EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-SA 4.0

OpenPose EfficientDet Feedback Supports Upper Limb Rehabilitation Robots in Clinical Motion Training with Environmental Cues in Clinics

Lydia Bennett, Mathieu Rolland, Serena Ferrari, Federica Ferrara

International Journal of Information and Communication Technology Trends · 01.06.2026 · 6 (1) · 307-318

DOI: 10.66525/ijictt99 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Information and Communication Technology Trends, online erschienen am 01.06.2026. Verfasst von Lydia Bennett und 3 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-SA 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Neurological disorders, particularly stroke, represent a leading cause of long-term disability worldwide, heavily impacting upper-limb motor function and diminishing the overall quality of life for millions of individuals. Traditional upper-limb rehabilitation relies extensively on manual therapy, which is highly labor-intensive, difficult to quantify, and restricted by the availability of specialized physical therapists. In response to these challenges, robotic rehabilitation has emerged as a promising adjunct to clinical practice. However, many current robotic systems lack real-time, context-aware visual feedback mechanisms that can accurately interpret both patient kinematics and interaction with therapeutic objects. This paper proposes a novel framework integrating the OpenPose human pose estimation algorithm and the EfficientDet object detection architecture to provide comprehensive motion and environmental feedback for upper-limb rehabilitation robots in clinical settings. By combining markerless skeletal tracking with high-efficiency object recognition, the proposed system enables robots to adaptively adjust task difficulty and provide corrective guidance based on the precise spatial relationship between the patient and the target objects. The methodology outlines the integration of these two deep learning pipelines, detailing the synchronization and data fusion processes required for low-latency clinical applications. Experimental validation in a controlled clinical environment demonstrates significant improvements in kinematic tracking accuracy, therapeutic object interaction detection, and overall system responsiveness. Furthermore, qualitative assessments suggest enhanced patient engagement and adherence due to the immediate, visually driven corrective feedback. The findings indicate that the unified OpenPose-EfficientDet framework offers a robust, scalable, and highly effective solution for advancing intelligent robotic rehabilitation therapies.

Zitieren

APA

Bennett, L., Rolland, M., Ferrari, S., & Ferrara, F. (2026). OpenPose EfficientDet Feedback Supports Upper Limb Rehabilitation Robots in Clinical Motion Training with Environmental Cues in Clinics. International Journal of Information and Communication Technology Trends, 6(1), 307-318. https://doi.org/10.66525/ijictt99

Vancouver

Bennett L, Rolland M, Ferrari S, Ferrara F. OpenPose EfficientDet Feedback Supports Upper Limb Rehabilitation Robots in Clinical Motion Training with Environmental Cues in Clinics. International Journal of Information and Communication Technology Trends. 2026;6(1):307-318. doi:10.66525/ijictt99

BibTeX
@article{Bennett2026,
  author = {Bennett, Lydia and Rolland, Mathieu and Ferrari, Serena and Ferrara, Federica},
  title = {OpenPose EfficientDet Feedback Supports Upper Limb Rehabilitation Robots in Clinical Motion Training with Environmental Cues in Clinics},
  journal = {International Journal of Information and Communication Technology Trends},
  year = {2026},
  volume = {6},
  number = {1},
  pages = {307--318},
  doi = {10.66525/ijictt99}
}
Kostenlos starten →