Using Computer Vision and Deep Learning to Measure Worker Kinematics

Details

• Personal Author:
  Fethke NB
• Description:
  Methods and procedures have been developed to enable robust validation of three-dimensional measurement of human posture and movement obtained from a combination of consumer-grade video recording devices, computer vision, and deep learning algorithms. The methods include consideration for the complexity of the video recording hardware (i.e., a single two-dimensional video, stereovision, or video plus depth sensing), all major body joints, and the extent of variation in joint angles over time (i.e., movement through small or large ranges of motion). While analyses are ongoing, results will provide occupational safety and health practitioners key information about the performance of computer vision-based task analysis and enterprise risk management applications (relative to ergonomics and musculoskeletal disorders) that have rapidly proliferated the marketplace. [Description provided by NIOSH]
• Subjects:
  Automation Biomechanical Phenomena Ergonomics Musculoskeletal System Occupational Health Risk Assessment Safety
• Keywords:
  Algorithms Artificial Intelligence Biomechanics Motion Studies Posture Risk Management
• Series:
  Grant Final Reports
• Publisher:
  National Institute for Occupational Safety and Health
• Document Type:
  Text
• Funding:
  Grant
• Genre:
  Final Grant Report
• Place as Subject:
  Iowa ; OSHA Region 7
• CIO:
  National Institute for Occupational Safety and Health (NIOSH)
• Division:
  OEP - Office of Extramural Programs
• Topic:
  Workplace Safety & Health
• Location:
  North America
• Pages in Document:
  1-13
• NIOSHTIC Number:
  nn:20069705
• Citation:
  Atlanta, GA: U.S. Department of Health and Human Services, Public Health Service, Centers for Disease Control and Prevention, National Institute for Occupational Safety and Health, R21-OH-011911, 2024 Jan; :1-13
• Email:
  nathan-fethke@uiowa.edu
• Federal Fiscal Year:
  2024
• Performing Organization:
  University of Iowa
• Peer Reviewed:
  False
• Start Date:
  20210930
• Source Full Name:
  National Institute for Occupational Safety and Health
• End Date:
  20230929
• Collection(s):
  National Institute for Occupational Safety and Health
• Main Document Checksum:
  urn:sha-512:f3123583eb47c6cbebb0ffffbbe5a1aa74a41599c5ccfeba829824a06ab1744871824afa3510c4b56a11f1a9f10402158096f2b8992c45f4133c25655adcbc21
• Download URL:
  https://stacks.cdc.gov/view/cdc/219256/cdc_219256_DS1.pdf
• File Type:
  [PDF - 1.14 MB ]