The data acquisition with Indoor Mobile Laser Scanners (IMLS) is quick, low-cost and accurate for indoor 3D modeling. Besides a point cloud, an IMLS also provides the trajectory of the mobile scanner. We analyze this trajectory jointly with the point cloud to support the labeling of noisy, highly reflected and cluttered points in indoor scenes. An adjacency-graph-based method is presented for detecting and labeling of permanent structures, such as walls, floors, ceilings, and stairs. Through occlusion reasoning and the use of the trajectory as a set of scanner positions, gaps are discriminated from real openings in the data. Furthermore, a voxel-based method is applied for labeling of navigable space and separating them from obstacles. The results show that 80% of the doors and 85% of the rooms are correctly detected, and most of the walls and openings are reconstructed. The experimental outcomes indicate that the trajectory of MLS systems plays an essential role in the understanding of indoor scenes. the complexity of 3D space. Few works deal with arbitrary wall layouts [6][7][8], but they are restricted to vertical walls and horizontal ceilings. Our method detects slanted walls and sloped ceilings exploiting the adjacency of permanent structures, based on the assumption that there is less clutter near the ceiling in indoor environments. Additionally, the arbitrary arrangements of walls (non-Manhattan-World) will be handled in this work. Our pipeline for semantic labeling of permanent structure uses detection of planar primitives labelled as wall, floor and ceiling, and their topological relations.Room segmentation is another research problem in large-scale indoor modeling. In the literature, different approaches, such as Voronoi graphs, cell decomposition, binary space partitioning and morphology operators [9] are suggested for 2D and 3D room segmentation. Some of these methods have limitations, such as Manhattan-World constraints and vertical walls. Most of the room segmentation methods rely on the viewpoint [8,10] and require scanning with a TLS in each room [7]. However, as opposed to one scanning location per room, mobile laser scanning systems produce a continuous trajectory and assigning points per room based on the scan location is not possible. Similar to our method for trajectory analysis, refs. [11,12] exploit the trajectory for space subdivision. Although their focus is only on space subdivision and simple structure, their results support our motivation of using the trajectory for interpretation of point clouds.In our pipeline, a novel method is suggested for partitioning interior spaces based on voxels and exploiting unoccupied space. Besides knowing the room layout, information about the doors, walkable space and stairs supports navigation planning. Therefore, voxels are used to identify the walkable space and the trajectory to identify the stairs and doors.Reflective surfaces, such as glass, complicate the analysis of indoor point clouds. Such surfaces cause the appearance of "ghost walls" in the...
ABSTRACT:The use of Indoor Mobile Laser Scanners (IMLS) for data collection in indoor environments has been increasing in the recent years. These systems, unlike Terrestrial Laser Scanners (TLS), collect data along a trajectory instead of at discrete scanner positions. In this research, we propose several methods to exploit the trajectories of IMLS systems for the interpretation of point clouds. By means of occlusion reasoning and use of trajectory as a set of scanner positions, we are capable of detecting openings in cluttered indoor environments. In order to provide information about both the partitioning of the space and the navigable space, we use the voxel concept for point clouds. Furthermore, to reconstruct walls, floor and ceiling we exploit the indoor topology and plane primitives. The results show that the trajectory is a valuable source of data for feature detection and understanding of indoor MLS point clouds.
ABSTRACT:Automated generation of 3D indoor models from point cloud data has been a topic of intensive research in recent years. While results on various datasets have been reported in literature, a comparison of the performance of different methods has not been possible due to the lack of benchmark datasets and a common evaluation framework. The ISPRS benchmark on indoor modelling aims to address this issue by providing a public benchmark dataset and an evaluation framework for performance comparison of indoor modelling methods. In this paper, we present the benchmark dataset comprising several point clouds of indoor environments captured by different sensors. We also discuss the evaluation and comparison of indoor modelling methods based on manually created reference models and appropriate quality evaluation criteria. The benchmark dataset is available for download at:
ABSTRACT:The paper presents a grammar-based approach for the robust automatic reconstruction of 3D interiors from raw point clouds. The core of the approach is a 3D indoor grammar which is an extension of our previously published grammar concept for the modeling of 2D floor plans. The grammar allows for the modeling of buildings whose horizontal, continuous floors are traversed by hallways providing access to the rooms as it is the case for most office buildings or public buildings like schools, hospitals or hotels. The grammar is designed in such way that it can be embedded in an iterative automatic learning process providing a seamless transition from LOD3 to LOD4 building models. Starting from an initial low-level grammar, automatically derived from the window representations of an available LOD3 building model, hypotheses about indoor geometries can be generated. The hypothesized indoor geometries are checked against observation data -here 3D point clouds -collected in the interior of the building. The verified and accepted geometries form the basis for an automatic update of the initial grammar. By this, the knowledge content of the initial grammar is enriched, leading to a grammar with increased quality. This higher-level grammar can then be applied to predict realistic geometries to building parts where only sparse observation data are available. Thus, our approach allows for the robust generation of complete 3D indoor models whose quality can be improved continuously as soon as new observation data are fed into the grammar-based reconstruction process. The feasibility of our approach is demonstrated based on a real-world example.
While location-based services are already well established in outdoor scenarios, they are still not available in indoor environments. The reason for this can be found in two open problems: First, there is still no off-the-shelf indoor positioning system for mobile devices and, second, indoor maps are not publicly available for most buildings. While there is an extensive body of work on the first problem, the efficient creation of indoor maps remains an open challenge. We tackle the indoor mapping challenge in our MapGENIE approach that automatically derives indoor maps from traces collected by pedestrians moving around in a building. Since the trace data is collected in the background from the pedestrians' mobile devices, MapGENIE avoids the labor-intensive task of traditional indoor map creation and increases the efficiency of indoor mapping. To enhance the map building process, MapGE-NIE leverages exterior information about the building and uses grammars to encode structural information about the building. Hence, in contrast to existing work, our approach works without any user interaction and only needs a small amount of traces to derive the indoor map of a building. To demonstrate the performance of MapGENIE, we implemented our system using Android and a foot-mounted IMU to collect traces from volunteers. We show that using our grammar approach, compared to a purely trace-based approach we can identify up to four times as many rooms in a building while at the same time achieving a consistently lower error in the size of detected rooms.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.