EUVIMEDEUVIMED entdecken
Crossref

From Semantic LiDAR Point Clouds to As-Built BIM: An AI Framework for 3D Reconstruction of Transport Infrastructure

Mingkai Li, Vincent J. L. Gan, Kexin Li, Xiuqi Li, Kelvin Goh Chun Keong, Lim Pia Lian, Allan Yeo Chen Long

Journal of Computing in Civil Engineering · 01.03.2027 · 41 (2)

DOI: 10.1061/jccee5.cpeng-7978 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Computing in Civil Engineering, erschienen am 01.03.2027. Verfasst von Mingkai Li und 6 weiteren Autor:innen. Die Arbeit nennt 40 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The rapid development of transport infrastructure highlights the need for efficient and accurate methods to reconstruct digital 3D models for asset information management. This study presents an AI-driven framework that integrates semantic light detection and ranging (LiDAR) point clouds with as-built building information modeling (BIM) reconstruction for mass rapid transit (MRT) stations. The proposed approach combines semantic segmentation with a geometry-aware, type-specific instance segmentation strategy, where spatially isolated components are clustered using voxel- and density-based spatial clustering of applications with noise (DBSCAN), while interconnected components are separated through orientation-based grouping and clustering. Furthermore, this study presents a scientific formulation for geometric representation and logical relationships among architectural and mechanical, electrical, and plumbing (MEP) components that bridges semantic instance segmentation to BIM reconstruction. Parametric modeling and matching-based modeling are developed to accommodate components with different characteristics. Experimental results demonstrate high segmentation accuracy (overall accuracy, OA, above 97%; mean intersection over union, mIoU, above 90%) and BIM geometric accuracy (above 80% at a 10 mm geometric deviation threshold), as well as remarkable savings in terms of manpower and time consumption (above 80%).

Zitieren

APA

Li, M., Gan, V. J. L., Li, K., Li, X., Keong, K. G. C., Lian, L. P., & Long, A. Y. C. (2027). From Semantic LiDAR Point Clouds to As-Built BIM: An AI Framework for 3D Reconstruction of Transport Infrastructure. Journal of Computing in Civil Engineering, 41(2). https://doi.org/10.1061/jccee5.cpeng-7978

Vancouver

Li M, Gan VJL, Li K, Li X, Keong KGC, Lian LP, et al. From Semantic LiDAR Point Clouds to As-Built BIM: An AI Framework for 3D Reconstruction of Transport Infrastructure. Journal of Computing in Civil Engineering. 2027;41(2). doi:10.1061/jccee5.cpeng-7978

BibTeX
@article{Li2027,
  author = {Li, Mingkai and Gan, Vincent J. L. and Li, Kexin and Li, Xiuqi and Keong, Kelvin Goh Chun and Lian, Lim Pia and Long, Allan Yeo Chen},
  title = {From Semantic LiDAR Point Clouds to As-Built BIM: An AI Framework for 3D Reconstruction of Transport Infrastructure},
  journal = {Journal of Computing in Civil Engineering},
  year = {2027},
  volume = {41},
  number = {2},
  doi = {10.1061/jccee5.cpeng-7978}
}
Kostenlos starten →