Presentation
Toward Full Automation of the Revised NIOSH Lifting Equation
SessionPoster Session 1
DescriptionThis study proposes a computer vision-based method to automate the Revised NIOSH Lifting Equation (RNLE) for ergonomic assessments, addressing the inefficiencies of manual measurements. Using BlazePose for real-time pose estimation, kinematic features are extracted to identify lifting phases through the k-TSP classifier, and RNLE multipliers are automatically estimated. Validation using 40 lifting tasks showed strong agreement between automated and ground-truth recommended weight limits (RWLs) (average error = 2.72 kg). The method leverages standard RGB video without the need for specialized equipment, offering a cost-effective and scalable solution. However, limitations include testing only with light loads (RWL < 8 kg) and excluding the coupling multiplier, suggesting future work to expand validation conditions and integrate object detection for full RNLE automation.
Event Type
Poster
TimeTuesday, October 14th5:30pm - 6:30pm CDT
LocationRiverside East
Similar Presentations