Machine Learning Based Architectural Drawing Element Extraction and Fire-Protection Design Automation: An Automated Layout Algorithm

Sang-Hun Yeon; Min-Gyu Kim; Doochan Choi; Kwang-Ho Lee

doi:10.21086/ksles.2025.10.32.5.582

All Issue

2025 Vol.32, Issue 5 Preview Page Next Page

Research Article

Machine Learning Based Architectural Drawing Element Extraction and Fire-Protection Design Automation: An Automated Layout Algorithm 머신러닝 기반 건축도면 요소 추출 및 소방설계 자동화: 화재방호 설비 자동 배치 알고리즘

31 October 2025. pp. 582-592

PDF XML

Abstract

This study develops and validates an algorithm that automates fire-protection design from architectural drawings. Building-summary tables and annotations are parsed with optical character recognition (OCR) and OpenCV to normalize occupancy, gross floor area, story count, and floor height. Doors and columns are detected by a You Only Look Once v4 (YOLO v4) convolutional neural network, and room boundaries are reconstructed to form space-level metadata. A rule engine derived from the National Fire Safety Code (NFSC) determines installation or exemption for each system and computes equipment placement and wiring. Outputs are written as computer-aided design (CAD) entities through the AutoCAD application programming interface. In tests, table structure and text recognition reached accuracy 0.91, precision 0.89, recall 0.99, F1 Score 0.94, and intersection-over-union 0.83. Average detection confidence was 0.89 for doors and 0.86–0.93 for columns. Checklist comparison yielded about 97% normal outputs, and repeated runs reproduced coordinates and connections, indicating reliable end-to-end automation from image inputs to CAD deliverables.

Keywords

Fire-protection design automation

Architectural floor plans

Automated recognition

Machine learning

AutoCAD

References

Bochkovskiy, A., Wang, C.-Y., & Liao, H.-Y. M. (2020). YOLOv4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934. https://doi.org/10.48550/arXiv.2004.10934

10.48550/arXiv.2004.10934

Choi, D. C., Kim, M. G., Kim, C. H., & Park, G. W. (2024). Development of Design Engineering Solutions for AI-Based Fire Protection System. Seoul: Korea Fire Protection UBIS Co., Ltd.

Choi, S.-H., & Lee, J.-K. (2023). Generative AI for automated urban housing floor plan generation. Korean Journal of Computational Design and Engineering, 28(4), 514-523. https://doi.org/10.7315/CDE.2023.514

10.7315/CDE.2023.514

Everingham, M., Van Gool, L., Williams, C. K. I., Winn, J., & Zisserman, A. (2010). The PASCAL Visual Object Classes (VOC) challenge. International Journal of Computer Vision, 88(2), 303-338. https://doi.org/10.1007/s11263-009-0275-4

10.1007/s11263-009-0275-4

JaidedAI. (2024, September 24). EasyOCR. Retrieved October 7, 2025, https://github.com/JaidedAI/EasyOCR

Joe, G. S., & Park, S. H. (2023). A study on development of real-time monitoring platform based on IoT for building fire safety management. Journal of the Korean Institute of Architectural and Environmental Building Systems, 17(2), 98-109. https://doi.org/10.22696/jkiaebs.20230009

10.22696/jkiaebs.20230009

Kim, I., Lee, M., Choi, J., & Kim, G. (2016). Development of an application to generate 2D drawings in automation using open BIM technologies. Korean Journal of Computational Design and Engineering, 21(4), 417-425. http://dx.doi.org/10.7315/CDE.2016.417

10.7315/CDE.2016.417

Kim, M. G., Ko, S. Y., & Choi, D. C. (2025). A study on AI-based fire protection system design automation technology using CNN. Journal of the Society of Disaster Information, 21(1), 186-192. https://doi.org/10.15683/kosdi.2025.3.31.186

10.15683/kosdi.2025.3.31.186

Lee, H. K., Choi, J. H., & Cho, H. S. (2020). Research for automatic generation of 2D design drawings of firefighting equipment using AI. Proceedings of the Korea Institute of Fire Science and Engineering Conference, 2020(1), 47-47

Lee, H. Y., & Park, D. W. (2023). Application of AI firefighting drone and artificial intelligence in case of fire. The Journal of the Korea Institute of Communications and Information Sciences, 48(4), 469-477. https://doi.org/10.7840/kics.2023.48.4.469

10.7840/kics.2023.48.4.469

Lee, S., Park, J.-H., Lee, K.-B., & Lee, J. (2024). Automatic generation system for Industry Foundation Classes files based on 2D drawings for Building Information Modeling. Journal of the Korea Institute of Information and Communication Engineering, 28(12), 1597-1604. https://doi.org/10.6109/jkiice.2024.28.12.1597

10.6109/jkiice.2024.28.12.1597

Lv, X., Zhao, S., Yu, X., & Zhao, B. (2021). Residential floor plan recognition and reconstruction. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 16717-16726. https://ieeexplore.ieee.org/document/9577792

10.1109/CVPR46437.2021.01644

Min, D. L., & Cho, H. Y. (2021). Fire nozzle internal shape design to reduce anti-repulsive force. Transactions of the Korean Society of Mechanical Engineers A, 45(8), 699-707. https://doi.org/10.3795/KSME-A.2021.45.8.699

10.3795/KSME-A.2021.45.8.699

Ministry of Land, Infrastructure and Transport. (2025, September 29). Nationwide building stock: 7,421,603 buildings and 4.314 billion m². Retrieved October 7, 2025, from https://www.molit.go.kr/USR/NEWS/m_71/dtl.jsp?id=95091261

Nam, G.-T., Jun, S.-K., & Choi, D.-C. (2022). A study on the development of AI-based fire fighting facility design technology through image recognition. Journal of the Society of Disaster Information, 18(4), 883- 890. https://doi.org/10.15683/kosdi.2022.12.31.883

10.15683/kosdi.2022.12.31.883

National Fire Agency. (n.d). Fire legislation information. Retrieved October 7, 2025, from https://www.nfa.go.kr

National Fire Agency. (n.d). National Fire Safety Code. Retrieved. October 7, 2025. from https://feia.ekffa.or.kr/doc/nfsc/

Parente, J., Rodrigues, E., Rangel, B., & Martins, J. P. (2023). Integration of convolutional and adversarial networks into building design: A review. Journal of Building Engineering, 76, 10.1016/j.jobe.2023.1071557155. https://doi.org/10.1016/j.jobe.2023.107155

10.1016/j.jobe.2023.107155

Sokolova, M., & Lapalme, G. (2009). A systematic analysis of performance measures for classification tasks. Information Processing & Management, 45(4), 427- 437. https://doi.org/10.1016/j.ipm.2009.03.002

10.1016/j.ipm.2009.03.002

Villena Toro, J., Wiberg, A., & Tarkian, M. (2023). Optical character recognition on engineering drawings to achieve automation in production quality control. Frontiers in Manufacturing Technology, 3, 1154132. https://doi.org/10.3389/fmtec.2023.1154132

10.3389/fmtec.2023.1154132

Wang, Y., Liu, Y., Cai, H., Wang, J., & Zhou, X. (2023). An automated fire code compliance checking jointly using building information models and natural language processing. Fire, 6(9), 358. https://doi.org/10.3390/fire6090358

10.3390/fire6090358

Yeon, S. H., Kim, C. H., Park, K.W., Choi, D. C., Jo, Y., Choi, J. M., & Lee, K. H. (2023). Automated extraction of fire protection system design information from architectural drawings using artificial intelligence. Korean Journal of Air-Conditioning and Refrigeration Engineering, 35(7), 331-342. https://doi.org/10.6110/KJACR.2023.35.7.331

10.6110/KJACR.2023.35.7.331

Zeng, Z., Li, X., Yu, Y. K., & Fu, C.-W. (2019). Deep floor plan recognition using a multi-task network with room-boundary-guided attention. arXiv preprint arXiv: 1908.11025. https://doi.org/10.1109/ICCV.2019.00919

10.1109/ICCV.2019.00919

Information

Publisher :The Korean Society of Living Environmental System
Publisher(Ko) :한국생활환경학회
Journal Title :Journal of The Korean Society of Living Environmental System
Journal Title(Ko) :한국생활환경학회
Volume : 32
No :5
Pages :582-592
Received Date : 2025-10-11
Revised Date : 2025-10-15
Accepted Date : 2025-10-24
DOI :https://doi.org/10.21086/ksles.2025.10.32.5.582

Journal of The Korean Society of Living Environmental System ISSN:1226-1289(Print) 한국생활환경학회

All Issue