Author: Wang, Ruolei
Title: Automatic extraction of indoor objects by using lidar point cloud
Advisors: Shi, Wenzhong John (LSGI)
Degree: M.Sc.
Year: 2017
Subject: Building information modeling
Buildingsā€”Computer-aided design
Remote sensing
Hong Kong Polytechnic University -- Dissertations
Department: Faculty of Construction and Environment
Department of Land Surveying and Geo-Informatics
Pages: vii, 93 pages : color illustrations
Language: English
Abstract: Recently, with the bring forward of concept of 'Smart City', the BIM technology is commonly accepted by users and continues to develop rapidly. Because of its rapid data collection, high accuracy and being less limited, laser scanning technology is increasingly used in data acquisition of building 3D modeling. Simultaneously, in order to improve the service ability of management and analysis of BIM, automatic extraction of windows and doors is a necessary work which can improve work efficiency and increase the level of detail of BIM. However, high accuracy of indoor scene description means a great quantity of data and high requirement of processing computer hardware. After introduction and analysis of previous related researches, principles and characteristics of laser scanning, and some classic point cloud processing algorithms. By using indoor LIDAR point clouds, an automatic extraction of window and doors method based on both position relationship and intensity correlation has been proposed in this dissertation. The core idea of the algorithm can be concluded as, after wall extraction, re-projecting the clutter within specific range back to the position where they should be, thereby obtaining the door and window coordinates. By using a program written in C++ and some related function libraries, the proposed algorithm is tested with four groups of indoor point clouds. After analysis and evaluation of experimental results, the proposed method is discussed and concluded, in addition, future works are listed aimed at the challenges met during the test.
Rights: All rights reserved
Access: restricted access

Files in This Item:
File Description SizeFormat 
991022385851303411.pdfFor All Users (off-campus access for PolyU Staff & Students only)5.35 MBAdobe PDFView/Open


Copyright Undertaking

As a bona fide Library user, I declare that:

  1. I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
  2. I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
  3. I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.

By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.

Show full item record

Please use this identifier to cite or link to this item: https://theses.lib.polyu.edu.hk/handle/200/10537