Data-Driven Modeling of Building Interiors From Lidar Point Clouds

Abstract

Abstract. This paper deals with 3D modeling of building interiors from point clouds captured by a 3D LiDAR scanner. Indeed, currently, the building reconstruction processes remain mostly manual. While LiDAR data have some specific properties which make the reconstruction challenging (anisotropy, noise, clutters, etc.), the automatic methods of the state-of-the-art rely on numerous construction hypotheses which yield 3D models relatively far from initial data. The choice has been done to propose a new modeling method closer to point cloud data, reconstructing only scanned areas of each scene and excluding occluded regions. According to this objective, our approach reconstructs LiDAR scans individually using connected polygons. This modeling relies on a joint processing of an image created from the 2D LiDAR angular sampling and the 3D point cloud associated to one scan. Results are evaluated on synthetic and real data to demonstrate the efficiency as well as the technical strength of the proposed method.

An Efficient Approach to Automatic Construction of 3D Watertight Geometry of Buildings Using Point Clouds

“…Using the reconstruction grammar rules defined in Section 2.2.3, the initial 2D boundaries obtained from each room candidate are shown in Figure 10a2,b2,c2 for the three The distances between individual data points representing the structural elements and the corresponding nearest planes of the geometric model (in Figure 11) generated for each site were calculated, the average value of which was used as the error statistics to assess the overall accuracy of the final 3D geometric model created. The mean errors (given in Table 1) for the six sites considered were found to be 13-21 mm, in comparison to 8-54 mm (Table 2) reported in similar studies in the literature [19,[21][22][23][24]. It should be noted that the mean errors are not only affected by the reconstruction method itself but also depend on several other factors, such as the measurement accuracy of the devices used to collect the data and the presence of thin objects (e.g., whiteboard at Site 2) attached to the wall and/or ceiling surfaces.…”

“…Three-dimensional geometric models of building structures have widely been used in various applications such as indoor navigation guidance [7,8], the management of energy, space and emergency [9][10][11], health monitoring and retrofit planning [12][13][14], and risk management of the decommissioning processes [15][16][17][18] of buildings. Using point cloud data, researchers have proposed a variety of approaches to the automatic reconstruction of building structures [11,[19][20][21][22][23][24]. In these approaches, there are mainly two steps in the process of the 3D geometric modelling for a building.…”

“…More specifically, the requirements consist of watertight geometries and accurate partitions of the indoor space to represent distinct thermal zones [6]. For example, the approaches in Bassier and Vergauwen [54] and Sanchez et al [24] led to non-watertight geometric models that are unsuitable for energy simulations.…”

Normal Classification of 3d Occupancy Grids for Voxel-Based Indoor Reconstruction From Point Clouds

“…Automated reconstruction of building environments from indoor mapping data such as point clouds is a wide and active field of research (Kang et al, 2020;Pintore et al, 2020). The various proposed approaches differ significantly in the amount of assumptions that are made with respect to the building structure to be reconstructed and thus in their flexibility towards challenging building environments, ranging from single room scenarios (Li et al, 2020;Sanchez et al, 2020b), Manhattan World structures where all surfaces are orthogonal to the coordinate axes (Ryu et al, 2020;Kim et al, 2020) to diagonal (Shi et al, 2019;Tran and Khoshelham, 2020) or even curved walls (Yang et al, 2019;Wu et al, 2020) and slanted ceilings (Nikoohemat et al, 2020;Lim and Doh, 2021).…”

Effective Selection of Variable Point Neighbourhood for Feature Point Extraction from Aerial Building Point Cloud Data

“…Estimation of the feature points and lines is a fundamental problem in the field of image and shape analysis as this estimation facilitates better understanding of an object in a variety of areas, e.g., data registration [1], data simplification [2], road extraction [3], and building reconstruction [4]. Specifically, the area of 3D building reconstruction has a broad range of applications, such as building type classification, urban planning, solar potential estimation, change detection, forest management, and virtual tours [5][6][7][8][9][10]. Due to the availability of 3D point cloud data, from both airborne and ground-based mobile laser scanning systems, the extraction of 3D feature points and lines from point cloud data has become an attractive research topic to describe an object shape more accurately.…”