Deep Learning for Skeleton Based Human Motion Rehabilitation Assessment: A Benchmark
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916867403153408 |
|---|---|
| author | Ismail-Fawaz, Ali Devanne, Maxime Berretti, Stefano Weber, Jonathan Forestier, Germain |
| author_facet | Ismail-Fawaz, Ali Devanne, Maxime Berretti, Stefano Weber, Jonathan Forestier, Germain |
| contents | Automated assessment of human motion plays a vital role in rehabilitation, enabling objective evaluation of patient performance and progress. Unlike general human activity recognition, rehabilitation motion assessment focuses on analyzing the quality of movement within the same action class, requiring the detection of subtle deviations from ideal motion. Recent advances in deep learning and video-based skeleton extraction have opened new possibilities for accessible, scalable motion assessment using affordable devices such as smartphones or webcams. However, the field lacks standardized benchmarks, consistent evaluation protocols, and reproducible methodologies, limiting progress and comparability across studies. In this work, we address these gaps by (i) aggregating existing rehabilitation datasets into a unified archive called Rehab-Pile, (ii) proposing a general benchmarking framework for evaluating deep learning methods in this domain, and (iii) conducting extensive benchmarking of multiple architectures across classification and regression tasks. All datasets and implementations are released to the community to support transparency and reproducibility. This paper aims to establish a solid foundation for future research in automated rehabilitation assessment and foster the development of reliable, accessible, and personalized rehabilitation solutions. The datasets, source-code and results of this article are all publicly available. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_21018 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Deep Learning for Skeleton Based Human Motion Rehabilitation Assessment: A Benchmark Ismail-Fawaz, Ali Devanne, Maxime Berretti, Stefano Weber, Jonathan Forestier, Germain Computer Vision and Pattern Recognition Machine Learning Automated assessment of human motion plays a vital role in rehabilitation, enabling objective evaluation of patient performance and progress. Unlike general human activity recognition, rehabilitation motion assessment focuses on analyzing the quality of movement within the same action class, requiring the detection of subtle deviations from ideal motion. Recent advances in deep learning and video-based skeleton extraction have opened new possibilities for accessible, scalable motion assessment using affordable devices such as smartphones or webcams. However, the field lacks standardized benchmarks, consistent evaluation protocols, and reproducible methodologies, limiting progress and comparability across studies. In this work, we address these gaps by (i) aggregating existing rehabilitation datasets into a unified archive called Rehab-Pile, (ii) proposing a general benchmarking framework for evaluating deep learning methods in this domain, and (iii) conducting extensive benchmarking of multiple architectures across classification and regression tasks. All datasets and implementations are released to the community to support transparency and reproducibility. This paper aims to establish a solid foundation for future research in automated rehabilitation assessment and foster the development of reliable, accessible, and personalized rehabilitation solutions. The datasets, source-code and results of this article are all publicly available. |
| title | Deep Learning for Skeleton Based Human Motion Rehabilitation Assessment: A Benchmark |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2507.21018 |