Generation of Structural Components for Indoor Spaces from Point Clouds

Point clouds from laser scanners have been widely used in recent research on indoor modeling methods. Currently, particularly in data-driven modeling methods, data preprocessing for dividing structural components and nonstructural components is required before modeling. In this paper, we propose an...

Full description

Saved in:
Bibliographic Details
Main Authors: Junhyuk Lee, Yutaka Ohtake, Takashi Nakano, Daisuke Sato
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/10/3012
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849718944284278784
author Junhyuk Lee
Yutaka Ohtake
Takashi Nakano
Daisuke Sato
author_facet Junhyuk Lee
Yutaka Ohtake
Takashi Nakano
Daisuke Sato
author_sort Junhyuk Lee
collection DOAJ
description Point clouds from laser scanners have been widely used in recent research on indoor modeling methods. Currently, particularly in data-driven modeling methods, data preprocessing for dividing structural components and nonstructural components is required before modeling. In this paper, we propose an indoor modeling method without the classification of structural and nonstructural components. A pre-mesh is generated for constructing the adjacency relations of point clouds, and plane components are extracted using planar-based region growing. Then, the distance fields of each plane are calculated, and voxel data referred to as a surface confidence map are obtained. Subsequently, the inside and outside of the indoor model are classified using a graph-cut algorithm. Finally, indoor models with watertight meshes are generated via dual contouring and mesh refinement. The experimental results showed that the point-to-mesh error ranged from approximately 2 mm to 50 mm depending on the dataset. Furthermore, completeness—measured as the proportion of original point-cloud data successfully reconstructed into the mesh—approached 1.0 for single-room datasets and reached around 0.95 for certain multiroom and synthetic datasets. These results demonstrate the effectiveness of the proposed method in automatically removing non-structural components and generating clean structural meshes.
format Article
id doaj-art-2210960b5ccb410e97dd9b51c657a1c0
institution DOAJ
issn 1424-8220
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-2210960b5ccb410e97dd9b51c657a1c02025-08-20T03:12:15ZengMDPI AGSensors1424-82202025-05-012510301210.3390/s25103012Generation of Structural Components for Indoor Spaces from Point CloudsJunhyuk Lee0Yutaka Ohtake1Takashi Nakano2Daisuke Sato3School of Precision Engineering, The University of Tokyo, Tokyo 113-8654, JapanSchool of Precision Engineering, The University of Tokyo, Tokyo 113-8654, JapanDataLabs, Inc., Tokyo 103-0024, JapanDataLabs, Inc., Tokyo 103-0024, JapanPoint clouds from laser scanners have been widely used in recent research on indoor modeling methods. Currently, particularly in data-driven modeling methods, data preprocessing for dividing structural components and nonstructural components is required before modeling. In this paper, we propose an indoor modeling method without the classification of structural and nonstructural components. A pre-mesh is generated for constructing the adjacency relations of point clouds, and plane components are extracted using planar-based region growing. Then, the distance fields of each plane are calculated, and voxel data referred to as a surface confidence map are obtained. Subsequently, the inside and outside of the indoor model are classified using a graph-cut algorithm. Finally, indoor models with watertight meshes are generated via dual contouring and mesh refinement. The experimental results showed that the point-to-mesh error ranged from approximately 2 mm to 50 mm depending on the dataset. Furthermore, completeness—measured as the proportion of original point-cloud data successfully reconstructed into the mesh—approached 1.0 for single-room datasets and reached around 0.95 for certain multiroom and synthetic datasets. These results demonstrate the effectiveness of the proposed method in automatically removing non-structural components and generating clean structural meshes.https://www.mdpi.com/1424-8220/25/10/30123D indoor modeling3D reconstructionplanar-based region growinggraph-cutunsigned distance fields
spellingShingle Junhyuk Lee
Yutaka Ohtake
Takashi Nakano
Daisuke Sato
Generation of Structural Components for Indoor Spaces from Point Clouds
Sensors
3D indoor modeling
3D reconstruction
planar-based region growing
graph-cut
unsigned distance fields
title Generation of Structural Components for Indoor Spaces from Point Clouds
title_full Generation of Structural Components for Indoor Spaces from Point Clouds
title_fullStr Generation of Structural Components for Indoor Spaces from Point Clouds
title_full_unstemmed Generation of Structural Components for Indoor Spaces from Point Clouds
title_short Generation of Structural Components for Indoor Spaces from Point Clouds
title_sort generation of structural components for indoor spaces from point clouds
topic 3D indoor modeling
3D reconstruction
planar-based region growing
graph-cut
unsigned distance fields
url https://www.mdpi.com/1424-8220/25/10/3012
work_keys_str_mv AT junhyuklee generationofstructuralcomponentsforindoorspacesfrompointclouds
AT yutakaohtake generationofstructuralcomponentsforindoorspacesfrompointclouds
AT takashinakano generationofstructuralcomponentsforindoorspacesfrompointclouds
AT daisukesato generationofstructuralcomponentsforindoorspacesfrompointclouds