Error-Guided Pose Augmentation: Enhancing Rehabilitation Exercise Assessment through Targeted Data Generation

TL;DR

This paper presents Error-Guided Pose Augmentation (EGPA), a novel data generation method that improves rehabilitation exercise assessment by simulating movement errors, leading to better accuracy and interpretability in clinical and home settings.

Contribution

EGPA is the first augmentation technique specifically targeting clinically relevant biomechanical errors in rehabilitation pose data.

Findings

Up to 27.6% reduction in mean absolute error

45.8% increase in error classification accuracy

Enhanced model focus on key joints and movement phases

Abstract

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.