Error-Guided Pose Augmentation: Enhancing Rehabilitation Exercise Assessment through Targeted Data Generation
This addresses the need for more accurate and interpretable automated movement quality assessment in clinical and home-based rehabilitation settings, representing a domain-specific incremental improvement.
The paper tackled the problem of data imbalance and subtle movement error detection in rehabilitation exercise assessment by introducing Error-Guided Pose Augmentation (EGPA), which generated synthetic skeleton data to simulate clinical errors, resulting in reductions in mean absolute error of up to 27.6% and gains in error classification accuracy of 45.8%.
Effective rehabilitation assessment is essential for monitoring patient progress, particularly in home-based settings. Existing systems often face challenges such as data imbalance and difficulty detecting subtle movement errors. This paper introduces Error-Guided Pose Augmentation (EGPA), a method that generates synthetic skeleton data by simulating clinically relevant movement mistakes. Unlike standard augmentation techniques, EGPA targets biomechanical errors observed in rehabilitation. Combined with an attention-based graph convolutional network, EGPA improves performance across multiple evaluation metrics. Experiments demonstrate reductions in mean absolute error of up to 27.6 percent and gains in error classification accuracy of 45.8 percent. Attention visualizations show that the model learns to focus on clinically significant joints and movement phases, enhancing both accuracy and interpretability. EGPA offers a promising approach for improving automated movement quality assessment in both clinical and home-based rehabilitation contexts.