Journal of KIBIM (한국BIM학회 논문집)

Korean Institute of Building Information Modeling (한국BIM학회)
권호 표지
DOI QR코드

DOI QR Code

A Proposal of Deep Learning Based Semantic Segmentation to Improve Performance of Building Information Models Classification

Semantic Segmentation 기반 딥러닝을 활용한 건축 Building Information Modeling 부재 분류성능 개선 방안

  • 이고은 (서울과학기술대학교 건설시스템공학과) ;
  • 유영수 (서울과학기술대학교 건설시스템공학과) ;
  • 하대목 (서울과학기술대학교 건설시스템공학과) ;
  • 구본상 (서울과학기술대학교 건설시스템공학과) ;
  • 이관훈 (고려대학교 컴퓨터학과)
  • Received : 2021.07.09
  • Accepted : 2021.07.19
  • Published : 2021.09.30
Download PDF
⟨ Previous Next ⟩

Abstract

In order to maximize the use of BIM, all data related to individual elements in the model must be correctly assigned, and it is essential to check whether it corresponds to the IFC entity classification. However, as the BIM modeling process is performed by a large number of participants, it is difficult to achieve complete integrity. To solve this problem, studies on semantic integrity verification are being conducted to examine whether elements are correctly classified or IFC mapped in the BIM model by applying an artificial intelligence algorithm to the 2D image of each element. Existing studies had a limitation in that they could not correctly classify some elements even though the geometrical differences in the images were clear. This was found to be due to the fact that the geometrical characteristics were not properly reflected in the learning process because the range of the region to be learned in the image was not clearly defined. In this study, the CRF-RNN-based semantic segmentation was applied to increase the clarity of element region within each image, and then applied to the MVCNN algorithm to improve the classification performance. As a result of applying semantic segmentation in the MVCNN learning process to 889 data composed of a total of 8 BIM element types, the classification accuracy was found to be 0.92, which is improved by 0.06 compared to the conventional MVCNN.

Keywords

Acknowledgement

본 연구는 국토교통부 도시건축 연구개발사업의 연구비 지원 (21AUDP-B127891-05)에 의해 수행되었습니다.

References

  1. Bauer, S., Wiest, R., Nolte, L. P., Reyes, M. (2013). A survey of MRI-based medical image analysis for brain tumor studies, Physics in Medicine & Biology, 58(13), pp. 97-129.
  2. Belsky, M., Sacks, R., Brilakis, I. (2016). Semantic enrichment for building information modeling, Computer-Aided Civil and Infrastructure Engineering, 31(4), pp. 261-274. https://doi.org/10.1111/mice.12128
  3. Bloch, T., Sacks, R. (2018). Comparing machine learning and rule-based inferencing for semantic enrichment of BIM models, Automation in Construction, 91, pp. 256-272. https://doi.org/10.1016/j.autcon.2018.03.018
  4. buildingSMART Korea, KBIMS Library v1.02, http://step1.kbims.or.kr/sub/Default.aspx (Jan. 2019).
  5. Chen, L. C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A. L. (2017). Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs, IEEE transactions on pattern analysis and machine intelligence, 40(4), pp. 834-848. https://doi.org/10.1109/TPAMI.2017.2699184
  6. Cursi, S., Simeone, D., Coraglia, U. M. (2017). An ontology-based platform for BIM semantic enrichment, Educational and research in Computer Aided Architectural Design in Europe 35, 2, pp. 649-656.
  7. Jung, R. K., Koo, B. S., Yu, Y. S. (2019). Using Deep Learning for automated classification of wall subtypes for semantic integrity checking of Building Information Models, Korean Institute of Building Information Modeling, 9(4), pp. 31-40.
  8. Kim, I. H., Kim, Y. H., Choi, J. S. (2014). Building Code Typology and Application for Open BIM based Code Checking, Korean Journal of Computational Design and Engineering, 19(3), pp. 224-235. https://doi.org/10.7315/CADCAM.2014.224
  9. Koo, B. S., Yu, Y. S., Jung, R. K. (2018). Machine learning based approach to building element classification for semantic integrity checking of building information models, Korean Journal of Computational Design and Engineering, 23(4), pp. 373-383. https://doi.org/10.7315/cde.2018.373
  10. Krahenbuhl, P., Koltun, V. (2011). Efficient inference in fully connected crfs with gaussian edge potentials, Advances in neural information processing systems, 24(13), pp. 109-117.
  11. Lafferty, D., McCallum, A., Pereira, F. C. N. (2001). Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data, Proceedings of the Eighteenth International Conference on Machine Learning, 1(8), pp. 282-289.
  12. Long, J., Shelhamer, E., Darrell, T. (2015). Fully convolutional networks for semantic segmentation, Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 3431-3440.
  13. Lu, Q., Lee, S., Chen, L. (2018). Image-driven fuzzy-based system to construct as-is IFC BIM objects, Automation in Construction, 92, pp. 68-87. https://doi.org/10.1016/j.autcon.2018.03.034
  14. Ma, L., Sacks, R., Kattell, U. (2017). Building model object classification for semantic enrichment using geometric features and pairwise spatial relations, Proceedings of the Joint Conference on Computing in Construction, 1, pp. 373-380.
  15. Maturana, D., Scherer, S. (2015). Voxnet: A 3d convolutional neural network for real-time object recognition, 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 922-928.
  16. Ministry of Land, Infrastructure and Transport. (2020). Basic guidelines for BIM in the construction industry.
  17. Noh, H., Hong, S., Han, B. (2015). Learning deconvolution network for semantic segmentation, Proceedings of the IEEE international conference on computer vision, pp. 1520-1528.
  18. Prasoon, A., Petersen, K., Igel, C., Lauze, F., Dam, E., Nielsen, M. (2013). Deep feature learning for knee cartilage segmentation using a triplanar convolutional neural network, International conference on medical image computing and computer-assisted intervention, 2(31), pp. 246-253.
  19. Qi, C. R., Su, H., Mo, K., Guibas, L. J. (2017). Pointnet: Deep learning on point sets for 3d classification and segmentation, Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 652-660.
  20. Su, H., Maji, S., Kalogerakis, E., Learned-Miller, E. (2015). Multi-view convolutional neural networks for 3d shape recognition, Proceedings of the IEEE international conference on computer vision, pp. 945-953.
  21. Wu, Z., Song, S., Khosla, A., Yu, F., Zhang, L., Tang, X., Xiao, J. (2015). 3d shapenets: A deep representation for volumetric shapes, Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1912-1920.
  22. Xu, X., Zhou, F., Liu, B. (2018). Automatic bladde r segmentation from CT images using deep CNN and 3D fully connected CRF-RNN, International journal of computer assisted radiology and surgery, 13(7), pp. 967-975. https://doi.org/10.1007/s11548-018-1733-7
  23. Ying, H. Q., Lee, S. (2019). A Mask R-CNN Based Approach to Automatically Construct As-is IFC BIM Objects from Digital Images, Proceedings of the International Symposium on Automation and Robotics in Construction, 36, pp. 764-771.
  24. Yu, F., Koltun, V. (2015). Multi-scale context aggregation by dilated convolutions, arXiv preprint arXiv:1511.07122.
  25. Yu, Y. S., Lee, K. E., Koo, B. S., Lee, K. H. (2021). Modeling Element Relations as Structured Graphs Via Neural Structured Learning to Improve BIM Element Classification, Journal of Civil and Environmental Engineering Research, 41(3), pp. 227-288.
  26. Zhao, X., Wu, Y., Song, G., Li, Z., Zhang, Y., Fan, Y. (2018). A deep learning model integrating FCNNs and CRFs for brain tumor segmentation, Medical image analysis, 43(8), pp. 98-111. https://doi.org/10.1016/j.media.2017.10.002
  27. Zheng, S., Jayasumana, S., Romera-Paredes, B., Vineet, V., Su, Z., Du, D., Huang, C., Torr, P. H. S. (2015). Conditional random fields as recurrent neural networks, Proceedings of the IEEE International Conference on Computer Vision, pp. 1529-1537.