Publications / 2019 Proceedings of the 36th ISARC, Banff, Alberta, Canada

3D Posture Estimation from 2D Posture Data for Construction Workers

Yantao Yu, Heng Li and Xincong Yang
Pages 26-34 (2019 Proceedings of the 36th ISARC, Banff, Alberta, Canada)

Construction workers’ behaviour is important for safety, health and productivity management. Workers’ 3D postures are the data foundation of their behaviours. This paper established a preliminary 3D posture dataset of construction tasks and provided a 3D posture estimation method based on 2D joint locations. The results showed that the method could estimate 3D postures accurately and timely. The mean joint error and estimation time of each frame were 1.10 cm and 0.12 ms respectively. This method makes it possible to estimate construction workers’ 3D postures from construction site images and contributes to a data-based construction workers’ behaviour management.

Keywords: Posture estimation; Construction worker; Behavior management