<  Back to the Polytechnique Montréal portal

Pose Estimation with a Kinect for Ergonomic Studies: Evaluation of the Accuracy Using a Virtual Mannequin

Pierre Plantard, Edouard Auvinet, Anne-Sophie Pierres and Franck Multon

Article (2015)

[img]
Preview
Published Version
Terms of Use: Creative Commons Attribution.
Download (1MB)
Cite this document: Plantard, P., Auvinet, E., Pierres, A.-S. & Multon, F. (2015). Pose Estimation with a Kinect for Ergonomic Studies: Evaluation of the Accuracy Using a Virtual Mannequin. Sensors, 15(1). doi:10.3390/s150101785
Show abstract Hide abstract

Abstract

Analyzing human poses with a Kinect is a promising method to evaluate potentials risks of musculoskeletal disorders at workstations. In ecological situations, complex 3D poses and constraints imposed by the environment make it difficult to obtain reliable kinematic information. Thus, being able to predict the potential accuracy of the measurement for such complex 3D poses and sensor placements is challenging in classical experimental setups. To tackle this problem, we propose a new evaluation method based on a virtual mannequin. In this study, we apply this method to the evaluation of joint positions (shoulder, elbow, and wrist), joint angles (shoulder and elbow), and the corresponding RULA (a popular ergonomics assessment grid) upper-limb score for a large set of poses and sensor placements. Thanks to this evaluation method, more than 500,000 configurations have been automatically tested, which would be almost impossible to evaluate with classical protocols. The results show that the kinematic information obtained by the Kinect software is generally accurate enough to fill in ergonomic assessment grids. However inaccuracy strongly increases for some specific poses and sensor positions. Using this evaluation method enabled us to report configurations that could lead to these high inaccuracies. As a supplementary material, we provide a software tool to help designers to evaluate the expected accuracy of this sensor for a set of upper-limb configurations. Results obtained with the virtual mannequin are in accordance with those obtained from a real subject for a limited set of poses and sensor placements.

Uncontrolled Keywords

Adult; Biomechanical Phenomena; Human Engineering; Humans; Joints; Manikins; Movement; Posture; User-Computer Interface; Analytical Chemistry; 0301 Analytical Chemistry; 0906 Electrical And Electronic Engineering; Journal Article

Open Access document in PolyPublie
Subjects: 1900 Génie biomédical > 1900 Génie biomédical
Department: Institut de génie biomédical
Research Center: Non applicable
Funders: Convention industrielle de formation par la recherche (CIFRE), Faurecia Company
Grant number: 1222/2012
Date Deposited: 23 Nov 2018 10:23
Last Modified: 24 Nov 2018 01:20
PolyPublie URL: https://publications.polymtl.ca/3491/
Document issued by the official publisher
Journal Title: Sensors (vol. 15, no. 1)
Publisher: MDPI
Official URL: https://doi.org/10.3390/s150101785

Statistics

Total downloads

Downloads per month in the last year

Origin of downloads

Dimensions

Repository Staff Only