Key points are not available for this paper at this time.
The increasing demand for remote healthcare solutions has driven the need for effective telerehabilitation systems to support elderly individuals recovering from chronic conditions or post-operative impairments. Existing rehabilitation methods face limitations such as restricted access to specialized care, overburdened healthcare providers, and the need for consistent, real-time monitoring. To address these challenges, we propose a novel telerehabilitation system that processes depth video frames using a multi-stage methodology. The pipeline begins with noise and floor removal, followed by 3D connected component labeling (CCL) to identify the human subject and extract the human silhouette. Next, skeleton joint points are estimated, and features are extracted from both the joints and silhouette. These multimodal features are fused and input into a deep learning model for classification and correctness assessment. Advanced feature extraction techniques, including Synchrosqueezing Transform (SST) and Hilbert-Huang Transform (HHT), are employed to capture dynamic time-frequency characteristics of human actions. The proposed system classifies nine distinct exercises and assesses the correctness of movements. Experimental evaluation on the IRDS dataset demonstrates a classification accuracy of 91% for exercise recognition and 82% for movement correctness assessment. These results highlight the system’s potential to deliver scalable, cost-effective, real-time rehabilitation, reducing the need for in-person clinical visits and supporting healthcare services for elderly populations.
Ashraf et al. (Wed,) studied this question.