EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Performance Evaluation of Monocular Markerless Pose Estimation Systems for Industrial Exoskeletons

Soocheol Yoon iD, Ya-Shian Li-Baboud iD, Ann Virts, Roger Bostelman, Mili Shah iD, Nishat Ahmed

Sensors · 02.05.2025 · 25 (9) · 2877

DOI: 10.3390/s25092877 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 02.05.2025. Verfasst von Soocheol Yoon und 5 weiteren Autor:innen. Beteiligte Einrichtung: National Institute of Standards and Technology, Gaithersburg, MD 20899, USA. Hauptthemen laut MEDLINE: Exoskeleton Device, Robotics, Posture. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 57 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIST DOC, NIST, Georgetown University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Industrial exoskeletons (a.k.a. wearable robots) have been developed to reduce musculoskeletal fatigue and work injuries. Human joint kinematics and human–robot alignment are important measurements in understanding the effects of industrial exoskeletons. Recently, markerless pose estimation systems based on monocular color (red, green, blue—RGB) and depth cameras are being used to estimate human joint positions. This study analyzes the performance of monocular markerless pose estimation systems on human skeletal joint estimation while wearing exoskeletons. Two pose estimation systems producing RGB and depth images from ten viewpoints are evaluated for one subject in 14 industrial poses. The experiment was repeated for three different types of exoskeletons on the same subject. An optical tracking system (OTS) was used as a reference system. The image acceptance rate was 56% for the RGB, 22% for the depth, and 78% for the OTS pose estimation system. The key sources of pose estimation error were the occlusions from the exoskeletons, industrial poses, and viewpoints. The reference system showed decreased performance when the optical markers were occluded by the exoskeleton or when the markers’ position shifted with the exoskeleton. This study performs a systematic comparison of two types of monocular markerless pose estimation systems and an optical tracking system, as well as a proposed metric, based on a tracking quality ratio, to assess whether a skeletal joint estimation would be acceptable for human kinematics analysis in exoskeleton studies.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Exoskeleton DeviceRoboticsPostureHumansBiomechanical PhenomenaMaleJoints

Stichwörter der Autor:innen

exoskeletonjoint pose estimationperformance evaluationpose estimation system

Autor:innen und Institutionen

  • National Institute of Standards and Technology, Gaithersburg, MD 20899, USA.
  • Institute for Soft Matter Synthesis and Metrology, Georgetown University, Washington, DC 20057, USA.
  • Smart HLPR LLC, Troutman, NC 28166, USA.
  • Department of Mathematics, Albert Nerken School of Engineering, The Cooper Union for the Advancement of Science and Art, New York, NY 10003, USA.
  • Department of Electrical Engineering, Albert Nerken School of Engineering, The Cooper Union for the Advancement of Science and Art, New York, NY 10003, USA.

ORCID-Profile: Soocheol Yoon, Ya-Shian Li-Baboud, Mili Shah

Förderung

  • NIST DOC
  • NIST
  • Georgetown University

Zitieren

APA

Yoon, S., Li-Baboud, Y. S., Virts, A., Bostelman, R., Shah, M., & Ahmed, N. (2025). Performance Evaluation of Monocular Markerless Pose Estimation Systems for Industrial Exoskeletons. Sensors, 25(9), 2877. https://doi.org/10.3390/s25092877

Vancouver

Yoon S, Li-Baboud YS, Virts A, Bostelman R, Shah M, Ahmed N. Performance Evaluation of Monocular Markerless Pose Estimation Systems for Industrial Exoskeletons. Sensors. 2025;25(9):2877. doi:10.3390/s25092877

BibTeX
@article{Yoon2025,
  author = {Yoon, Soocheol and Li-Baboud, Ya-Shian and Virts, Ann and Bostelman, Roger and Shah, Mili and Ahmed, Nishat},
  title = {Performance Evaluation of Monocular Markerless Pose Estimation Systems for Industrial Exoskeletons},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {9},
  pages = {2877},
  doi = {10.3390/s25092877}
}
Kostenlos starten →