EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Toward intelligent rehabilitation: Multimodal human pose modeling with parametric meshes and graph-based temporal reasoning

Aleena Kamal, Yanfeng Wu, Shaheryar Najam iD, Nouf Abdullah Almujally, Ahmad Jalal iD, Hui Liu

DIGITAL HEALTH · 2026-02 · 12

DOI: 10.1177/20552076261417873 ↗

Kurz gefasst

Fachartikel in der Zeitschrift DIGITAL HEALTH, online erschienen am 24.04.2026. Verfasst von Aleena Kamal und 5 weiteren Autor:innen. Beteiligte Einrichtung: Guodian Nanjing Automation Co., Ltd, Nanjing, China. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 54 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

Accurate assessment of physiotherapy exercises is critical for effective rehabilitation, particularly for elderly and mobility-impaired individuals. While telerehabilitation offers a viable alternative to in-clinic supervision, existing approaches often rely on single-modality sensors, limiting robustness and adaptability. This study aims to develop a multimodal, markerless framework for reliable home-based physiotherapy exercise recognition.

Methods

A deep learning–based multimodal framework is proposed that integrates synchronized RGB and depth streams. From RGB data, two-dimensional keypoints, semantic body-part labels, and contour-based visual descriptors are extracted. Depth silhouettes are used to estimate three-dimensional joint positions and reconstruct full-body meshes using the Skinned Multi-Person Linear model, along with global shape descriptors such as Zernike moments. Multimodal features are fused and refined using Kernel Fisher Discriminant Analysis, followed by classification using a Graph Convolutional Network to capture spatial and temporal relationships.

Results

The proposed framework was evaluated on three publicly available rehabilitation datasets: KIMORE, mRI, and UTKinect-Action3D. The system achieved classification accuracies of 95.30%, 92.70%, and 95.59%, respectively, demonstrating consistent performance across diverse rehabilitation-oriented benchmarks.

Conclusions

The results suggest that integrating complementary RGB and depth-based representations can enhance robustness and accuracy in physiotherapy exercise recognition under home-based settings. The proposed framework shows potential for supporting accessible telerehabilitation, while future work will focus on broader validation and practical deployment considerations.

Schlagwörter

Stichwörter der Autor:innen

3D human mesh reconstructionGraph Convolutional NetworkKernel Fisher Discriminant AnalysisMultimodal physiotherapy recognitionRGB-Depth fusionZernike momentstelerehabilitation

Autor:innen und Institutionen

  • Guodian Nanjing Automation Co., Ltd, Nanjing, China.
  • Department of Biomedical Engineering, Riphah International University, Islamabad, Pakistan.
  • Department of Electrical Engineering, Bahria University, Islamabad, Pakistan.
  • Department of Information Systems, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, Riyadh, Saudi Arabia.
  • Department of Computer Science, Air University, Islamabad, Pakistan.
  • Department of Computer Science and Engineering, College of Informatics, Korea University, Seoul, South Korea.

ORCID-Profile: Shaheryar Najam, Ahmad Jalal

Zitieren

APA

Kamal, A., Wu, Y., Najam, S., Almujally, N. A., Jalal, A., & Liu, H. (2026). Toward intelligent rehabilitation: Multimodal human pose modeling with parametric meshes and graph-based temporal reasoning. DIGITAL HEALTH, 12. https://doi.org/10.1177/20552076261417873

Vancouver

Kamal A, Wu Y, Najam S, Almujally NA, Jalal A, Liu H. Toward intelligent rehabilitation: Multimodal human pose modeling with parametric meshes and graph-based temporal reasoning. DIGITAL HEALTH. 2026;12. doi:10.1177/20552076261417873

BibTeX
@article{Kamal2026,
  author = {Kamal, Aleena and Wu, Yanfeng and Najam, Shaheryar and Almujally, Nouf Abdullah and Jalal, Ahmad and Liu, Hui},
  title = {Toward intelligent rehabilitation: Multimodal human pose modeling with parametric meshes and graph-based temporal reasoning},
  journal = {DIGITAL HEALTH},
  year = {2026},
  volume = {12},
  doi = {10.1177/20552076261417873}
}
Kostenlos starten →