A Point Cloud Transformer for Remote Monitoring and Automated Assessment of Physical Rehabilitation Exercises
2026-06-29 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors developed a new computer method to help people do physical therapy exercises correctly at home. Their system uses special cameras to track joint positions and analyzes this data with a transformer model to judge exercise quality. They improved how the model looks at joint data by adding a technique that focuses on important joint movements. Their approach is faster and smaller than past methods, making it practical for everyday use. They tested it on several standard rehabilitation exercise datasets and found it worked better than existing systems.
rehabilitation exercisesRGBD imagespoint cloudstransformer modelaxial self-attentionjoint position trackingfeature aggregationphysical therapyexercise assessmentmachine learning
Authors
Kazi Rafat, Md. Ismail Hossain, M M Lutfe Elahi, Sifat Momen, Fuad Rahman, Nabeel Mohammed, Shafin Rahman
Abstract
Rehabilitation exercises are essential in restoring lost physical functions of patients suffering from various diseases (e.g., Parkinson's, back pain). Carrying out these rehabilitation exercises, often prescribed by health experts, is costly, unavailable, and requires expert supervision. The availability of RGBD images and movement/position data of joints along with expert annotation of exercise data has prompted the use of automatic assessment of the quality of rehabilitation exercises, which is cost-effective and can be carried out at home. However, existing approaches do not extract relevant features, lack practical application, require expensive pre-processing, or overlook crucial features. This study proposes a transformer-based framework for point clouds to extract features and assess rehabilitation exercises by analyzing joint positions collected through RGBD data. We adapt and utilize a curve-based point-cloud feature aggregation technique to augment point-cloud information that aids model output. The transformer architecture also uses axial self-attention, recognizing important joints and their roles to assist users in performing the exercise better. The guided system outperforms existing approaches and is also practically relevant due to its small size, fast inference, and generalization on specific joints in similar exercises. We conduct our experiments on three crucial baseline datasets for rehabilitation exercises: Kimore, UI-PRMD, and IRDS.