Abstract
This paper discusses the challenge of using 3D models created during the design stage in the construction stage due to the need for segmentation or remodeling to incorporate activity concepts. To address this challenge, the paper proposes a methodology that uses the PointNet deep learning technique to automatically classify and segment design model elements into activity units for the construction stage while preserving attribute information. The authors introduce a module that utilize the bounding box concept to simplify the segmentation process after importing the 3D model into the 4D system used in the construction stage. This eliminates the need for separate CAD software and allows for direct segmentation into activity units within the 4D system and simultaneous simulation. The proposed methodology was applied to two real bridge projects and demonstrated increased 3D model reusability in the construction stage. The paper concludes that this approach can improve the usability of 3D models for construction projects.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Andrichm W, Daniotti B, Pavan A, Mirarchi C (2022) Check and validation of building information models in detailed design phase: A check flow to pave the way for BIM-based renovation and construction processes. Buildings 12(2):154, DOI: https://doi.org/10.3390/buildings12020154
Ciribini ALC, Ventura SM, Paneroni M (2016) Implementation of an interoperable process to optimise design and construction phases of a residential building: A BIM pilot project. Automation in Construction 71:62–73, DOI: https://doi.org/10.1016/j.autcon.2016.03.005
Dashti MS, RezaZadeh M, Khanzadi M, Taghaddos H (2021) Integrated BIM-based simulation for automated time-space conflict management in construction projects. Automation in Construction 132:103957, DOI: https://doi.org/10.1016/j.autcon.2021.103957
Enshassi MA, Al Hallaq KA, Tayeh BA (2019) Limitation factors of Building Information Modeling (BIM) implementation. The Open Construction & Building Technology Journal 13(1):189–196, DOI: https://doi.org/10.2174/1874836801913010189
Getuli V, Capone P, Bruttini A, Isaac S (2020) BIM-based immersive virtual reality for construction workspace planning: A safety-oriented approach. Automation in Construction 114:103160, DOI: https://doi.org/10.1016/j.autcon.2020.103160
Google Colab (2022) Retrieved July 4, 2022, https://colab.research.google.com/
Grandio J, Riveiro B, Soilán M, Arias P (2022) Point cloud semantic segmentation of complex railway environments using deep learning. Automation in Construction 141:104425, DOI: https://doi.org/10.1016/j.autcon.2022.104425
Griffiths D (2020) Point cloud classification with PointNet, Retrieved April 5, 2022, https://keras.io/examples/vision/pointnet/
Griffiths D, Boehm J (2019) A review on deep learning techniques for 3D sensed data classification. Remote Sensing 11(12):1499, DOI: https://doi.org/10.3390/rs11121499
GSA (2009) BIM guides, Retrieved may 30, 2022, https://www.gsa.gov/real-estate/design-and-construction/3d4d-building-information-modeling/bim-guides
Han KK, Cline D, Golparvar-Fard M (2015) Formalized knowledge of construction sequencing for visual monitoring of work-in-progress via incomplete point clouds and low-LoD 4D BIMs. Automation in Construction 29(4):889–901, DOI: https://doi.org/10.1016/j.aei.2015.10.006
Hartmann T, Gao J, Fischer M (2008) Areas of application for 3D and 4D models on construction projects. Journal of Construction Engineering and Management 134(10):776–785, DOI: https://doi.org/10.1061/(ASCE)0733-9364(2008)134:10(776)
Jung RK, Koo BS, Yu YS (2019) Using deep learning for automated classification of wall subtypes for semantic integrity checking of building information models. Journal of KIBIM 9(4):31–40, DOI: https://doi.org/10.13161/KIBIM.2019.9.4.031 (in Korean)
Kim CM, Son HJ, Kim CW (2013) Automated construction progress measurement using a 4D building information model and 3D data. Automation in Construction 31:75–82, DOI: https://doi.org/10.1016/j.autcon.2012.11.041
Kim JS, Song JY, Lee JK (2019) Recognizing and classifying unknown object in BIM using 2D CNN. In Computer-Aided Architectural Design. “Hello Culture” 18th International Conference, CAAD 2019, Daejoen, Republic of Korea, Jun 26–28, 2019, Selected Papers 18:47–57, DOI: https://doi.org/10.1007/978-981-13-8410-34
Kim HJ, Yoon JY, Sim SH (2020) Automated bridge component recognition from point clouds using deep learning. Structural Control and Health Monitoring 27(9):e2591, DOI: https://doi.org/10.1002/stc.2591
Koo BS, Jung RK, Yu YS (2020) Automatic classification of wall and door BIM element subtypes using 3D geometric deep neural networks. Advanced Engineering Informatics 47:101200, DOI: https://doi.org/10.1016/j.aei.2020.101200
Lee JH, Park JJ, Yoon HC (2020a) Automatic bridge design parameter extraction for scan-to-BIM. Applied Sciences 10(20):7346, DOI: https://doi.org/10.3390/app10207346
Lee JH, Park JJ, Yoon HC (2020b) Automatic classification of bridge component based on deep learning. KSCE Journal of Civil and Environmental Engineering Research 40(2):239–245, DOI: https://doi.org/10.12652/KSCE.2020.40.2.0239 (in Korean)
Malsane S, Matthews J, Lockley S, Love PE, Greenwood D (2015) Development of an object model for automated compliance checking. Automation in Construction 49:51–58, DOI: https://doi.org/10.1016/j.autcon.2014.10.004
Mattaraia L, Fabricio MM, Codinhoto R (2021) Structure for the classification of disassembly applied to BIM models. Architectural Engineering and Design Management 19(1):56–73, DOI: https://doi.org/10.1080/17452007.2021.1956420
Popov V, Juocevicius V, Migilinskas D, Ustinovichius L, Mikalauskas S (2010) The use of a virtual building design and construction model for developing an effective project concept in 5D environment. Automation in Construction 19(3):357–367, DOI: https://doi.org/10.1016/j.autcon.2009.12.005
Qi CR, Su H, Mo K, Guibas LJ (2017) PointNet: Deep learning on point sets for 3D classification and segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 652–660, DOI: https://doi.org/10.48550/arXiv.1706.02413
Rakshit S, Paul S (2020) Point cloud segmentation with PointNet, Retrieved April 5, 2022, https://keras.io/examples/vision/pointnet_segmentation/
Rausch C, Sanchez B, Haas C (2019) Spatial parameterization of non-semantic CAD elements for supporting automated disassembly planning. Modular and Offsite Construction (MOC) Summit Proceedings 108–115, DOI: https://doi.org/10.29173/mocs83
Revit Dynamo (2022) Retrieved May 12, 2022, https://dynamobim.org/
Rho GH, Park MS, Lee HS (2020) Automated construction progress management using computer vision-based CNN model and BIM. Korea Journal of Construction Engineering and Management 21(5):11–19, DOI: https://doi.org/10.6106/KJCEM.2020.21.5.011 (in Korean)
Romero-Jarén R, Arranz JJ (2021) Automatic segmentation and classification of BIM elements from point clouds. Automation in Construction 124:103576, DOI: https://doi.org/10.1016/j.autcon.2021.103576
Ryu YM, Kim BK, Park JJ (2021) Effect of learning data on the semantic segmentation of railroad tunnel using deep learning. Journal of the Korean Geotechnical Society 37(11):107–118, DOI: https://doi.org/10.7843/kgs.2021.37.11.107 (in Korean)
Sanchez B, Haas C (2018) A novel selective disassembly sequence planning method for adaptive reuse of buildings. Journal of Cleaner Production 183:998–1010, DOI: https://doi.org/10.1016/j.jclepro.2018.02.201
Sanchez B, Rausch C, Haas C, Hartmann T (2021) A framework for BIM-based disassembly models to support reuse of building components. Resources, Conservation and Recycling 175:105825, DOI: https://doi.org/10.1016/j.resconrec.2021.105825
Sanchez B, Rausch C, Haas C, Saari R (2020) A selective disassembly multi-objective optimization approach for adaptive reuse of building components. Resources, Conservation and Recycling 154:104605, DOI: https://doi.org/10.1016/j.resconrec.2019.104605
Soilán Rodríguez M, Nóvoa Martínez A, Sánchez Rodríguez A, Riveiro Rodríguez B, Arias Sánchez P (2020) Semantic segmentation of point clouds with pointnet and kpconv architectures applied to railway tunnels. ISPRS Annals of Photogrammetry Remote Sensing and Spatial Information Sciences 281–288, DOI: https://doi.org/10.5194/isprs-annals-V-2-2020-281-2020
Wu J, Zhang J, Debs L (2022) Model validation for automated building code compliance checking. In Construction Research Congress 2022 640–650, DOI: https://doi.org/10.1061/9780784483961.067
Yoon SW, Kim SA, Choi JM, Keum DY, Jo CW (2015) A proposal for using BIM model created in design to construction phase - Case study on preconstruction adopting BIM. Journal of KIBIM 5(4):1–10, DOI: https://doi.org/10.13161/kibim.2015.5.4.001 (in Korean)
Zhao W, Jiang Y, Liu Y, Shu J (2022) Automated recognition and measurement based on three-dimensional point clouds to connect precast concrete components. Automation in Construction 133:104000, DOI: https://doi.org/10.1016/j.autcon.2021.104000
Acknowledgments
This study was conducted through the 2022 Research Fund Support Project of the Korea Agency for Infrastructure Technology Advancement (22RBIM-C158185-03).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Lee, J., Park, S. & Kang, L. Methodology for Activity Unit Segmentation of Design 3D Models Using PointNet Deep Learning Technique. KSCE J Civ Eng 28, 29–44 (2024). https://doi.org/10.1007/s12205-023-0816-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12205-023-0816-3