Auto-AzKNIOSH: an automatic NIOSH evaluation with Azure Kinect coupled with task recognition.

Standard Ergonomic Risk Assessment (ERA) from video analysis is a highly time-consuming activity and is affected by the subjectivity of ergonomists. Motion Capture (MOCAP) addresses these limitations by allowing objective ERA. Here a depth camera, one of the most commonly used MOCAP systems for ERA...

Descripción completa

Detalles Bibliográficos
Publicado en:Ergonomics Vol. 68; no. 10; pp. 1718 - 1735
Autores principales: Lolli, Francesco, Coruzzolo, Antonio Maria, Forgione, Chiara, Peron, Mirco, Sgarbossa, Fabio
Formato: algorithm pictorial research tables/charts Journal Article
Publicado: Taylor & Francis Ltd Oct2025
Acceso en línea:Ver este registro en EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=188122501&site=ehost-live
header:
  @attributes:
    shortDbName: ccm
    uiTerm: 188122501
    longDbName: CINAHL Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    dissinfo:
    jinfo:
      jid:
        00140139
        ERO
      jtl: Ergonomics
      issn: 00140139
      maglogo: Y
    pubinfo:
      dt: Oct2025
      vid: 68
      iid: 10
      pid: 377
      pub: Taylor & Francis Ltd
      place: Philadelphia, Pennsylvania
    artinfo:
      ui:
        188122501
        181428765
        188122501
        188122501
        10.1080/00140139.2024.2433027
        188122501
      ppf: 1718
      ppct: 17
      formats:
      tig:
        atl: Auto-AzKNIOSH: an automatic NIOSH evaluation with Azure Kinect coupled with task recognition.
      aug:
        au:
          Lolli, Francesco
          Coruzzolo, Antonio Maria
          Forgione, Chiara
          Peron, Mirco
          Sgarbossa, Fabio
        affil: Department of Sciences and Methods for Engineering, University of Modena and Reggio Emilia, Reggio Emilia, Italy
      sug:
        subj:
          Ergonomics Evaluation
          Lifting Physiology
          Occupational Safety Evaluation
          Convolutional Neural Networks Evaluation
          Occupational-Related Injuries Risk Factors
          Risk Assessment
          Task Performance and Analysis Evaluation
          Videorecording
          National Institute for Occupational Safety and Health
          Human
          Funding Source
          Motion Capture
          Biomechanics
          Movement Evaluation
          Balance, Postural
          Motion Analysis Systems
          Software Design
          Comparative Studies
          Kinematics
          T-Tests
          Benchmarking
      ab: Standard Ergonomic Risk Assessment (ERA) from video analysis is a highly time-consuming activity and is affected by the subjectivity of ergonomists. Motion Capture (MOCAP) addresses these limitations by allowing objective ERA. Here a depth camera, one of the most commonly used MOCAP systems for ERA (i.e. Azure Kinect), is used for the evaluation of the NIOSH Lifting Equation exploiting a tool named AzKNIOSH. First, to validate the tool, we compared its performance with those provided by a commercial software, Siemens Jack TAT, based on an Inertial Measurement Units (IMUs) suit and found a high agreement between them. Secondly, a Convolutional Neural Network (CNN) was employed for task recognition, automatically identifying the lifting actions. This procedure was evaluated by comparing the results obtained from manual detection with those obtained through automatic detection. Thus, through automated task detection and the implementation of Auto-AzKNIOSH we achieved a fully automated ERA. Practitioner Summary: The standard evaluation of the NIOSH Lifting Equation is time-consuming and subjective, thus a new automatic tool is designed, which integrates motion captures provided by Azure Kinect and task recognition. We found a high agreement between our tool and Siemens Jack TAT suit, the golden standard technology for motion capture.
      pubtype: Academic Journal
      doctype:
        algorithm
        pictorial
        research
        tables/charts
        Journal Article
      ougenre: Article
    language: English
    refInfo:
    holdings:
      @attributes:
        islocal: N