Jul 2026· The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences· Vol XLIX-B2-2026, pp. 1237-1243· 0 citations· 11 references
Abstract
Abstract. This paper presents a comprehensive methodology for the automated semantic segmentation and 3D reconstruction of industrial building elements, including roof panels, floor, rafters, purlins, and columns, from unstructured point clouds. The proposed approach integrates orientation-based filtering, projection onto characteristic planes, morphological analysis, and optimization-based I-profile fitting to generate accurate 3D models. The workflow begins with point cloud preprocessing, where the data are aligned with the building axes and cleaned of outliers, followed by subdivision into two subsets based on local surface orientation. Binary projections are then processed to extract element contours, while roof slopes and panel inclinations are automatically estimated to guide the reconstruction of rafters and purlins. The method was validated on a real-case study of 930 m² industrial warehouse scanned with a mobile laser scanner, resulting in a raw dataset of seven million points. The segmentation achieved F1-scores above 0.90 for floors, roof panels, rafters, and columns, and 0.75 for purlins. Profile fitting yielded an average width error of 3.8%, confirming the robustness and reliability of the reconstruction across diverse structural components.
In the experiments, 3D roof models manually digitized by stereoscopic measurement were used as the ground truth, and the automatically reconstructed 3D roof models were evaluated by comparison with this reference.
Yong-Heng Li, Masaya Shimasaki, M. Sakamoto et al.· The International Archives o...· 0 citations
Abstract. This paper presents a semi-automated pipeline for extracting architectural plans from terrestrial LiDAR point clouds of archaeological sites characterized by irregular geometries and significant surface degradation. The proposed workflow converts dense three-dimensional data into simplified two-dimensional re...
Marianna Bartrick-Krana, Roberto de Lima-Hernandez, A. Vandesande et al.· The International Archives o...· 0 citations
The results demonstrate the potential of hybrid AI and geometric approaches to improve the efficiency, repeatability, and reliability of Scan-to-BIM processes for historical masonry bridge heritage and show that the geometric quality of the HBIM model depends primarily on the density, spatial distribution and completen...
V. Alfio, Massimiliano Pepe, Donato Palumbo et al.· Applied Sciences· 0 citations
The proposed incremental geometric reconstruction framework for building structures based on LiDAR point clouds combines temporal state inheritance and orthogonal projection to transform 3D point-cloud processing into 2D plane-based contour updating and can recover major planar building structures.
Xian Cao, Changyu Qian, Hanqiang Deng et al.· ISPRS Int. J. Geo Inf.· 0 citations
Reconstructing 3D building models from point clouds acquired by UAV sensors remains challenging due to irregular building geometries and sensor noise. This paper proposes an unsupervised, geometry-oriented reconstruction method based on the line-symmetric bilateral point distribution features. The method constructs bas...
B. Xiao, Wei Xuan, Jinsong Gao et al.· Symmetry· 0 citations
Open-pit mines contain rapidly changing terrain, discontinuous bench structures, and mixed artificial–natural objects, which complicate automated three-dimensional mapping. This study presents a dual-module workflow for UAV LiDAR point clouds. Module A characterizes local geometry using normal and curvature descriptors...
