A Deep Learning Model for Markerless Pose Estimation Based on Keypoint Augmentation: What Factors Influence Errors in Biomechanical Applications?
Sensors · 17.03.2024 · 24 (6) · 1923
DOI: 10.3390/s24061923 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 17.03.2024. Verfasst von Ana V Ruescas-Nicolau und 5 weiteren Autor:innen. Beteiligte Einrichtung: Instituto de Biomecánica-IBV, Universitat Politècnica de València, Edifici 9C, Camí de Vera s/n, 46022 Valencia, Spain. Hauptthemen laut MEDLINE: Deep Learning. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 61 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Instituto Valenciano de Competitividad Empresarial (IVACE) and Valencian Regional Government (GVA).
Abstract (Originalsprache)
In biomechanics, movement is typically recorded by tracking the trajectories of anatomical landmarks previously marked using passive instrumentation, which entails several inconveniences. To overcome these disadvantages, researchers are exploring different markerless methods, such as pose estimation networks, to capture movement with equivalent accuracy to marker-based photogrammetry. However, pose estimation models usually only provide joint centers, which are incomplete data for calculating joint angles in all anatomical axes. Recently, marker augmentation models based on deep learning have emerged. These models transform pose estimation data into complete anatomical data. Building on this concept, this study presents three marker augmentation models of varying complexity that were compared to a photogrammetry system. The errors in anatomical landmark positions and the derived joint angles were calculated, and a statistical analysis of the errors was performed to identify the factors that most influence their magnitude. The proposed Transformer model improved upon the errors reported in the literature, yielding position errors of less than 1.5 cm for anatomical landmarks and 4.4 degrees for all seven movements evaluated. Anthropometric data did not influence the errors, while anatomical landmarks and movement influenced position errors, and model, rotation axis, and movement influenced joint angle errors.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Instituto de Biomecánica-IBV, Universitat Politècnica de València, Edifici 9C, Camí de Vera s/n, 46022 Valencia, Spain.
- Instituto Universitario de Automática e Informática Industrial, Universitat Politècnica de València, Edifici 1F, Camí de Vera, s/n, 46022 Valencia, Spain.
ORCID-Profile: Ana V Ruescas-Nicolau, Enrique Medina-Ripoll, Helios de Rosario, Joaquín Sanchiz Navarro, Eduardo Parrilla, María Carmen Juan Lizandra
Förderung
- Instituto Valenciano de Competitividad Empresarial (IVACE) and Valencian Regional Government (GVA)
Zitieren
APA
Ruescas-Nicolau, A. V., Medina-Ripoll, E., de Rosario, H., Sanchiz Navarro, J., Parrilla, E., & Juan Lizandra, M. C. (2024). A Deep Learning Model for Markerless Pose Estimation Based on Keypoint Augmentation: What Factors Influence Errors in Biomechanical Applications?. Sensors, 24(6), 1923. https://doi.org/10.3390/s24061923
Vancouver
Ruescas-Nicolau AV, Medina-Ripoll E, de Rosario H, Sanchiz Navarro J, Parrilla E, Juan Lizandra MC. A Deep Learning Model for Markerless Pose Estimation Based on Keypoint Augmentation: What Factors Influence Errors in Biomechanical Applications?. Sensors. 2024;24(6):1923. doi:10.3390/s24061923
BibTeX
@article{RuescasNicolau2024,
author = {Ruescas-Nicolau, Ana V and Medina-Ripoll, Enrique and de Rosario, Helios and Sanchiz Navarro, Joaquín and Parrilla, Eduardo and Juan Lizandra, María Carmen},
title = {A Deep Learning Model for Markerless Pose Estimation Based on Keypoint Augmentation: What Factors Influence Errors in Biomechanical Applications?},
journal = {Sensors},
year = {2024},
volume = {24},
number = {6},
pages = {1923},
doi = {10.3390/s24061923}
}
EUVIMED