This project investigates the development of an artificial intelligence-based system for automated movement analysis and feedback in physical therapy and rehabilitation settings using computer vision and human pose estimation technologies.

The framework extracts body keypoints from video sequences, computes joint angles and temporal motion features, and compares patient movements with reference demonstrations to generate quantitative performance scores. The approach enables objective evaluation of rehabilitation exercises and supports remote therapy delivery without requiring specialised motion capture hardware.

The research contributes to the emerging field of digital rehabilitation and intelligent healthcare monitoring, with potential applications in physiotherapy, sports science, and assistive healthcare technologies.

Pose estimation for rehabilitation movement

Human pose estimation used for automated assessment of rehabilitation exercises.

This work was conducted in collaboration with industry partners, including 🌐 Agile Kinetic, a digital health company specialising in artificial intelligence solutions for movement analysis and remote clinical monitoring. Their technology focuses on making movement assessment accessible using standard consumer devices and scalable software platforms for healthcare applications.


Key Contributions


Technologies

Computer vision · Human pose estimation · Machine learning · Healthcare AI · Movement analysis · Digital health · Rehabilitation technology


Industry Collaboration

Agile Kinetic — Digital Health Technology Partner

🌐 Company Website


Journal Publication

A real time action scoring system for movement analysis and feedback in physical therapy using human pose estimation Scientific Reports (Nature Portfolio), 2025

📄 View Article