We present a novel approach for segmenting and counting the repetitions of rehabilitation exercises performed by patients, based on their skeletal body joints. Skeletal body joints can be acquired through two means, depth cameras or computer vision techniques applied to RGB videos of patients. Various sequential neural networks, including many-to-many models with binary sequence output and density map output and many-to-one models with single output, are designed and implemented to analyze the sequences of skeletal body joints and perform repetition segmentation and counting. Extensive experiments on three publicly available rehabilitation exercise datasets, KIMORE, UI-PRMD, and IntelliRehabDS, demonstrate the superiority of the proposed method compared to previous methods. The proposed method enables accurate exercise analysis while preserving patient privacy, facilitating the effective delivery of virtual home-based rehabilitation programs.
Preprint: https://arxiv.org/abs/2304.09735
Note:
- This repository does not contain the preprocessed datasets, log files and our trained modified-TransRAC models.