Predicting movements of onsite workers and mobile equipment for enhancing construction site safety

Zhu, Zhenhua; Park, Man-Woo; Koch, Christian; Soltani, Mohamad; Hammad, Amin; Davari, Khashayar

Abstract

Tens of thousands of time-loss injuries and deaths are annually reported from the construction sector, and a high percentage of them are due to the workers being struck by mobile equipment on sites. In order to address this site safety issue, it is necessary to provide proactive warning systems. One critical part in such systems is to locate the current positions of onsite workers and mobile equipment and also predict their future positions to prevent immediate collisions. This paper proposes novel Kalman filters for predicting the movements of the workers and mobile equipment on the construction sites. The filters take the positions of the equipment and workers estimated from multiple video cameras as input, and output the corresponding predictions on their future positions. Moreover, the filters could adjust their predictions based on the worker or equipment's previous movements. The effectiveness of the filters has been tested with real site videos and the results show the high prediction accuracy of the filters.

Citation

Zhu, Z., Park, M., Koch, C., Soltani, M., Hammad, A., & Davari, K. (2016). Predicting movements of onsite workers and mobile equipment for enhancing construction site safety. Automation in Construction, 68, https://doi.org/10.1016/j.autcon.2016.04.009

• Journal Article Type: Article
• Acceptance Date: Apr 28, 2016
• Online Publication Date: May 20, 2016
• Publication Date: Aug 1, 2016
• Deposit Date: Jun 6, 2016
• Publicly Available Date: Jun 6, 2016
• Journal: Automation in Construction
• Print ISSN: 0926-5805
• Electronic ISSN: 0926-5805
• Publisher: Elsevier
• Peer Reviewed: Peer Reviewed
• Volume: 68
• DOI: https://doi.org/10.1016/j.autcon.2016.04.009
• Keywords: Movement prediction; Kalman filtering; construction safety
• Public URL: https://nottingham-repository.worktribe.com/output/798172
• Publisher URL: http://dx.doi.org/10.1016/j.autcon.2016.04.009