Real-time EH&S Intervention to Improve Site Safety
This project leverages the integration of AI-based visual models into augmented reality (AR) to address fall-from-height (FFH) risks in high-rise construction. Current FFH mitigation relies heavily on manual site inspections, which are time-consuming, labour-intensive, and difficult to keep up to date in fast-changing construction environments.
In collaboration with our industry partner (Lendlease), we investigated how emerging digital technologies can support more timely, accurate, and scalable identification of FFH hazards such as gaps in perimeter screens and unprotected openings.
We designed and implemented proof-of-concept prototypes that combine AI-assisted computer vision with AR to automate hazard detection and enhance inspection workflows. The prototypes demonstrate real-time visual analysis, automated reporting, and immersive AR-based site inspection and training capabilities.
Feedback from industry stakeholders confirmed the strong potential of this approach to enable earlier risk detection, reduce reliance on manual inspections, improve reporting accuracy, and support workforce training, contributing to safer and more efficient high-rise construction practices.
Publication
Liu, J., Rao, A. S., Ke, F., Dwyer, T., Tag, B., & Delir Haghighi, P. (2024, October). AR-Facilitated Safety Inspection and Fall Hazard Detection on Construction Sites. In 2024 IEEE International Symposium on Mixed and Augmented Reality Adjunct (ISMAR-Adjunct) (pp. 12-14). IEEE. Publication Link
Building 4.0 CRC PhD Scholarship Project (#29)
PhD candidate: Fucai Ke