University of Twente Student Theses

Login
This website will be unavailable due to maintenance December 1st between 8:00 and 12:00 CET.

Space subdivision in indoor mobile laser scanning point clouds based on scanline analysis

Zheng, Li (2018) Space subdivision in indoor mobile laser scanning point clouds based on scanline analysis.

Link to full-text:https://ezproxy2.utwente.nl/login?url=https://library.itc.utwente.nl/login/2018/msc/gfm/zheng.pdf
(only accessible for UT students and staff)
Abstract:Indoor sceneshowsboard application in our daily life,such as navigation, mapping, disaster management etc.In order to meet the demands of these applications,the Indoor Mobile Laser Scanner (IMLS)iswidely utilised for acquiring indoor information.This is due to IMLSsystem not only obtain point cloudsat a sufficient level of detail and accuracywithin ashort periodbut also providesa continuous trajectory of device locations.Tohave a better understandingof the indoor scene, several objects like doors, windows and space subdivision arethe object of this research, which provides important architectural structure forindoor environments.This thesis proposesa workflow to subdivide space based on openingdetection results. Up to now, many openingdetection methods have been demonstrated based on trajectory and modelling which leads complicating operations, high computational load and low processing speed because they need analysis numerous pointsin thedataset.In this research, I demonstrated a novel openingdetection method which can efficientlydetectsboth doors and windowsby analysing scanlines. This method could be even usedin real-timeprocessing.After that,a two-step space subdivision method based on extracted openingsis described. Firstly, the trajectory points are subdividedinto differentspaces. Secondly, the corresponding point clouds thatarerelated to the trajectory points within same space aresubdividedbased on the detected doors. In the end, doors, windows and space subdivision results weresavedas point cloudlabel, which will be used for further investigations.The workflowhas been testedon the real dataset that collected by ZEB-REVO from GeoSLAM Company. Finally, the experimental results validated the completeness and robustness of the proposed methods under different indoor environment and different scanning paths.
Item Type:Essay (Master)
Faculty:ITC: Faculty of Geo-information Science and Earth Observation
Programme:Geoinformation Science and Earth Observation MSc (75014)
Link to this item:https://purl.utwente.nl/essays/85873
Export this item as:BibTeX
EndNote
HTML Citation
Reference Manager

 

Repository Staff Only: item control page