Deep Learning-Based Estimation of Whole-Body Kinematics from Multi-View Images

Details

• Personal Author:
  Breloff SP ; Carey RE ; Hawke AL ; Li K ; Nguyen KX ; Peng X ; Zheng L
• Description:
  It is necessary to analyze the whole-body kinematics (including joint locations and joint angles) to assess risks of fatal and musculoskeletal injuries in occupational tasks. Human pose estimation has gotten more attention in recent years as a method to minimize the errors in determining joint locations. However, the joint angles are not often estimated, nor is the quality of joint angle estimation assessed. In this paper, we presented an end-to-end approach on direct joint angle estimation from multi-view images. Our method leveraged the volumetric pose representation and mapped the rotation representation to a continuous space where each rotation was uniquely represented. We also presented a new kinematic dataset in the domain of residential roofing with a data processing pipeline to generate necessary annotations for the supervised training procedure on direct joint angle estimation. We achieved a mean angle error of 7.19 degrees on the new Roofing dataset and 8.41 degrees on the Human3.6M dataset, paving the way for employment of on-site kinematic analysis using multi-view images. [Description provided by NIOSH]
• Subjects:
  Coal Coal Mining Engineering Hearing Hearing Loss Hearing Loss, Noise-Induced Mining Noise Occupational Health Safety
• Keywords:
  Author Keywords: Deep Learning Biomechanics Computers Computer Vision Imaging Techniques Kinematic Estimation Motion Studies MSD Musculoskeletal System Disorders Sensors
• ISSN:
  1077-3142
• Document Type:
  Text
• Genre:
  Journal Article
• Place as Subject:
  Delaware ; New Jersey ; OSHA Region 2 ; OSHA Region 3 ; West Virginia
• CIO:
  National Institute for Occupational Safety and Health (NIOSH)
• Division:
  HELD - Health Effects Laboratory Division
• Topic:
  Workplace Safety & Health
• Location:
  North America
• Volume:
  235
• NIOSHTIC Number:
  nn:20066120
• Citation:
  Comput Vis Image Underst 2023 Oct; 235:103780
• Contact Point Address:
  Kien X. Nguyen, Department of Computer & Information Science, University of Delaware, Newark, DE, USA
• Email:
  kxnguyen@udel.edu
• Federal Fiscal Year:
  2024
• NORA Priority Area:
  Construction
• Peer Reviewed:
  True
• Source Full Name:
  Computer Vision and Image Understanding
• Collection(s):
  National Institute for Occupational Safety and Health
• Main Document Checksum:
  urn:sha-512:83dabe67242a283847c35ffc3b22f4af837e081de1510fb25236e40bf7b2fa8fdd81a799ab81a2c7f30412813a02159893f667de701779238087fb4fff8994bf
• Download URL:
  https://stacks.cdc.gov/view/cdc/212633/cdc_212633_DS1.pdf
• File Type:
  [PDF - 1.53 MB ]