| Title |
Identification Method for Indoor Structural Elements Using Point Cloud Data |
| Authors |
이유신(Lee, Yu-Sin) ; 임현수(Lim, Hyeon-Su) ; 김유경(Kim, You-Kyung) ; 윤석헌(Yun, Seok-Heon) |
| DOI |
https://doi.org/10.5659/JAIK.2025.41.12.371 |
| Keywords |
Point Cloud; BIM; Structural Identification; RANSAC; DBSCAN |
| Abstract |
Point cloud data can be used to automatically identify real indoor spaces. However, indoor environments often include many non-structural
elements. This study presents a method to remove non-structural elements from point clouds gathered through 3D scanning and to isolate
structural components. Preprocessing techniques, such as SOR and voxel downsampling, were applied to optimize the data. The RANSAC
algorithm detected horizontal and vertical planes, while the DBSCAN algorithm identified columns. To assess the method's performance,
quantitative analyses using RMSE and M3C2 were conducted, referencing the BIM model. Results showed high precision, with RMSE values
of 0.860628 for type 1 and 0.322795 for type 2. Additionally, M3C2 analysis indicated that type 2 had a distribution closer to a normal
curve, suggesting more stable registration results compared to type 1. The proposed approach improves the accuracy of identifying structural
elements in 3D-scanned point cloud data. However, limitations exist in applying these results to complex or irregular structures and varied
spatial conditions. Future research will explore deep learning-based classification and automatic correction algorithms to recognize irregular
structural forms, aiming to broaden the method's applicability. |