Development of a fully automated RULA assessment system based on computer vision

The purpose of this study was to develop an automated, RULA-based posture assessment system using a deep learning algorithm estimate RULA scores, including scores for wrist posture, based on images workplace postures. proposed estimation reported mean absolute error (MAE) 2.86 the validation dataset obtained by randomly splitting 20% original training before data augmentation. results were compared with those two experts’ manual evaluation computing intraclass correlation coefficient (ICC), which yielded index values greater than 0.75, thereby confirming good agreement between raters and system. This will reduce time required postural while producing highly reliable that are consistent generated approach. Thus, we expect aid ergonomic experts in conducting surveys occupational postures conditions.