Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2020 Jan 4;20(1):293.
doi: 10.3390/s20010293.

Automatic Indoor as-Built Building Information Models Generation by Using Low-Cost RGB-D Sensors

Yaxin Li  1   2 , Wenbin Li  2 , Shengjun Tang  3 , Walid Darwish  4   5 , Yuling Hu  2 , Wu Chen  1   2
Affiliations

Automatic Indoor as-Built Building Information Models Generation by Using Low-Cost RGB-D Sensors

Yaxin Li et al. Sensors (Basel). .

Abstract

To generate indoor as-built building information models (AB BIMs) automatically and economically is a great technological challenge. Many approaches have been developed to address this problem in recent years, but it is far from being settled, particularly for the point cloud segmentation and the extraction of the relationship among different elements due to the complicated indoor environment. This is even more difficult for the low-quality point cloud generated by low-cost scanning equipment. This paper proposes an automatic as-built BIMs generation framework that transforms the noisy 3D point cloud produced by a low-cost RGB-D sensor (about 708 USD for data collection equipment, 379 USD for the Structure sensor and 329 USD for iPad) to the as-built BIMs, without any manual intervention. The experiment results show that the proposed method has competitive robustness and accuracy, compared to the high-quality Terrestrial Lidar System (TLS), with the element extraction accuracy of 100%, mean dimension reconstruction accuracy of 98.6% and mean area reconstruction accuracy of 93.6%. Also, the proposed framework makes the BIM generation workflows more efficient in both data collection and data processing. In the experiments, the time consumption of data collection for a typical room, with an area of 45-67 m 2 , is reduced to 4-6 min with an RGB-D sensor from 50-60 min with TLS. The processing time to generate BIM models is about half minutes automatically, from around 10 min with a conventional semi-manual method.

Keywords: RGB-D sensors; as-built BIMs; automatic.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
Three stages of automatic building information models (BIM) generation by using a low-cost RGB-D sensor.
Figure 2
Figure 2
The main elements of hardware used in this paper, which includes one RGB-D camera and one iPad [37]. The total cost of the equipment is about 708 USD, 379 USD for the Structure sensor, and 329 USD for iPad.
Figure 3
Figure 3
The comparison between the raw depth and calibrated depth.
Figure 4
Figure 4
The example of (a) RGB image, (b) raw depth, and (c) filled depth.
Figure 5
Figure 5
Examples of depth encoding. (a) Raw depth image, (b) the horizontal disparity, (c) the height above ground, (d) the angle with gravity.
Figure 6
Figure 6
(a) The point cloud generated by low-cost RGB-D sensor, the empty area in the center area is caused by the data collection trajectory, (b) is the point cloud generated by terrestrial laser scanner (TLS).
Figure 7
Figure 7
The workflow of wall boundary extraction.
Figure 8
Figure 8
Description of the over-detection problem and the solution used in this paper.
Figure 9
Figure 9
Description of the over removing problem as well as the proposed solution.
Figure 10
Figure 10
One detail example of 2D wall lines extraction.
Figure 11
Figure 11
2D wall lines connection and refining.
Figure 12
Figure 12
Position and size extraction of door and windows.
Figure 13
Figure 13
The example of the output geometry information of elements.
Figure 14
Figure 14
The detail processes from the raw point clouds to BIM format models.
Figure 15
Figure 15
The compare of BIM format 3D models between the proposed method and ground truth.
Figure 16
Figure 16
The compare between measurement dimensions of the room and the actual values collected by range finder.
Figure 17
Figure 17
The compare between measurement length of the “narrow” walls and the actual values collected by range finder.
See this image and copyright information in PMC

References

    1. Volk R., Stengel J., Schultmann F. Building Information Modeling (BIM) for existing buildings—Literature review and future needs. Autom. Constr. 2014;38:109–127. doi: 10.1016/j.autcon.2013.10.023. - DOI
    1. Hartmann T., Van Meerveld H., Vossebeld N., Adriaanse A. Aligning building information model tools and construction management methods. Autom. Constr. 2012;22:605–613. doi: 10.1016/j.autcon.2011.12.011. - DOI
    1. Yan W., Culp C., Graf R. Integrating BIM and gaming for real-time interactive architectural visualization. Autom. Constr. 2011;20:446–458. doi: 10.1016/j.autcon.2010.11.013. - DOI
    1. Becker T., Nagel C., Kolbe T.H. 3D Geo-information Sciences. Springer; Berlin/Heidelberg, Germany: 2009. A multilayered space-event model for navigation in indoor spaces; pp. 61–77.
    1. Li N., Becerik-Gerber B., Krishnamachari B., Soibelman L. A BIM centered indoor localization algorithm to support building fire emergency response operations. Autom. Constr. 2014;42:78–89. doi: 10.1016/j.autcon.2014.02.019. - DOI

LinkOut - more resources