Auto-AzKNIOSH: an automatic NIOSH evaluation with Azure Kinect coupled with task recognition DOI
Francesco Lolli, Antonio Maria Coruzzolo,

Chiara Forgione

и другие.

Ergonomics, Год журнала: 2024, Номер unknown, С. 1 - 17

Опубликована: Дек. 4, 2024

Standard Ergonomic Risk Assessment (ERA) from video analysis is a highly time-consuming activity and affected by the subjectivity of ergonomists. Motion Capture (MOCAP) addresses these limitations allowing objective ERA. Here depth camera, one most commonly used MOCAP systems for ERA (i.e. Azure Kinect), evaluation NIOSH Lifting Equation exploiting tool named AzKNIOSH. First, to validate tool, we compared its performance with those provided commercial software, Siemens Jack TAT, based on an Inertial Measurement Units (IMUs) suit found high agreement between them. Secondly, Convolutional Neural Network (CNN) was employed task recognition, automatically identifying lifting actions. This procedure evaluated comparing results obtained manual detection through automatic detection. Thus, automated implementation Auto-AzKNIOSH achieved fully

Язык: Английский

Auto-AzKNIOSH: an automatic NIOSH evaluation with Azure Kinect coupled with task recognition DOI
Francesco Lolli, Antonio Maria Coruzzolo,

Chiara Forgione

и другие.

Ergonomics, Год журнала: 2024, Номер unknown, С. 1 - 17

Опубликована: Дек. 4, 2024

Standard Ergonomic Risk Assessment (ERA) from video analysis is a highly time-consuming activity and affected by the subjectivity of ergonomists. Motion Capture (MOCAP) addresses these limitations allowing objective ERA. Here depth camera, one most commonly used MOCAP systems for ERA (i.e. Azure Kinect), evaluation NIOSH Lifting Equation exploiting tool named AzKNIOSH. First, to validate tool, we compared its performance with those provided commercial software, Siemens Jack TAT, based on an Inertial Measurement Units (IMUs) suit found high agreement between them. Secondly, Convolutional Neural Network (CNN) was employed task recognition, automatically identifying lifting actions. This procedure evaluated comparing results obtained manual detection through automatic detection. Thus, automated implementation Auto-AzKNIOSH achieved fully

Язык: Английский

Процитировано

0