A Comparative Assessment of Accuracy in Video-Based Monocular Human Pose Estimation Frameworks
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2026-07 · 48 (7) · 8470-8484
DOI: 10.1109/tpami.2026.3672463 ↗Kurz gefasst
Vergleichsstudie in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026-07. Verfasst von Fabian Kahl und 6 weiteren Autor:innen. Hauptthemen laut MEDLINE: Video Recording, Posture, Imaging, Three-Dimensional. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 160 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: German Federal Ministry of Education and Research, Ministry of Culture and Science of the State of North Rhine-Westphalia, Open Access Publication Fund of the University of Bonn.
Abstract (Originalsprache)
In human pose estimation, a comprehensive evaluation of state-of-the-art frameworks is necessary to advance both research and practical applications. This paper presents a thorough review of state-of-the-art 2D and 3D human pose estimation frameworks, analyzing 118 papers and four GitHub repositories, with a focus on frameworks made since 2019. The following frameworks are chosen based on predefined inclusion criteria: AlphaPose, Detectron2, MediaPipe, MeTRAbs, MHFormer, MMPose, MoveNet, OpenPifPaf, OpenPifPaf-vita, OpenPose, PoseFormerV2, rtmlib, StridedTransformer-Pose3D, ultralytics (YOLOv8), ViTPose, and YOLOv7. This paper evaluates these 16 frameworks on an existing, unpublished dataset consisting of exercise videos recorded with a monocular RGB camera and synchronized gold-standard motion capture data. The dataset includes videos of nine individuals performing eight exercises, recorded from two camera views with different planar angles. The analysis evaluates joint angle performance of the frameworks using weighted mean absolute error and weighted intraclass correlation coefficient as quantitative metrics. MeTRAbs emerged as the best overall framework, while AlphaPose, rtmlib, and YOLOv7 were the top 2D performers. The used code is available open source.1.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Förderung
- German Federal Ministry of Education and Research
- Ministry of Culture and Science of the State of North Rhine-Westphalia
- Open Access Publication Fund of the University of Bonn
Zitieren
APA
Kahl, F., Wegner, P., Kapsecker, M., Nissen, L., Faber, J., Jonas, S. M., & Reimer, L. M. (2026). A Comparative Assessment of Accuracy in Video-Based Monocular Human Pose Estimation Frameworks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 48(7), 8470-8484. https://doi.org/10.1109/tpami.2026.3672463
Vancouver
Kahl F, Wegner P, Kapsecker M, Nissen L, Faber J, Jonas SM, et al. A Comparative Assessment of Accuracy in Video-Based Monocular Human Pose Estimation Frameworks. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2026;48(7):8470-8484. doi:10.1109/tpami.2026.3672463
BibTeX
@article{Kahl2026,
author = {Kahl, Fabian and Wegner, Philipp and Kapsecker, Maximilian and Nissen, Leon and Faber, Jennifer and Jonas, Stephan M and Reimer, Lara Marie},
title = {A Comparative Assessment of Accuracy in Video-Based Monocular Human Pose Estimation Frameworks},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2026},
volume = {48},
number = {7},
pages = {8470--8484},
doi = {10.1109/tpami.2026.3672463}
}
EUVIMED