Depth-informed point cloud-to-BIM registration for construction inspection using augmented reality

Augmented reality (AR) is increasingly being used to assist construction inspection onsite. Underpinning this AR-assisted inspection is a technique called registration, which aims to align the physical world with a digital building information model (BIM) so that the as-built can be intuitively compared with the as-designed. Despite its importance, how to precisely and efficiently register BIM to the physical world still remains a challenge. This paper contributes to tackling the challenge by proposing a novel depth-informed point cloud-to-BIM registration (D-PC2BIM) algorithm. The idea is to enhance registration performance by estimating the depth of a sparse point cloud to inform interpolation of the missing points and to extract the endpoints that matter most in a registration. A novel integration algorithm is proposed to improve the success rate of final registration. Experiments demonstrate the effectiveness of the proposed algorithm, which outperformed existing approaches with higher accuracy and faster speed. The contribution of the study resides in the development of the D-PC2BIM algorithm and a demonstration of its applicability in enabling construction inspection using AR.