Automatic generation of floor plans for indoor navigation using point cloud
U. Rajvanshi (TU Delft - Civil Engineering & Geosciences)
AA Verhagen – Mentor (TU Delft - Mathematical Geodesy and Positioning)
More Info
expand_more
Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
Abstract
This paper describes a methodology for an automated floor plan generation using point cloud captured via Mobile Laser Scanner(MLS) for indoor navigation purposes. The method takes as input a 3D point cloud and using geometrical features, a
ground plane histogram is computed representing the points density using projection. Finally using edge extraction and Hough Transform the polylines are extracted out in a very robust and efficient manner. This methodology works for any cluttered environment due to the projection and obtaining a volumetric slice where the extra noise is then removed using cluttering techniques. The
methodology tested on a hallway of academic building gives promising results.