Smart Passive Mixed Reality-Based Construction Inspection Framework

Smart Passive Mixed Reality-Based Construction Inspection Framework Boan Tao, Jiajun Li, Frédéric Bosché Pages 776-783 (2024 Proceedings of the 41st ISARC, Lille, France, ISBN 978-0-6458322-1-1, ISSN 2413-5844) Abstract: With increasingly complex construction projects, improving inspection efficiency and accuracy is an important challenge. This paper proposes a novel MR-based construction inspection framework that integrates BIM, MR, and AI technologies to achieve automatic and passive inspection tasks. The framework comprises object detection, 2D to 3D projection, and digital twin-based object recognition and MR-based visualisation to provide an efficient inspection process. The framework is evaluated in an indoor construction environment with common elements like electrical sockets and switches as a typical example to validate our approach in real-world applications. Keywords: Mixed reality, BIM, Digital Twin, Construction Inspection, Camera Projection, Object detection; Deep Learning DOI: https://doi.org/10.22260/ISARC2024/0101 Download fulltext Download BibTex Download Endnote (RIS) TeX Import to Mendeley