Skip to main content
SpringerLink
Log in

3D Building Internal Structural Component Segmentation from Point Cloud Data Using DBSCAN and Modified RANSAC with Normal Deviation Conditions

  • Conference paper
  • First Online:
Data Science and Algorithms in Systems (CoMeSySo 2022)

Part of the book series: Lecture Notes in Networks and Systems ((LNNS,volume 597))

Included in the following conference series:

Abstract

Three-dimensional (3D) reconstruction of indoor environments from point cloud data is the process that has been studied and developed to facilitate the reconstruction of 3D models for old buildings. Prior to reconstruction, segmentation is the main process that is used to extract structural components such as floors, ceilings, and walls. This paper presents the segmentation method to extract the planar structures of a building from point cloud data. The original Random Sample Consensus (RANSAC) is modified by reducing computational complexity using localized sampling, and improving segmentation quality by adding smoothness constraints to the surface and applying the connectivity to the detected components. The results of the proposed method compared with those of the original RANSAC on the International Society for Photogrammetry and Remote Sensing (ISPRS) benchmark dataset indicate that the extracted components are more precise, more accurate, while also preserving the overall characteristics of the buildings.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 169.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 219.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Hichri, N., Stefani, C., de Luca, L., Veron, P., Hamon, G.: From point cloud to BIM: a survey of existing approaches. Int. Arch. Photogram. Remote Sens. Spat. Inf. Sci. XL-5/W2, 343–348 (2013)

    Google Scholar 

  2. Fischler, M.A., Bolles, R.C.: Random sample consensus. Commun. ACM 24(6), 381–395 (1981)

    Article  Google Scholar 

  3. Hough, P.V.C.: Method and means for recognizing complex patterns. U.S. Patent 3.069.654 (1962)

    Google Scholar 

  4. Tarsha-Kurdi, F., Landes, T., Grussenmeyer, P.: Hough-Transform and extended RANSAC algorithms for automatic detection of 3D building roof planes from LiDAR data. Int. Arch. Photogram. Remote Sens. Spat. Inf. Sci. 124–132 (2007)

    Google Scholar 

  5. Schnabel, R., Wahl, R., Klein, R.: Efficient RANSAC for point-cloud shape detection. Comput. Graph. Forum 214–226 (2007)

    Google Scholar 

  6. Kada, M., Luo, F.: Generalisation of building ground plans using half-spaces. Int. Arch. Photogram. Remote Sens. Spat. Inf. Sci. 36(4) (2008)

    Google Scholar 

  7. Budroni, A., Boehm, J.: Automated 3D reconstruction of interiors from point clouds. Int. J. Archit. Comput. 8(1), 55–73 (2010)

    Google Scholar 

  8. Capocchiano, F., Ravanelli, R., Crespi, M.: A tool for crowdsourced building information modeling throughlow-cost range camera: preliminary demonstration and potential. Int. Arch. Photogram. Remote Sens. Spat. Inf. Sci. XLII-2/W8, 75–81 (2017)

    Google Scholar 

  9. Capocchiano, F., Ravanelli, R.: An original algorithm for BIM generation from indoor survey point clouds. Int. Arch. Photogram. Remote Sens. Spat. Inf. Sci. XLII-2/W13, 769–776 (2019)

    Google Scholar 

  10. Murali, S., Speciale, P., Oswald, M.R., Pollefeys, M.: Indoor Scan2BIM: building information models of house interiors. In: IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (2017)

    Google Scholar 

  11. Macher, H., Landes, T., Grussenmeyer, P.: Point clouds segmentation as base for as-built BIM creation. ISPRS Ann. Photogram. Remote Sens. Spat. Inf. Sci. II-5/W3, 191–197 (2015)

    Google Scholar 

  12. Macher, H., Landes, T., Grussenmeyer, P.: From point clouds to building information models: 3d semi-automatic reconstruction of indoors of existing buildings. Appl. Sci. 7(10), 1030 (2017)

    Article  Google Scholar 

  13. Cui, Y., Li, Q., Yang, B., Xiao, W., Chen, C., Dong, Z.: Automatic 3-D reconstruction of indoor environment with mobile laser scanning point clouds. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 12(8), 3117–3130 (2019)

    Article  Google Scholar 

  14. Khoshelham, K., Díaz Vilariño, L., Peter, M., Kang, Z., Acharya, D.: The ISPRS benchmark on indoor modelling. Int. Arch. Photogram. Remote Sens. Spat. Inf. Sci. XLII-2/W7, 367–372 (2017)

    Google Scholar 

Download references

Acknowledgments

The authors would like to thank the Development and Promotion of Science and Technology Talents Project (DPST) for providing financial support. The implemented data were selected from the ISPRS benchmark on indoor modelling.

Author information

Authors and Affiliations

  1. Machine Intelligence and Multimedia Information Technology Laboratory, Department of Mathematics and Computer Science, Faculty of Science, Chulalongkorn University, Bangkok, Thailand

    Thanapon Doougphummet, Petarpa Boonserm & Rajalida Lipikorn

Authors
  1. Thanapon Doougphummet
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Petarpa Boonserm
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Rajalida Lipikorn
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Thanapon Doougphummet .

Editor information

Editors and Affiliations

  1. Faculty of Applied Informatics, Tomas Bata University in Zlín, Zlín, Czech Republic

    Radek Silhavy

  2. Faculty of Applied Informatics, Tomas Bata University in Zlín, Zlín, Czech Republic

    Petr Silhavy

  3. Faculty of Applied Informatics, Tomas Bata University in Zlín, Zlín, Czech Republic

    Zdenka Prokopova

Rights and permissions

Reprints and permissions

Copyright information

© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Doougphummet, T., Boonserm, P., Lipikorn, R. (2023). 3D Building Internal Structural Component Segmentation from Point Cloud Data Using DBSCAN and Modified RANSAC with Normal Deviation Conditions. In: Silhavy, R., Silhavy, P., Prokopova, Z. (eds) Data Science and Algorithms in Systems. CoMeSySo 2022. Lecture Notes in Networks and Systems, vol 597. Springer, Cham. https://doi.org/10.1007/978-3-031-21438-7_7

Download citation

Publish with us

Policies and ethics

Search

Navigation