Pilot Study of 3D Point Cloud-based BIM Entity Classification

TaeYoul Lim; SangUk Han

doi:10.55785/JCAR.1.3.18

All Issue

2022 Vol.1, Issue 3 Preview Page

Pilot Study of 3D Point Cloud-based BIM Entity Classification 3D 포인트 클라우드 기반 BIM 객체 분류에 관한 선행연구

30 September 2022. pp. 18-24

PDF XML

Abstract

The successful mapping between IFC entities and BIM objects may directly enhance the semantic integrity of information and interoperability of BIM products. Despite the advance of standardized data models (e.g., IFC), however, the loss and error of information during data exchanges between BIM software still remain problematic in practice. This paper presents 3D point cloud-based BIM entity classification as a potential means of detecting and updating misclassified entities in IFC data for their semantic integrity. Specifically, for the prediction of IFC entities, the classification model is designed to learn the spatial patterns hidden in point cloud datasets, which are extracted and converted from IFC data. For performance evaluation, the model was tested on a dataset collected from two publicly available BIM data repositories, achieving an accuracy of 0.84 for the classification of 5 IFC entities. This approach thus may serve as a foundation for the improvement of information integrity and interoperability of BIM by allowing for automated updates of IFC data.

Keywords

BIM

IFC

Semantic Integrity

3D Point Cloud

Classification

BIM 소프트웨어 간 데이터 호환성 부족은 현재 다양한 분야에서 BIM을 활용하는데 있어 필수적으로 해결해야 하는 문제이다. 현재 활용되는 데이터 모델 표준인 IFC 데이터는 BIM 소프트웨어 간 데이터 교환 시 여전히 오류 및 누락이 발생하여 IFC 엔터티와 BIM 객체 간의 부정확한 매핑으로 인해 시멘틱 무결성이 보장 되지 않는 현상이 발생한다. 본 연구에서는 시멘틱 무결성을 위해 IFC 데이터에서 잘못 분류된 개체를 감지하고 업데이트하는 수단으로 3D 포인트 클라우드 기반 BIM 개체 분류 기법을 제시한다. 특히 IFC 엔티티 예측을 위해 IFC 데이터에서 추출 및 변환된 포인트 클라우드 데이터를 사용하여 특정 공간 패턴을 학습하도록 분류모델을 설계하였다. 실험 결과 5개의 IFC 엔터티(IfcBeam, IfcColumn, IfcSlab, IfcWall, IfcStair)에 대해 0.84의 분류 정확도를 달성했다. 이러한 접근법은 IFC 데이터의 업데이트를 자동화하기 위해 기초가 되는 기법으로 BIM 정보의 무결성 및 상호운용성을 개선하는데 기여할 수 있으리라 기대된다.

키워드

BIM

IFC

시멘틱 무결성

3D 포인트 클라우드

분류

References

김시현, 이원복, 유영수, 구본상 (2022). 딥러닝 기반 BIM 부재 자동분류 학습모델의 성능 향상을 위한 Ensemble 모델 구축에 관한 연구. KIBIM Magazine, 12(2), pp. 12-25.

진상윤 (2020). 스토리텔링 BIM. 씨아이알, pp. 79-82

Churcher, D., Davidson, S., and Kemp, A. (2019). The information management according to BS EN ISO 19650 Guidance Part 1: Concepts. 2nd ED., UKBIM Alliance Jul.

Eastman, C., Lee, J. M., Jeong, Y. S., and Lee, J. K. (2009). Automatic rule-based checking of building designs. Automation in construction, 18(8), pp. 1011-1033. 10.1016/j.autcon.2009.07.002

Emunds, C., Pauen, N., Richter, V., Frisch, J., and van Treeck, C. (2021). IFCNet: A Benchmark Dataset for IFC Entity Classification. In EG-ICE 2021 Workshop on Intelligent Computing in Engineering (p. 166). Universit¨ atsverlag der TU Berlin.

Emunds, C., Pauen, N., Richter, V., Frisch, J., and van Treeck, C. (2022). SpaRSE-BIM: Classification of IFC-based geometry via sparse convolutional neural networks. Advanced Engineering Informatics, 53, 101641. 10.1016/j.aei.2022.101641

Kajima Corp. (2018). Kajima Smart Future Vision. Kajima Corp. http://www.kajima.co.jp/english/tech/smart_future_vision/index.html

Kim, J., Song, J., and Lee, J. K. (2019). Recognizing and classifying unknown object in BIM using 2D CNN. In International Conference on Computer-Aided Architectural Design Futures (pp. 47-57). Springer, Singapore. 10.1007/978-981-13-8410-3_4

Koo, B., and Shin, B. (2018). Applying novelty detection to identify model element to IFC class misclassifications on architectural and infrastructure Building Information Models. Journal of Computational Design and Engineering, 5(4), pp. 391-400. 10.1016/j.jcde.2018.03.002

Koo, B., Jung, R., Yu, Y., and Kim, I. (2021). A geometric deep learning approach for checking element-to-entity mappings in infrastructure building information models. Journal of Computational Design and Engineering, 8(1), pp. 239-250. 10.1093/jcde/qwaa075

Kotsiantis, S. B., Zaharakis, I., and Pintelas, P. (2007). Supervised machine learning: A review of classification techniques. Emerging artificial intelligence applications in computer engineering, 160(1), pp. 3-24.

Krijnen, T., and Tamke, M. (2015). Assessing implicit knowledge in BIM models with machine learning. In Modelling Behaviour. Springer, Cham, pp. 397-406. 10.1007/978-3-319-24208-8_33

Lomio, F., Farinha, R., Laasonen, M., and Huttunen, H. (2018). Classification of building information model (BIM) structures with deep learning. In 2018 7th European Workshop on Visual Information Processing (EUVIP). IEEE, pp. 1-6. 10.1109/EUVIP.2018.8611701

Ma, L., Sacks, R., and Kattell, U. (2017). Building model object classification for semantic enrichment using geometric features and pairwise spatial relations. 10.24928/JC3-2017/0044

Qi, C. R., Su, H., Mo, K., and Guibas, L. J. (2017). Pointnet: Deep learning on point sets for 3d classification and segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition , pp. 652-660.

Romero-Jarén, R., and Arranz, J. J. (2021). Automatic segmentation and classification of BIM elements from point clouds. Automation in Construction, 124, 103576. 10.1016/j.autcon.2021.103576

Su, H., Maji, S., Kalogerakis, E., and Learned-Miller, E. (2015). Multi-view convolutional neural networks for 3d shape recognition. In Proceedings of the IEEE international conference on computer vision, pp. 945-953. 10.1109/ICCV.2015.114

Yu, Y., Lee, K., Koo, B., and Lee, K. (2021). Modeling Element Relations as Structured Graphs Via Neural Structured Learning to Improve BIM Element Classification. KSCE Journal of Civil and Environmental Engineering Research, 41(3), pp. 277-288.

Zhang, J., Luo, H., and Xu, J. (2022). Towards fully BIM-enabled building automation and robotics: A perspective of lifecycle information flow. Computers in Industry, 135, 103570. 10.1016/j.compind.2021.103570

Information

Publisher :Korean Society of Automation and Robotics in Construction
Publisher(Ko) :(사)한국건설자동화·로보틱스학회
Journal Title :Journal of Construction Automation and Robotics
Journal Title(Ko) :건설자동화·로보틱스 논문집
Volume : 1
No :3
Pages :18-24
Received Date : 2022-09-21
Revised Date : 2022-09-23
Accepted Date : 2022-09-26
DOI :https://doi.org/10.55785/JCAR.1.3.18

Journal of Construction Automation and Robotics ISSN:2800-0552(Print) 2951-116X(Online) 건설자동화·로보틱스 논문집

All Issue