A Single-Camera Method for Estimating Lift Asymmetry Angles Using Deep Learning Computer Vision Algorithms

Details

• Personal Author:
  Hu YH ; Li Y ; Lou Z ; Lu M-L ; Radwin RG ; Werren, Dwight M. ; Xu H ; Zhan Z
• Description:
  A computer vision (CV) method to automatically measure the revised NIOSH lifting equation asymmetry angle (A) from a single camera is described and tested. A laboratory study involving ten participants performing various lifts was used to estimate A in comparison to ground truth joint coordinates obtained using 3-D motion capture (MoCap). To address challenges, such as obstructed views and limitations in camera placement in real-world scenarios, the CV method utilized video-derived coordinates from a selected set of landmarks. A 2-D pose estimator (HR-Net) detected landmark coordinates in each video frame, and a 3-D algorithm (VideoPose3D) estimated the depth of each 2-D landmark by analyzing its trajectories. The mean absolute precision error for the CV method, compared to MoCap measurements using the same subset of landmarks for estimating A, was 6.25 degrees (SD = 10.19 degrees, N = 360). The mean absolute accuracy error of the CV method, compared against conventional MoCap landmark markers was 9.45 degrees (SD = 14.01 degrees, N = 360). [Description provided by NIOSH]
• Subjects:
  Ergonomics Musculoskeletal System Occupational Health Safety
• Keywords:
  Algorithms Author Keywords: Computer Vision CV Low Back Pain Machine Learning Manual Lifting Manual Materials Handling NIOSH Lifting Equation Risk Assessment
• ISSN:
  2168-2291
• Document Type:
  Text
• Funding:
  Grant
• Genre:
  Journal Article
• Place as Subject:
  Chicago Region [OSHA] ; Ohio ; Wisconsin
• CIO:
  National Institute for Occupational Safety and Health (NIOSH)
• Division:
  DFSE - Division of Field Studies and Engineering
• Topic:
  Workplace Safety & Health
• Location:
  North America
• Pages in Document:
  309-314
• Volume:
  55
• Issue:
  2
• NIOSHTIC Number:
  nn:20070655
• Citation:
  IEEE Trans Hum-Mach Syst 2025 Apr; 55(2):309-314
• Contact Point Address:
  Robert G. Radwin, Department of Industrial and Systems Engineering, Department of Biomedical Engineering, University of WisconsinMadison, Madison, WI 53706
• Email:
  rradwin@wisc.edu
• Federal Fiscal Year:
  2025
• Performing Organization:
  University of Wisconsin-Madison
• Peer Reviewed:
  True
• Start Date:
  20160901
• Source Full Name:
  IEEE Transactions on Human-Machine Systems
• End Date:
  20190831
• Collection(s):
  National Institute for Occupational Safety and Health
• Main Document Checksum:
  urn:sha-512:50f030a4b09590fe16513bcdf08ca1f9eea28e878c1115f26ccaed6b0eb0bdf24e2abd2fb7421156f0d606e55fc4823989cac37864325ec0fcf56a9ab6706e19
• Download URL:
  https://stacks.cdc.gov/view/cdc/208833/cdc_208833_DS1.pdf
• File Type:
  [PDF - 811.85 KB ]