Dynamic biomechanical analysis for construction tasks using motion data from vision-based motion capture approaches

In the labor-intensive construction industry, workers are frequently exposed to manual handling tasks involving forceful exertions and awkward postures. As a result, construction workers are at about a 16 percent higher risk of work-related musculoskeletal disorders (WMSDs) than workers in other industries. A biomechanical model-based musculoskeletal stress analysis is one of the widely used methods to identify the risk of WMSDs during occupational tasks. However, the use of biomechanical analysis has been limited to only laboratory experiments due to the difficulty of collecting motion data required for biomechanical models under real conditions. To reflect postural variations when performing construction tasks, an effective and easily accessible mean that enables us to conduct biomechanical analysis under real conditions is required. To address this issue, we propose a motion-data-driven biomechanical analysis by enabling automatic processes to convert motion data from vision-based motion capture into available data for representing motions in biomechanical analysis tools. We conduct a case study on masonry work to determine the feasibility of the proposed method. The results show that the proposed approach has the potential to assess an individual's motions and to provide personalized feedback for the purpose of reducing biomechanical loads and WMSD risk in real workplaces.