Door detection in 3D coloured point clouds of indoor environments

Blanca Quintana, Samuel A. Prieto, Antonio Adán, Frédéric Bosché

Research output: Contribution to journalArticle

Abstract

Door detection is becoming an increasingly important subject in building indoor modelling owing to its value in scan-to-BIM processes. This paper presents an original approach that detects open, semi-open and closed doors in 3D laser scanned data of indoor environments. The proposed technique is unique in that it integrates the information regarding both the geometry (i.e. XYZ coordinates) and colour (i.e. RGB or HSV) provided by a calibrated set of 3D laser scanner and a colour camera. In other words, our technique is developed in a 6D-space framework. The geometry-colour integration and other characteristics of our method make it robust to occlusion and variations in colours resulting from varying lighting conditions at each scanning location (e.g. specular highlights) and from different scanning locations. In addition to this paper, the authors also contribute a public dataset of real scenes along with an annotated ground truth. The dataset has varying levels of challenges and will help to assess the performance of new and existing contributions in the field. The approach proposed in this paper is tested against that dataset, yielding encouraging results.
LanguageEnglish
Pages146-166
Number of pages21
JournalAutomation in Construction
Volume85
Early online date5 Nov 2017
DOIs
Publication statusPublished - Jan 2018

Fingerprint

Color
Scanning
Geometry
Lasers
Lighting
Cameras

Cite this

Quintana, Blanca ; Prieto, Samuel A. ; Adán, Antonio ; Bosché, Frédéric. / Door detection in 3D coloured point clouds of indoor environments. In: Automation in Construction. 2018 ; Vol. 85. pp. 146-166.
@article{485729ddca3d42a794f092dbc2457c43,
title = "Door detection in 3D coloured point clouds of indoor environments",
abstract = "Door detection is becoming an increasingly important subject in building indoor modelling owing to its value in scan-to-BIM processes. This paper presents an original approach that detects open, semi-open and closed doors in 3D laser scanned data of indoor environments. The proposed technique is unique in that it integrates the information regarding both the geometry (i.e. XYZ coordinates) and colour (i.e. RGB or HSV) provided by a calibrated set of 3D laser scanner and a colour camera. In other words, our technique is developed in a 6D-space framework. The geometry-colour integration and other characteristics of our method make it robust to occlusion and variations in colours resulting from varying lighting conditions at each scanning location (e.g. specular highlights) and from different scanning locations. In addition to this paper, the authors also contribute a public dataset of real scenes along with an annotated ground truth. The dataset has varying levels of challenges and will help to assess the performance of new and existing contributions in the field. The approach proposed in this paper is tested against that dataset, yielding encouraging results.",
author = "Blanca Quintana and Prieto, {Samuel A.} and Antonio Ad{\'a}n and Fr{\'e}d{\'e}ric Bosch{\'e}",
year = "2018",
month = "1",
doi = "10.1016/j.autcon.2017.10.016",
language = "English",
volume = "85",
pages = "146--166",
journal = "Automation in Construction",
issn = "0926-5805",
publisher = "Elsevier",

}

Door detection in 3D coloured point clouds of indoor environments. / Quintana, Blanca; Prieto, Samuel A.; Adán, Antonio; Bosché, Frédéric.

In: Automation in Construction, Vol. 85, 01.2018, p. 146-166.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Door detection in 3D coloured point clouds of indoor environments

AU - Quintana, Blanca

AU - Prieto, Samuel A.

AU - Adán, Antonio

AU - Bosché, Frédéric

PY - 2018/1

Y1 - 2018/1

N2 - Door detection is becoming an increasingly important subject in building indoor modelling owing to its value in scan-to-BIM processes. This paper presents an original approach that detects open, semi-open and closed doors in 3D laser scanned data of indoor environments. The proposed technique is unique in that it integrates the information regarding both the geometry (i.e. XYZ coordinates) and colour (i.e. RGB or HSV) provided by a calibrated set of 3D laser scanner and a colour camera. In other words, our technique is developed in a 6D-space framework. The geometry-colour integration and other characteristics of our method make it robust to occlusion and variations in colours resulting from varying lighting conditions at each scanning location (e.g. specular highlights) and from different scanning locations. In addition to this paper, the authors also contribute a public dataset of real scenes along with an annotated ground truth. The dataset has varying levels of challenges and will help to assess the performance of new and existing contributions in the field. The approach proposed in this paper is tested against that dataset, yielding encouraging results.

AB - Door detection is becoming an increasingly important subject in building indoor modelling owing to its value in scan-to-BIM processes. This paper presents an original approach that detects open, semi-open and closed doors in 3D laser scanned data of indoor environments. The proposed technique is unique in that it integrates the information regarding both the geometry (i.e. XYZ coordinates) and colour (i.e. RGB or HSV) provided by a calibrated set of 3D laser scanner and a colour camera. In other words, our technique is developed in a 6D-space framework. The geometry-colour integration and other characteristics of our method make it robust to occlusion and variations in colours resulting from varying lighting conditions at each scanning location (e.g. specular highlights) and from different scanning locations. In addition to this paper, the authors also contribute a public dataset of real scenes along with an annotated ground truth. The dataset has varying levels of challenges and will help to assess the performance of new and existing contributions in the field. The approach proposed in this paper is tested against that dataset, yielding encouraging results.

U2 - 10.1016/j.autcon.2017.10.016

DO - 10.1016/j.autcon.2017.10.016

M3 - Article

VL - 85

SP - 146

EP - 166

JO - Automation in Construction

T2 - Automation in Construction

JF - Automation in Construction

SN - 0926-5805

ER -