DBSCAN algorithm for segmenting indoor point clouds
DOI:
https://doi.org/10.46421/entac.v20i1.5834Keywords:
Point clouds, DBSCAN, BIMAbstract
Surveys carried out by laser scanners have been requested in a context of innovation and resource savings within the AECO (Architecture, Engineering, Construction and Operation) sector, especially in the BIM (Building Information Modeling) field, as they are capable of generating point clouds that accurately represent the real environment. Despite making surveys easier, working with point clouds can be a complex task, as they can require high computational processing power, in addition to modeling BIM models from these clouds being non-intuitive due to the overlapping of points from different elements. With the aim of facilitating BIM modeling from point clouds, the DBSCAN (Density-Based Spatial Clustering of Applications with Noise) segmentation algorithm was used in this study. An algorithm was developed in Python language using DBSCAN to segment a point cloud from an indoor environment. The algorithm proved to be useful for separating elements such as walls, floors, and roofs, allowing the export of segmented clouds of each of these elements to software such as Revit and facilitating BIM modeling.
References
KIM, Minju; LEE, Dongmin. Automated two-dimensional geometric model reconstruction from point cloud data for construction
quality inspection and maintenance. Automation in Construction, v. 154, p. 105024, 2023. ISSN 0926-5805. Disponível em https://
doi.org/10.1016/j.autcon.2023.105024. Acesso em 23 de Janeiro de 2024.
BRASIL. Presidência da República. Decreto nº 9.377, de 17 de maio de 2018. Estratégia Nacional de Disseminação do Building
Information Modelling no Brasil - Estratégia BIM BR. Diário Oficial da União, Brasília, DF, 17 maio de 2018. Disponível em https://
www2.camara.leg.br/legin/fed/decret/2018/decreto-9377-17-maio-2018-786731-publicacaooriginal-155623-pe.html. Acesso em 09
de abril de 2024.
CHEN, Hui et al. An approach to boundary detection for 3D point clouds based on DBSCAN clustering. Pattern Recognition, v. 124,
p. 108431, 2022.
Poux, F., & Billen, R. (2019). Voxel-based 3D point cloud semantic segmentation: unsupervised geometric and relationship
featuring vs deep learning methods. ISPRS International Journal of Geo-Information. 8(5), 213; https://doi.org/10.3390/ijgi8050213
GIONGO, Marcos et al. LiDAR: princípios e aplicações florestais. Pesquisa Florestal Brasileira, v. 30, n. 63, p. 231-231, 2010.
KOTB, Ahmed; HASSAN, Safaa; HASSAN, Hesham. A comparative study among various algorithms for lossless airborne LiDAR data
compression. In: 2018 14th International Computer Engineering Conference (ICENCO). IEEE, 2018. p. 17-21.
SEPASGOZAR, Samad ME; LIM, Samsung; SHIROWZHAN, Sara. Implementation of Rapid As-built Building Information Modeling
Using Mobile LiDAR. In: Construction Research Congress 2014: Construction in a Global Network. 2014. p. 209-218.
M.A. Fischler and R.C. Bolles. Random sample consensus: A paradigm for model fitting with applications to image analysis and
automated cartography. Communications of the ACM, 24(6):381–395, 1981. DOI: https://doi.org/10.1145/358669.358692
ESTER, Martin et al. A density-based algorithm for discovering clusters in large spatial databases with noise. In: kdd. 1996. p.
-231.
H. V. Singh, A. Girdhar and S. Dahiya, "A Literature survey based on DBSCAN algorithms," 2022 6th International Conference on
Intelligent Computing and Control Systems (ICICCS), Madurai, India, 2022, pp. 751-758, doi: https://doi.org/10.1109/
ICICCS53718.2022.9788440.
Lehtola, V., Nikoohemat, S., & Nüchter, A. (2020). Indoor 3D: Overview on scanning and reconstruction methods. Handbook of Big
Geospatial Data, 55–97. https://doi.org/10.1007/978-3-030-55462-0_3
Markus Götz, Christian Bodenstein, and Morris Riedel. 2015. HPDBSCAN: highly parallel DBSCAN. In Proceedings of the Workshop on Machine Learning in High-Performance Computing Environments (MLHPC '15). Association for Computing Machinery, New York,
NY, USA, Article 2, 1–10. https://doi.org/10.1145/2834892.2834894
Poux, F.; Mattes, C.; Kobelt, L. Unsupervised Segmentation of Indoor 3D Point Cloud: Application to Object-Based Classification.
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Volume XLIV-4/W1-2020,
