Semantic Extraction of Permanent Structures for the Reconstruction of Building Interiors from Point Clouds

Coudron, Inge; Puttemans, Steven; Goedemé, Toon; Vandewalle, Patrick

doi:10.3390/s20236916

Cited by 13 publications

(8 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Lim et al [ 16 ] not only segmented structural and object points but also filled in the holes that are used to construct architectural points by projecting object points onto the structural surfaces. Coudron et al [ 23 ] used deep learning to extract permanent structures.…”

Section: Related Workmentioning

confidence: 99%

Automatic Reconstruction of Multi-Level Indoor Spaces from Point Cloud and Trajectory

Lim

Doh

2021

Sensors

View full text Add to dashboard Cite

Remarkable progress in the development of modeling methods for indoor spaces has been made in recent years with a focus on the reconstruction of complex environments, such as multi-room and multi-level buildings. Existing methods represent indoor structure models as a combination of several sub-spaces, which are constructed by room segmentation or horizontal slicing approach that divide the multi-room or multi-level building environments into several segments. In this study, we propose an automatic reconstruction method of multi-level indoor spaces with unique models, including inter-room and inter-floor connections from point cloud and trajectory. We construct structural points from registered point cloud and extract piece-wise planar segments from the structural points. Then, a three-dimensional space decomposition is conducted and water-tight meshes are generated with energy minimization using graph cut algorithm. The data term of the energy function is expressed as a difference in visibility between each decomposed space and trajectory. The proposed method allows modeling of indoor spaces in complex environments, such as multi-room, room-less, and multi-level buildings. The performance of the proposed approach is evaluated for seven indoor space datasets.

show abstract

Section: Related Workmentioning

confidence: 99%

Automatic Reconstruction of Multi-Level Indoor Spaces from Point Cloud and Trajectory

Lim

Doh

2021

Sensors

View full text Add to dashboard Cite

show abstract

“…Other works have deployed deep learning methods. The first group of these methods converts the point cloud into a structured grid 52 , which is memory-intensive and leads to losing much information 51 . The second group of methods, like PointNet 53 , directly applied deep learning to point clouds.…”

Section: Introductionmentioning

confidence: 99%

Automatic generation of structural geometric digital twins from point clouds

Mirzaei

Arashpour

Asadi

et al. 2022

Sci Rep

View full text Add to dashboard Cite

A geometric digital twin (gDT) model capable of leveraging acquired 3D geometric data plays a vital role in digitizing the process of structural health monitoring. This study presents a framework for generating and updating digital twins of existing buildings by inferring semantic information from as-is point clouds (gDT’s data) acquired regularly from laser scanners (gDT’s connection). The information is stored in updatable Building Information Models (BIMs) as gDT’s virtual model, and dimensional outputs are extracted for structural health monitoring (gDT’s service) of different structural members and shapes (gDT’s physical part). First, geometric information, including position and section shape, is obtained from the acquired point cloud using domain-specific contextual knowledge and supervised classification. Then, structural members’ function and section family type is inferred from geometric information. Finally, a BIM is automatically generated or updated as the virtual model of an existing facility and incorporated within the gDT for structural health monitoring. Experiments on real-world construction data are performed to illustrate the efficiency and precision of the proposed model for creating as-is gDT of building structural members.

show abstract

“…Moreover, a suchlike alignment process -also known as pose normalization -can still be a reasonable choice, even if the respective indoor reconstruction method does not presuppose a Manhattan World compliant building structure. This is for instance the case, when a respective indoor reconstruction approach makes use of a voxel grid or octree representation of the input data [23,29,16,36]. Even if a voxel-based indoor reconstruction approach is able to handle building structures deviating from the Manhattan World assumption, having room surfaces aligned with the coordinate axes and thus with the voxel grid will result in a cleaner and visually more appealing reconstruction in voxel space.…”

Section: Introductionmentioning

confidence: 99%

Pose Normalization of Indoor Mapping Datasets Partially Compliant to the Manhattan World Assumption

Hübner¹,

Weinmann²,

Wursthorn³

et al. 2021

Preprint

View full text Add to dashboard Cite

Due to their potential for a variety of applications, digital building models are meanwhile well established in planning, construction and usage phases of modern building projects. Older stock buildings however frequently lack digital representations and creating these manually is a tedious and time-consuming endeavor. For this reason, as well as due to the increasing availability of mobile indoor mapping systems facilitating the straight-forward, accurate and time-efficient capture of building structures, the automated reconstruction of building models from indoor mapping data has arisen as an active field of research.In this context, many approaches rely on simplifying suppositions about the structure of buildings to be reconstructed like e.g. the well-known Manhattan World assumption. This however not only presupposes that a given building structure itself is compliant to this assumption but also that the respective indoor mapping dataset is aligned accordingly with the coordinate axes. Indoor mapping systems on the other hand typically initialize the coordinate system arbitrarily by the sensor pose at the beginning of the mapping process. Indoor mapping data thus need to be aligned with the coordinate axes as a necessary preprocessing step for many indoor reconstruction approaches, which is also frequently known as pose normalization. Even in the case of indoor reconstruction approaches that do not rely on the Manhattan World assumption, such an alignment can be beneficial as it prevents aliasing effects when using data structures like voxel grids or octrees. Furthermore, it can be useful in the context of coregistering multiple indoor mapping datasets, for the automated analysis of architectural structures as well as for stabilization and drift-reduction in indoor mapping applications.In this paper, we present a novel pose normalization method for indoor mapping point clouds and triangle meshes that is robust against large fractions of the indoor mapping geometries deviating from an ideal Manhattan World structure. In the case of building structures that contain multiple Manhattan World systems, the dominant Manhattan World structure supported by the largest fraction of geometries is determined and used for alignment. In a first step, a vertical alignment orienting a chosen axis to be orthogonal to horizontal floor and ceiling surfaces is conducted. Subsequently, a rotation around the resulting vertical axis is determined that aligns the dataset horizontally with the coordinate axes. The proposed method is evaluated quantitatively against several publicly available indoor mapping datasets. Our implementation of the proposed procedure along with code for reproducing the evaluation will be made available to the public upon acceptance for publication.

show abstract

Semantic Extraction of Permanent Structures for the Reconstruction of Building Interiors from Point Clouds

Cited by 13 publications

References 40 publications

Automatic Reconstruction of Multi-Level Indoor Spaces from Point Cloud and Trajectory

Automatic Reconstruction of Multi-Level Indoor Spaces from Point Cloud and Trajectory

Automatic generation of structural geometric digital twins from point clouds

Pose Normalization of Indoor Mapping Datasets Partially Compliant to the Manhattan World Assumption

Contact Info

Product

Resources

About