Vision-Language Models for Occupational Physical Exposure Assessment: Classification and Temporal Segmentation of Manual Material Handling Tasks

Details

• Journal Article:
  Applied Ergonomics
• Personal Author:
  Rajabi, Mohammad S. ; Ojelade, Aanuoluwapo ; Kim, Sunwook ; Nussbaum, Maury A.
• Description:
  Effective physical exposure assessment for manual materials handling (MMH) is essential for identifying activities that increase the risk of work-related musculoskeletal disorders and for guiding ergonomic interventions. However, existing methods are labor-intensive and often fail to capture task variability or to effectively estimate task timing characteristics. We evaluated the use of vision-language models (VLMs) to automatically and non-invasively classify eight MMH tasks and specific task conditions (i.e., hand configuration and lifting origin), and to detect task start and end times, using regular RGB video streams. We obtained task classification accuracies of approx. 82-85%, accuracies for classifying lifting origin of approx. 94-98%, and mean absolute start and end time errors <0.5 s, superior to prior work in some cases. Classification performance for hand configuration, though, was more variable. These findings demonstrate the potential of VLMs as a practical and scalable tool for physical exposure assessment of MMH tasks. Description provided by NIOSH
• Subjects:
  • Ergonomics
  • Musculoskeletal Diseases
  • Musculoskeletal System
  • Occupational Health
  • Safety
• Keywords:
  • Ergonomics
  • Exposure assessment
  • Manual materials handling
  • Musculoskeletal disorders
  • MSD
  • Automation
  • Machine learning
  • Motion studies
  • Author Keywords: Physical exposure assessment Vision-language model
  • VLM
  More +
• ISSN:
  0003-6870
• Document Type:
  Text
• Funding:
  Grant
• Genre:
  Journal Article
• Place as Subject:
  Birmingham Region OSHA ; Philadelphia Region OSHA ; Tennessee ; Virginia
• CIO:
  National Institute for Occupational Safety and Health (NIOSH)
• Topic:
  Workplace Safety & Health
• Location:
  North America
• Pages in Document:
  11 pdf pages
• Volume:
  138
• NIOSHTIC Number:
  nn:20071824
• Citation:
  Appl Ergon 2027 Jan; 138:104831
• Contact Point Address:
  Maury A. Nussbaum, Department of Industrial and Systems Engineering, Virginia Tech, Blacksburg, VA, 24061, USA
• Email:
  nussbaum@vt.edu
• Federal Fiscal Year:
  2027
• Performing Organization:
  Virginia Polytechnic Institute and State University, Blacksburg
• Peer Reviewed:
  True
• Start Date:
  2001/07/01
• End Date:
  2026/06/30
• Download URL:
  https://stacks.cdc.gov/view/cdc/260047/cdc_260047_DS1.pdf
• File Type:
  [PDF - 5.18 MB]
• Collection(s):
  National Institute for Occupational Safety and Health
• Main Document Checksum:
  urn:sha-512:8cbc00efd80e5de699202ef8bd8fda8a4bd7e311ff35e20e2a20e722e36c36ee19ab02b52ad15f3e8160dca387fcc8f567e108abc0f2e3a7ddf90ef9bad76c01