Automatic generation of floor plans for indoor navigation using point cloud

Student Report (2019)
Author(s)

U. Rajvanshi (TU Delft - Civil Engineering & Geosciences)

Contributor(s)

AA Verhagen – Mentor (TU Delft - Mathematical Geodesy and Positioning)

Faculty
Civil Engineering & Geosciences
Copyright
© 2019 Ullas Rajvanshi
More Info
expand_more
Publication Year
2019
Language
English
Copyright
© 2019 Ullas Rajvanshi
Graduation Date
27-01-2019
Awarding Institution
Delft University of Technology
Programme
['Geoscience and Remote Sensing']
Faculty
Civil Engineering & Geosciences
Reuse Rights

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.

Files

License info not available