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

Sensors

Enrique Valero²  Antonio Adán¹ 

[1] 3D Visual Computing and Robotics Lab, Universidad de Castilla-La Mancha (UCLM), Paseo de la Universidad, 4, 13071 Ciudad Real, Spain; E-Mail:;School of Computer Engineering, Universidad Nacional de Educación a Distancia (UNED), C/Juan del Rosal, 16, 28040 Madrid, Spain; E-Mail:

关键词: 3D modeling;    B-rep models;    laser scanners;    3D data processing;   

DOI  :  10.3390/s121216099

来源: mdpi

【 摘 要 】

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.

【 授权许可】

CC BY   
© 2012 by the authors; licensee MDPI, Basel, Switzerland