Camera angle strongly affects AI quality in rehab exercise monitoring
Impact of Patient Orientation in Single- and Multi-View Camera Environments for AI-based Rehabilitation Monitoring
Computer Vision and Pattern Recognition
Summary
Tracking how well people do rehab exercises with AI depends a lot on where the camera is placed. The authors made a dataset with many angles showing both good and bad exercise attempts to study this. They created a way to measure how well AI can tell right from wrong movements depending on camera views. They found that picking the best single camera angle can improve error detection more than some 3D methods and that using two cameras gives even better results. This helps decide how to set up cameras for rehab monitoring at home or in clinics.
What this means in practice
- •For physical therapy device makers: Design rehab monitoring systems that select optimal camera angles to improve error detection in patients’ exercise videos, enhancing remote or clinical assessments.$Commercial implications: Enables development of better AI-powered rehab devices that guide camera setup to accurately track patients' movements and detect errors.
- •For home health care providers: Set up camera systems in patient homes using recommended angles to reliably assess exercise quality through automated video analysis.
Authors
Miriama Jánošová, Andreas Lang, Petra Budikova, Jan Sedmidubsky
Abstract
Automated quality assessment of rehabilitation exercises relies heavily on accurate human pose estimation from video data. Although numerous RGB-based pose estimation methods have been proposed, the impact of camera placement on detecting clinically relevant movement errors remains insufficiently explored. To address this gap, we introduce REHAB26-ViewAngles, a dataset comprising correct and incorrect rehabilitation exercise executions captured from a wide range of camera angles. Furthermore, we propose a novel separability metric to quantify an algorithm's ability to distinguish between valid and faulty exercise repetitions. Using these tools, we analyze how various RGB-based pose-estimation strategies are suitable for exercise quality assessment under varying camera placements. In particular, we analyze single-camera 2D and 3D pose estimation and four multi-camera strategies: a combination of two orthogonal 2D views, 3D triangulation, weighted 3D fusion, and an AI-based pose-estimation transformer model specifically trained from two synchronized cameras. Our findings reveal that an optimally placed 2D camera can improve the separability by 16.9\,\% over the commonly used $0^\circ$ frontal view and frequently outperforms single-camera 3D estimation, while combining two views can further improve accuracy by up to 13.1\,\%. These results offer practical guidance for deploying rehabilitation monitoring in both home and clinical settings.