Automatic Method for Building Indoor Boundary Models from Dense Point Clouds Collected by Laser Scanners

Enrique Valero, Antonio Adán, Carlos Cerrada

Research output: Contribution to journalArticle

60 Citations (Scopus)

Abstract

In this paper we present a method that automatically yields Boundary Representation Models (B-rep) for indoors after processing dense point clouds collected by laser scanners from key locations through an existing facility. Our objective is particularly focused on providing single models which contain the shape, location and relationship of primitive structural elements of inhabited scenarios such as walls, ceilings and floors. We propose a discretization of the space in order to accurately segment the 3D data and generate complete B-rep models of indoors in which faces, edges and vertices are coherently connected. The approach has been tested in real scenarios with data coming from laser scanners yielding promising results. We have deeply evaluated the results by analyzing how reliably these elements can be detected and how accurately they are modeled.

Original languageEnglish
Pages (from-to)16099-16115
Number of pages17
JournalSensors
Volume12
Issue number12
DOIs
Publication statusPublished - Dec 2012

Keywords

  • 3D modeling
  • B-rep models
  • laser scanners
  • 3D data processing
  • ENVIRONMENTS
  • CONSTRUCTION
  • MAPS

Cite this