Interpolation Methods for MediaPipe Hand Tracking Gaps: A Pose-Based Approach
Studies in Health Technology and Informatics · 2026
DOI: 10.3233/shti261006 ↗Kurz gefasst
Fachartikel in der Zeitschrift Studies in Health Technology and Informatics, 2026. Verfasst von Solveig Kathleen Najork und 6 weiteren Autor:innen. Beteiligte Einrichtung: German Research Center for Artificial Intelligence (DFKI), Luebeck, Germany. Hauptthemen laut MEDLINE: Hand. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
Introduction
Kinematics are a relevant measure of movement quality, especially for physically restricted patients. Therefore, consistent landmark detection is necessary. Automated landmarks detection already has existing solutions, but a problem remains: missing frames, where landmarks cannot be automatically detected.
Methods
This paper evaluates three interpolation strategies to overcome this issue and thus enable kinematic analysis. These strategies are linear interpolation, the Kalman filter, and the developed pose-based approach. Recordings were obtained using the marker-based VICON system.
Participants
(n = 3) performed three tasks inspired by a standard stroke assessment. This setup allows the precision of marker-less detection and interpolation to be evaluated.
Results
In comparison with Percentage Root Mean Square Error (PRMSE) and the Procrustes mean disparity, linear interpolation yields the best results. It achieved a mean PRMSE of 36.5 and a mean disparity of 0.266. The pose-based approach, presented here, follows closely with a mean PRMSE of 36.6 and a mean disparity of 0.273. The use of Kalman filtering resulted in a mean disparity of 0.314 and a PRMSE of 35.7. The results were tested positive for significance using the Kolmogorov-Smirnov test.
Discussion
In subsequent optical evaluations, the pose-based approach demonstrated superior performance; it was possible to observe that the linear approach sometimes lags behind the movement, while the pose-based interpolation follows the movement of the subject. Our results demonstrate that a reliable estimate with consistent landmarks is possible, thus enabling kinematic analysis.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- German Research Center for Artificial Intelligence (DFKI), Luebeck, Germany.
- Fraunhofer Research Institution for Individualized Medical Technology and Engineering (IMTE), Luebeck, Germany.
- Center of Brain, Behavior and Metabolism, University of Luebeck, Luebeck, Germany.
- Department of Neurology, University Hospitals Schleswig-Holstein, Luebeck, Germany.
- Department of Neurology and Experimental Neurology, Charité-University Medicine Berlin, Berlin, Germany.
- Institute of Medical Informatics, University of Luebeck, Luebeck, Germany.
Zitieren
APA
Najork, S. K., Weber, M., Bücken, G., Maass, M., Kunkel Gen Bode, L., Koch, P. J., & Grzegorzek, M. (2026). Interpolation Methods for MediaPipe Hand Tracking Gaps: A Pose-Based Approach. Studies in Health Technology and Informatics. https://doi.org/10.3233/shti261006
Vancouver
Najork SK, Weber M, Bücken G, Maass M, Kunkel Gen Bode L, Koch PJ, et al. Interpolation Methods for MediaPipe Hand Tracking Gaps: A Pose-Based Approach. Studies in Health Technology and Informatics. 2026. doi:10.3233/shti261006
BibTeX
@article{Najork2026,
author = {Najork, Solveig Kathleen and Weber, Michael and Bücken, Gerrit and Maass, Marco and Kunkel Gen Bode, Lisa and Koch, Philipp J and Grzegorzek, Marcin},
title = {Interpolation Methods for MediaPipe Hand Tracking Gaps: A Pose-Based Approach},
journal = {Studies in Health Technology and Informatics},
year = {2026},
doi = {10.3233/shti261006}
}
EUVIMED