AR-Facilitated Safety Inspection and Fall Hazard Detection on Construction Sites

TL;DR

The paper investigates AR-assisted safety inspections on high-rise construction sites to prevent falls by tracking inspected areas and automatically detecting gaps in perimeter safety screens using a pipeline that integrates AR with advanced computer vision. The proposed AR system features spatial mapping, a 'brushing' progress indicator, 3D annotations, voice notes, automatic report generation, and Large Vision model integration for hazard segmentation. It also analyzes privacy and security risks for workers and bystanders, proposing mitigations such as privacy-preserving techniques, encryption, and access controls. Overall, the work outlines a pathway to integrate AR with CV and Digital Twins in AEC while addressing key governance and safety concerns through multi-stakeholder collaboration.

Abstract

Together with industry experts, we are exploring the potential of head-mounted augmented reality to facilitate safety inspections on high-rise construction sites. A particular concern in the industry is inspecting perimeter safety screens on higher levels of construction sites, intended to prevent falls of people and objects. We aim to support workers performing this inspection task by tracking which parts of the safety screens have been inspected. We use machine learning to automatically detect gaps in the perimeter screens that require closer inspection and remediation and to automate reporting. This work-in-progress paper describes the problem, our early progress, concerns around worker privacy, and the possibilities to mitigate these.