Proof-of-concept system evaluation of Ergomechanic for non-invasive estimation of upper-body posture and body load exposure in the workplace.

Abstract

Ergomechanic is a software-hardware system that uses cameras, computer vision and biomechanical modelling to calculate posture and body load during physical activity in the workplace. This study evaluated its ability to non-invasively and automatically identify postures adopted by workers that could lead to injury in the long term, and to use these results to suggest focuses for safety interventions. Five participants were recruited to perform normal duties in an area that was in view of four off-the-shelf security cameras. Participants were randomly assigned to the work area and 60 h of footage were collected. Five metrics relating to potential for injury were calculated for each second of footage. The extreme values of each metric were used to automatically identify body positions and work activities that could be hazardous in the long term. Insights from the process were used to recommend changes to the work area and activity design.