Door detection in 3D coloured point clouds of indoor environments

• Published in: Automation in construction Vol. 85; pp. 146 - 166
• Main Authors: Quintana, B., Prieto, S.A., Adán, A., Bosché, F.
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier B.V 01.01.2018; Elsevier BV
• Subjects: 3-D technology; Building information model; Building information modeling; Building management systems; Color; Door detection; Geometry; Ground truth; Indoor environments; Indoor navigation; Indoor spatial data model; Occlusion; Point cloud; Robot; Robots; Scan-to-BIM; Scanning; Spatial data; Three dimensional models; 3D; Indoor spatial data model; Point cloud; Indoor navigation; Scan-to-BIM; Building information model; Robot; Door detection
• ISSN: 0926-5805; 1872-7891
• DOI: 10.1016/j.autcon.2017.10.016

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. •New method for door detection in coloured 3D point clouds (6D data framework)•The 6D data is obtained using a calibrated set of a laser scanner and an SLR camera with a flash.•The method is robust under conditions of occlusion and non-homogeneous illumination.•The method detects open, semi-open and closed doors.•Performance is demonstrated with a dataset containing various levels of challenges made public by the authors.