have been produced including research articles and papers, seminar presentations, workshop presentations and bachelor theses. CV prototype applications for automatic
real-time joint angle measurements and functional movements in 2-dimension space have been developed, tested and evaluated by information technology and physiotherapy students and researchers at Arcada. While promising results have been achieved, further testing and development
is required before these prototypes can be implemented in clinical use in hospitals or rehabilitation centers and registered as health technology. The goal for the academic year 2023-2024 is thus to continue the improvement and evaluation process of our current CV prototypes while at the same
time focus on making our prototypes more user-friendly and integrate them in everyday devices, such as smartphone/tablet and social robots. We will also continue publishing research results in the field
of CV and TR.

Objectives and benefits

The long-term objective is to in close collaboration with students, companies, and partner universities develop prototype applications that can be registered as health technology and provide automatic guidance for clients doing rehabilitation exercises by using a low-cost and easy to use device, such as a computer with a web camera or a mobile device.

Societal impact

The project contributes to telerehabilitation and motion analysis applications for preemptive health care which is important for (among others) the aging population.

Abstract

The aging population and the recent corona pandemic, among others, have increased the need for easy-to-use, cost effective and reliable telerehabilitation services. Computer vision-based marker-less human pose estimation is a promising technique for telerehabilitation as the only technical equipment needed is a camera and a computing device. With this equipment, the rehabilitation application is able to analyse and supervise clients’ exercises and reduce clients’ need for visiting physiotherapists in person.The long-term goal is to in close collaboration with students, companies, and partner universities develop prototype applications that can be register as health technology and provide automatic guidance for clients doing rehabilitation exercises.