EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Meta-Transfer-Learning-Based Multimodal Human Pose Estimation for Lower Limbs

Guoming Du, Haiqi Zhu, Zhen Ding, Hong Huang, Xiaofeng Bie, Feng Jiang

Sensors · 2025

DOI: 10.3390/s25051613 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2025. Verfasst von Guoming Du und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Technology, Harbin Institute of Technology, Harbin 150001, China. Hauptthemen laut MEDLINE: Lower Extremity, Posture, Machine Learning. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 71 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Central Guidance for Local Science and Technology Development Fund Projects, National Key Laboratory of Unmanned Aerial Vehicle Technology in NPU.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate and reliable human pose estimation (HPE) is essential in interactive systems, particularly for applications requiring personalized adaptation, such as controlling cooperative robots and wearable exoskeletons, especially for healthcare monitoring equipment. However, continuously maintaining diverse datasets and frequently updating models for individual adaptation are both resource intensive and time-consuming. To address these challenges, we propose a meta-transfer learning framework that integrates multimodal inputs, including high-frequency surface electromyography (sEMG), visual-inertial odometry (VIO), and high-precision image data. This framework improves both accuracy and stability through a knowledge fusion strategy, resolving the data alignment issue, ensuring seamless integration of different modalities. To further enhance adaptability, we introduce a training and adaptation framework with few-shot learning, facilitating efficient updating of encoders and decoders for dynamic feature adjustment in real-time applications. Experimental results demonstrate that our framework provides accurate, high-frequency pose estimations, particularly for intra-subject adaptation. Our approach enables efficient adaptation to new individuals with only a few new samples, providing an effective solution for personalized motion analysis with minimal data.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Lower ExtremityPostureMachine LearningHumansElectromyographyWearable Electronic DevicesAlgorithmsRoboticsExoskeleton Device

Stichwörter der Autor:innen

human pose estimationknowledge fusionmeta learningmultimodalsEMGtransfer learning

Autor:innen und Institutionen

  • School of Computer Science and Technology, Harbin Institute of Technology, Harbin 150001, China.
  • School of Medicine and Health, Harbin Institute of Technology, Harbin 150001, China.
  • College of Computer and Control Engineering, Northeast Forestry University, Harbin 150040, China.
  • School of Computer Science and Engineering, Sichuan University of Science & Engineering, Zigong 643002, China.
  • Unmanned Systems Technology Research Institute, Northwestern Polytechnical University, Xi'an 710072, China.

Förderung

  • Central Guidance for Local Science and Technology Development Fund Projects
  • National Key Laboratory of Unmanned Aerial Vehicle Technology in NPU

Zitieren

APA

Du, G., Zhu, H., Ding, Z., Huang, H., Bie, X., & Jiang, F. (2025). Meta-Transfer-Learning-Based Multimodal Human Pose Estimation for Lower Limbs. Sensors. https://doi.org/10.3390/s25051613

Vancouver

Du G, Zhu H, Ding Z, Huang H, Bie X, Jiang F. Meta-Transfer-Learning-Based Multimodal Human Pose Estimation for Lower Limbs. Sensors. 2025. doi:10.3390/s25051613

BibTeX
@article{Du2025,
  author = {Du, Guoming and Zhu, Haiqi and Ding, Zhen and Huang, Hong and Bie, Xiaofeng and Jiang, Feng},
  title = {Meta-Transfer-Learning-Based Multimodal Human Pose Estimation for Lower Limbs},
  journal = {Sensors},
  year = {2025},
  doi = {10.3390/s25051613}
}
Kostenlos starten →