Measuring Exertion Time, Duty Cycle and Hand Activity Level for Industrial Tasks Using Computer Vision

Details

• Personal Author:
  Akkas O ; Harris Adamson C ; Hu YH ; Lee CH ; Radwin RG ; Rempel D
• Description:
  Two computer vision algorithms were developed to automatically estimate exertion time, duty cycle (DC), and hand activity level (HAL) from videos of workers performing 50 industrial tasks. The average DC difference between manual frame-by-frame analysis and the computer vision DC was -5.8% for the Decision Tree (DT) algorithm, and 1.4% for the Feature Vector Training (FVT) algorithm. The average HAL difference was 0.5 for the DT algorithm and 0.3 for the FVT algorithm. A sensitivity analysis, conducted to examine the influence that deviations in DC have on HAL, found it remained unaffected when DC error was less than 5%. Thus, a DC error less than 10% will impact HAL less than 0.5 HAL, which is negligible. Automatic computer vision HAL estimates were therefore comparable to manual frame-by-frame estimates. [Description provided by NIOSH]
• Subjects:
  Automation Environmental Exposure Musculoskeletal Diseases Musculoskeletal System Occupational Health Safety Software
• Keywords:
  Activity Levels Algorithms Analytical Instruments Analytical Processes Author Keywords: Computer Vision Automated Exposure Analysis Computer Models Exposure Assessment Exposure Levels Hand Injuries Mathematical Models Motion Studies Musculoskeletal System Musculoskeletal System Disorders Physiological Measurements Repetitive Motion Repetitive Work Sensitivity Testing Task Performance Video Visual Fields Visual Images Work Related Musculoskeletal Disorders

  More +
• ISSN:
  0014-0139
• Document Type:
  Text
• Funding:
  Grant
• Genre:
  Journal Article
• Place as Subject:
  California ; OSHA Region 5 ; OSHA Region 9 ; Wisconsin
• CIO:
  National Institute for Occupational Safety and Health (NIOSH)
• Topic:
  Workplace Safety & Health
• Location:
  North America
• Volume:
  60
• Issue:
  12
• NIOSHTIC Number:
  nn:20049982
• Citation:
  Ergonomics 2017 Dec; 60(12):1730-1738
• Contact Point Address:
  Robert G. Radwin, PhD, University of Wisconsin-Madison, 1550 Engineering Drive, Madison, WI 53706, USA
• Email:
  radwin@discovery.wisc.edu
• Federal Fiscal Year:
  2018
• Performing Organization:
  University of Wisconsin-Madison
• Peer Reviewed:
  True
• Start Date:
  20160901
• Source Full Name:
  Ergonomics
• End Date:
  20190831
• Collection(s):
  National Institute for Occupational Safety and Health
• Main Document Checksum:
  urn:sha-512:68477c9144d2df421a979d6ee88fde70fc1bae37dc028986e205441d56d858f54ba86d50dd6f89e31a563eb490025f154a4aab2cf953515f10f525ff8370f320
• Download URL:
  https://stacks.cdc.gov/view/cdc/210549/cdc_210549_DS1.pdf
• File Type:
  [PDF - 2.08 MB ]