Automatic generation of indoor navigable space using a point cloud and its scanner trajectory

B.R. Staats, A. A. Diakité, R. L. Voûte, S. Zlatanova

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

12 Citations (Scopus)
47 Downloads (Pure)

Abstract

Automatic generation of indoor navigable models is mostly based on 2D floor plans. However, in many cases the floor plans are out of date. Buildings are not always built according to their blue prints, interiors might change after a few years because of modified walls and doors, and furniture may be repositioned to the user's preferences. Therefore, new approaches for the quick recording of indoor environments should be investigated. This paper concentrates on laser scanning with a Mobile Laser Scanner (MLS) device. The MLS device stores a point cloud and its trajectory. If the MLS device is operated by a human, the trajectory contains information which can be used to distinguish different surfaces. In this paper a method is presented for the identification of walkable surfaces based on the analysis of the point cloud and the trajectory of the MLS scanner. This method consists of several steps. First, the point cloud is voxelized. Second, the trajectory is analysing and projecting to acquire seed voxels. Third, these seed voxels are generated into floor regions by the use of a region growing process. By identifying dynamic objects, doors and furniture, these floor regions can be modified so that each region represents a specific navigable space inside a building as a free navigable voxel space. By combining the point cloud and its corresponding trajectory, the walkable space can be identified for any type of building even if the interior is scanned during business hours.

Original languageEnglish
Title of host publicationISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
PublisherISPRS
Pages393-400
VolumeIV-2/W4
DOIs
Publication statusPublished - 2017
EventISPRS Geospatial Week 2017 - Wuhan, China
Duration: 18 Sep 201722 Sep 2017
http://www.isprs.org/documents/geoweek.aspx

Conference

ConferenceISPRS Geospatial Week 2017
CountryChina
CityWuhan
Period18/09/1722/09/17
Internet address

Keywords

  • 3D laser scanning
  • Dynamic objects
  • Floorplan
  • Indoor
  • MLS
  • Navigation space
  • Trajectory
  • Voxel

Fingerprint Dive into the research topics of 'Automatic generation of indoor navigable space using a point cloud and its scanner trajectory'. Together they form a unique fingerprint.

Cite this