Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-2/W7, 345-352, 2017
https://doi.org/10.5194/isprs-archives-XLII-2-W7-345-2017
© Author(s) 2017. This work is distributed under
the Creative Commons Attribution 4.0 License.
 
12 Sep 2017
INDOOR MODELLING FROM SLAM-BASED LASER SCANNER: DOOR DETECTION TO ENVELOPE RECONSTRUCTION
L. Díaz-Vilariño1,2, E. Verbree2, S. Zlatanova3, and A. Diakité3 1Applied Geotechnologies Group, Dept. Natural Resources and Environmental Engineering, University of Vigo, Campus Lagoas-Marcosende, CP 36310 Vigo, Spain
2GIS Technology, OTB Research Institute for the Built Environment, Delft University of Technology, Julianalaan 134, Delft, the Netherlands
33D Geoinformation, Department of Urbanism, Delft University of Technology, Julianalaan 134, Delft, the Netherlands
Keywords: Combinatorial Geometry, Energy Minimization, Connectivity, Completeness, Trajectory Abstract. Updated and detailed indoor models are being increasingly demanded for various applications such as emergency management or navigational assistance. The consolidation of new portable and mobile acquisition systems has led to a higher availability of 3D point cloud data from indoors. In this work, we explore the combined use of point clouds and trajectories from SLAM-based laser scanner to automate the reconstruction of building indoors. The methodology starts by door detection, since doors represent transitions from one indoor space to other, which constitutes an initial approach about the global configuration of the point cloud into building rooms.

For this purpose, the trajectory is used to create a vertical point cloud profile in which doors are detected as local minimum of vertical distances. As point cloud and trajectory are related by time stamp, this feature is used to subdivide the point cloud into subspaces according to the location of the doors. The correspondence between subspaces and building rooms is not unambiguous. One subspace always corresponds to one room, but one room is not necessarily depicted by just one subspace, for example, in case of a room containing several doors and in which the acquisition is performed in a discontinue way. The labelling problem is formulated as combinatorial approach solved as a minimum energy optimization. Once the point cloud is subdivided into building rooms, envelop (conformed by walls, ceilings and floors) is reconstructed for each space. The connectivity between spaces is included by adding the previously detected doors to the reconstructed model. The methodology is tested in a real case study.

Conference paper (PDF, 1483 KB)


Citation: Díaz-Vilariño, L., Verbree, E., Zlatanova, S., and Diakité, A.: INDOOR MODELLING FROM SLAM-BASED LASER SCANNER: DOOR DETECTION TO ENVELOPE RECONSTRUCTION, Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-2/W7, 345-352, https://doi.org/10.5194/isprs-archives-XLII-2-W7-345-2017, 2017.

BibTeX EndNote Reference Manager XML