< Back to previous page
Publication
Comparison of Wall Reconstruction algorithms from Point Cloud Data for as-built BIM
Journal Contribution - Journal Article
As-built Building Information Models (BIMs) are becoming increasingly popular
in the Architectural, Engineering and Construction (AEC) industry. These
models reflect the state of the building up to as-built conditions. The production
of these models for existing buildings with no prior BIM includes the segmentation
and classification of point cloud data and the reconstruction of the
BIM objects. Automation in this process is a must as the manual Scan-to-BIM
procedure is both time-consuming and error prone. However, the automated
reconstruction from point cloud data is still ongoing research with both 2D
and 3D approaches being proposed. Also, there is little literature concerning
the quality assessment of the created entities.
In this research, we present our implementation of both approaches for
the reconstruction of the BIM geometry. Additionally, we perform a quality
assessment with respect to existing standards. The emphasis of this work is
on the creation of BIM objects based on unstructured point cloud data. More
specifically, we focus on the reconstruction of the wall geometry as it forms
the basis of the model. Both presented approaches are unsupervised methods that segment, classify and create generic wall elements. The first method operates
on the 3D point cloud itself and consists of a general approach for the
segmentation and classification and a class specific reconstruction algorithm
for the wall geometry. The point cloud is first segmented into planar clusters,
after which a Random Forests classifier is used with geometric and contextual
features for the semantic labelling. The final wall geometry is created based
on the 3D point clusters representing the walls. The second method is an efficient
Manhattan-world scene reconstruction algorithm that simultaneously
segments and classifies the point cloud based on point feature histograms.
The wall reconstruction is considered an instance of image segmentation by
representing the data as 2D raster images. Both methods have promising results
towards the reconstruction of wall geometry of multi-storey AEC industry
buildings. The experiments report that over 80% of the walls was correctly
segmented by both methods. Furthermore, the reconstructed geometry is conform
Level-of-Accuracy 20 for 88% of the data by the first method and for 55%
by the second method despite the Manhattan-world scene assumption. The resulting
BIM wall geometry can be used as a basis for the reconstruction of the
floors, ceilings, windows and door geometry.
Journal: Journal of Information Technology in Construction
ISSN: 1874-4753
Volume: 25
Pages: 173 - 192
Publication year:2020
Accessibility:Open