Smart devices and AI for Rehabilitation

Project objectives: Incorporate AI into a Smart walker in order to provide real time feedback, and to store and generate relevant metrics of interest to patients and support therapists.

Context: 

The healthcare sector is under increasing pressure. Due to a shortage of personnel and an increase in the number of people in need of care, healthcare professionals have to perform more and more and often have too little time per care recipient. Smart devices and Artificial Intelligence (AI) offer a possible solution here.  

Description of the work done, and the main results obtained:  

Development of an AI Model that provides real time visual and auditory feedback and that delivers relevant information for the therapists. 
 
Thanks to a depth camera installed on the walker we were able to extract and recognize relevant data picturing contours of the feet and giving insights into the walking process/behavior. 

Creation of a user-friendly dashboard that can be used by therapists to analyze and follow up real time data about the patient’s walking process . 

This dashboard can also be used to assess the progress and evolution of the patient.

Approaches used in this project: 

• Computer Vision 
• Deep Learning (PoseNet)
Depth map 
Real-time object detection (Yolo)

 

Project Info

Start  1/03/2021

End    28/02/2023

Funding VLAIO

Project website: SAIRE

Members Prof. Dr. Johan Loeckx, Dr. Leticia Arco García, Jos Van Doorsselaere, Ivett Elena Fuentes, Joana Carolina Brites