Automated Scan-vs-BIM Registration Using Columns Segmented by Deep Learning for Construction Progress Monitoring

In construction automation applications, coarse registration between 3D Building Information Modelling (BIM) and the as-built point cloud is vital for the monitoring of construction progress. This can be achieved by extracting highly distinct geometric features in both datasets to speed up the corre...

Full description

Saved in:
Bibliographic Details
Main Authors: G. Z. Tsige, B. S. A. Alsadik, S. Oude Elberink, M. Bassier
Format: Article
Language:English
Published: Copernicus Publications 2025-08-01
Series:The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Online Access:https://isprs-archives.copernicus.org/articles/XLVIII-G-2025/1455/2025/isprs-archives-XLVIII-G-2025-1455-2025.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849247844455677952
author G. Z. Tsige
B. S. A. Alsadik
S. Oude Elberink
M. Bassier
author_facet G. Z. Tsige
B. S. A. Alsadik
S. Oude Elberink
M. Bassier
author_sort G. Z. Tsige
collection DOAJ
description In construction automation applications, coarse registration between 3D Building Information Modelling (BIM) and the as-built point cloud is vital for the monitoring of construction progress. This can be achieved by extracting highly distinct geometric features in both datasets to speed up the correspondence search. However, the existing geometric feature-based coarse registration methods have limitations in the Architecture, Engineering, Construction &amp; Facility Management (AEC/FM) context because building designs often contain a considerable self-similarity, symmetry, and lack of texture.</p> <p>In this work, we propose an automatic coarse registration method that is motivated by the Random Sample Consensus (RANSAC) algorithm to estimate the transformation parameters that best align the as-built point cloud in the coordinate frame of the BIM model by matching the corresponding columns. The method is based on the extraction of columns from the as-built point cloud and the as-planned BIM model. For the point cloud data, fully automated column extraction techniques are used by applying deep learning, whereas the BIM model columns are extracted from the available semantic information. Experiments are carried out on real-life datasets from the building construction site to validate the proposed method. The results show that our proposed column-based registration method achieved an RMSE of 2 centimeters , and the cloud-to-cloud mean distance of 1.6cm &plusmn; 1.8cm after fine registration. The accuracy of the co-registration result shows that our proposed approach contributes to automating the registration between the as-built point cloud and the as-planned BIM model for construction progress monitoring.
format Article
id doaj-art-b38e71ff4351491da8eeaed4a4464e54
institution Kabale University
issn 1682-1750
2194-9034
language English
publishDate 2025-08-01
publisher Copernicus Publications
record_format Article
series The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
spelling doaj-art-b38e71ff4351491da8eeaed4a4464e542025-08-20T03:58:07ZengCopernicus PublicationsThe International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences1682-17502194-90342025-08-01XLVIII-G-20251455146210.5194/isprs-archives-XLVIII-G-2025-1455-2025Automated Scan-vs-BIM Registration Using Columns Segmented by Deep Learning for Construction Progress MonitoringG. Z. Tsige0B. S. A. Alsadik1S. Oude Elberink2M. Bassier3Earth Observation Science Department, ITC Faculty, University of Twente, 7522 NH Enschede, The NetherlandsEarth Observation Science Department, ITC Faculty, University of Twente, 7522 NH Enschede, The NetherlandsEarth Observation Science Department, ITC Faculty, University of Twente, 7522 NH Enschede, The NetherlandsDept. of Civil Engineering, TC Construction- Geomatics KULeuven- Faculty of Engineering Technology Ghent, BelgiumIn construction automation applications, coarse registration between 3D Building Information Modelling (BIM) and the as-built point cloud is vital for the monitoring of construction progress. This can be achieved by extracting highly distinct geometric features in both datasets to speed up the correspondence search. However, the existing geometric feature-based coarse registration methods have limitations in the Architecture, Engineering, Construction &amp; Facility Management (AEC/FM) context because building designs often contain a considerable self-similarity, symmetry, and lack of texture.</p> <p>In this work, we propose an automatic coarse registration method that is motivated by the Random Sample Consensus (RANSAC) algorithm to estimate the transformation parameters that best align the as-built point cloud in the coordinate frame of the BIM model by matching the corresponding columns. The method is based on the extraction of columns from the as-built point cloud and the as-planned BIM model. For the point cloud data, fully automated column extraction techniques are used by applying deep learning, whereas the BIM model columns are extracted from the available semantic information. Experiments are carried out on real-life datasets from the building construction site to validate the proposed method. The results show that our proposed column-based registration method achieved an RMSE of 2 centimeters , and the cloud-to-cloud mean distance of 1.6cm &plusmn; 1.8cm after fine registration. The accuracy of the co-registration result shows that our proposed approach contributes to automating the registration between the as-built point cloud and the as-planned BIM model for construction progress monitoring.https://isprs-archives.copernicus.org/articles/XLVIII-G-2025/1455/2025/isprs-archives-XLVIII-G-2025-1455-2025.pdf
spellingShingle G. Z. Tsige
B. S. A. Alsadik
S. Oude Elberink
M. Bassier
Automated Scan-vs-BIM Registration Using Columns Segmented by Deep Learning for Construction Progress Monitoring
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
title Automated Scan-vs-BIM Registration Using Columns Segmented by Deep Learning for Construction Progress Monitoring
title_full Automated Scan-vs-BIM Registration Using Columns Segmented by Deep Learning for Construction Progress Monitoring
title_fullStr Automated Scan-vs-BIM Registration Using Columns Segmented by Deep Learning for Construction Progress Monitoring
title_full_unstemmed Automated Scan-vs-BIM Registration Using Columns Segmented by Deep Learning for Construction Progress Monitoring
title_short Automated Scan-vs-BIM Registration Using Columns Segmented by Deep Learning for Construction Progress Monitoring
title_sort automated scan vs bim registration using columns segmented by deep learning for construction progress monitoring
url https://isprs-archives.copernicus.org/articles/XLVIII-G-2025/1455/2025/isprs-archives-XLVIII-G-2025-1455-2025.pdf
work_keys_str_mv AT gztsige automatedscanvsbimregistrationusingcolumnssegmentedbydeeplearningforconstructionprogressmonitoring
AT bsaalsadik automatedscanvsbimregistrationusingcolumnssegmentedbydeeplearningforconstructionprogressmonitoring
AT soudeelberink automatedscanvsbimregistrationusingcolumnssegmentedbydeeplearningforconstructionprogressmonitoring
AT mbassier automatedscanvsbimregistrationusingcolumnssegmentedbydeeplearningforconstructionprogressmonitoring