Journal of the Architectural Institute of Korea (대한건축학회논문집)

Architectural Institute of Korea (대한건축학회)
권호 표지
DOI QR코드

DOI QR Code

Objective Typification of Building Exteriors Using Deep Learning - Focused on Public Office Buildings -

건축물 외관의 객관적 유형화를 위한 딥러닝의 활용 - 공공청사를 중심으로 -

  • An, Jong-Gyu (Dept. of Architecture and Architectural Engineering, Seoul National University) ;
  • Zo, Hangman (Dept. of Architecture and Architectural Engineering, Institute of Construction and Environmental Engineering, Seoul National University)
  • 안종규 (서울대 건축학과 ) ;
  • 조항만 (서울대 건축학과.서울대 건설환경종합연구소)
  • Received : 2023.04.24
  • Accepted : 2023.08.07
  • Published : 2023.08.30
⟨ Previous Next ⟩

Abstract

This study introduces an objective typification methodology that employs deep learning to analyze the exterior appearances of buildings. The conventional approach to typification was reliant on subjective analysis and was limited in terms of the number of structures that could be assessed. This study aimed to overcome these limitations by establishing an objective typification method using deep learning, focusing specifically on public office buildings. The research process involved a comprehensive survey of domestic public office buildings to compile an image dataset. Subsequently, a model was constructed utilizing Convolutional Neural Networks (CNN), a form of deep learning, to grasp the distinctive features of building images. These features, extracted from the CNN model, were then organized into groups through k-means clustering. The outcome of this clustering enabled the analysis of each cluster's unique characteristics, facilitating the establishment of typification criteria such as building height, fa?ade pattern, materials, protrusions, and roof structures. This methodology's effectiveness was validated through a comparative analysis with prior research. The results of this study offer potential applications in fundamental investigations concerning the current state of public office buildings and in typification studies encompassing diverse architectural forms beyond public office buildings.

Keywords

References

  1. Ahn, E. (2021). An analysis on the evolution of Korean apartment unit plans using deep learning. Journal of the Architectural Institute of Korea, 37(10), 13-22.  https://doi.org/10.5659/JAIK.2021.37.10.13
  2. Ahn, J. K. (2014). Study on images of a city and surface design of public office buildings. Journal of Cultural Product & Design, 37(0), 81-90. 
  3. Archisoup (2017). Understanding building yypology. Retrieved April 2, 2023 from https://www.archisoup.com/understanding-building-typology 
  4. Arthur, D., & Vassilvitskii, S. (2007). K-means++: the advantages of careful seeding. In Proceedings of the eighteenth annual ACM-SIAM symposium on Discrete algorithms (SODA '07). Society for Industrial and Applied Mathematics, USA, 1027-1035. 
  5. Buhrmester, V., Munch, D., & Arens, M. (2021). Analysis of explainers of black box deep neural networks for computer vision: A survey. Machine Learning and Knowledge Extraction, 3(4), 966-989.  https://doi.org/10.3390/make3040048
  6. Cha, H. C., & Park, C. M. (2021). A study on the expressive technique of government office design considering locality - focused on "Winner of Architectural Competition" in Jeju-do -. Journal of the Architectural Institute of Korea, 37(7), 33-42.  https://doi.org/10.5659/JAIK.2021.37.7.33
  7. Chaurasia, A. (2020). Exploring ResNets with W&B. Retrieved July 6, 2023 from https://wandb.ai/site/articles/exploring-resnets-with-w-b 
  8. Choi, H. Y., Choi, Y. K., & Jeon, Y. H. (2014). A study on the publicness of atrium space in government office - focused on the evaluation of publicness and deduction of design elements -. Journal of the Korean Institute of Culture Architecture, 46, 93-100. 
  9. Choi., Y. K., & Hyun, C. Y. (2011). A study on the evolution of the spatial organization appeared in local government buildings in Korea. Journal of the Korean Institute of Interior Design, 20(6), 36-43. 
  10. Franck, K. A., & Schneekloth, L. H. (2012). Ordering Space: Types in Architecture and Design, Nanam, 
  11. Gholamy, A., Kreinovich, V., & Kosheleva, O. (2018). Why 70/30 or 80/20 relation between training and testing sets: A pedagogical explanation. International Journal of Intelligent Technologies and Applied Statisticsl, 11(2). 
  12. Gu, J., Wang, Z., Kuen, J., Ma, L., Shahroudy, A., Shuai, B., Liu, T., Wang, X., Wang, G., Cai, J., & Chen, T. (2018). Recent advances in convolutional neural networks, Pattern Recognition, 77, 354-377.  https://doi.org/10.1016/j.patcog.2017.10.013
  13. Guerin, J., Gibaru, O., Thiery, S., & Nyiri, E. (2018). CNN features are also great at unsupervised classification. Ithaca: Cornell University Library, arXiv.org. 
  14. Hong, S. J., & Lee, Y. S. (2022). Typification of irregular shaped land parcels using machine learning. Journal of the Architectural Institute of Korea, 38(3), 189-198.  https://doi.org/10.5659/JAIK.2022.38.3.189
  15. Hyun, C., & Lee, J. (2020). A study on the characteristic of spatial structure of government buildings by types. Journal of the Korea Institute of the Spatial Design, 15(7), 319-328. 
  16. Hyun, C. Y., & Choi., Y. K. (2021). A chronological analysis of spatial structure in Korean government buildings through space syntax. KIEAE Journal, 21(2), 103-112.  https://doi.org/10.12813/kieae.2021.21.2.103
  17. Irani, J., Pise, N., & Phatak, M. (2016). Clustering techniques and the similarity measures used in clustering: A survey. International Journal of Computer Applications. 134. 9-14.  https://doi.org/10.5120/ijca2016907841
  18. Jeffares, A. (2019). K-means: A complete introduction. Towards Data Science. Retrieved July 6, 2023 from https://towardsdatascience.com/k-means-a-complete-introduction-1702af9cd8c 
  19. Kang, E. J., & Choi, S. H. (2014). A study on the planning characteristics & improvement of citizen cultural space in public building in terms of cultural administration - focused on the cases since 2000's -. Korean Institute of Interior Design Journal, 23(2), 174-181.  https://doi.org/10.14774/JKIID.2014.23.2.174
  20. Kang, M. S., Jung, Y. G., & Jang, D. H. (2017). A study on the search of optimal aquaculture farm condition based on machine learning. The Journal of the Institute of Internet, Broadcasting and Communication, 17(2), 135-140.  https://doi.org/10.7236/JIIBC.2017.17.2.135
  21. Kim, C. S., Dong, J. U., & Lee, H. R. (2013). Design criteria for effective public building construction process. Journal of The Korean Digital Architecture Interior Association, 13(1), 43-53. 
  22. Kim, J. H. (1997). A study on the composition of facade in the small commercial buildings, Journal of the Korean Institute of Interior Design, (13), 181-186. 
  23. Kim, J. M., & Kim, D. J. (2014). Typology as form generating process in contemporary architecture. Journal of the Korean Institute of Interior Design, 23(5), 3-13. 
  24. Kwon, N. Y., Kwon, E., & Jung, S. (2020). A study on the classification of theft using k-modes clustering - focused on correlation between land use and types of theft -. Journal of the Architectural Institute of Korea, 36(8), 81-90.  https://doi.org/10.5659/JAIK.2020.36.8.81
  25. Lee, H. (2022). Post-authoritarian design of public offices - focused on the plaza and facade of metropolitan city halls that emerged after local autonomy -. Journal of the Architectural Institute of Korea, 38(7), 127-138.  https://doi.org/10.5659/JAIK.2022.38.7.127
  26. Oh, J. H., Kim, H. G., & Kim, S. S. (2021). Development of representative envelope types in existing public building for green remodeling. Journal of the Architectural Institute of Korea, 37(12), 277-284.  https://doi.org/10.5659/JAIK.2021.37.12.277
  27. Pan, S. J., & Yang, Q. (2010). A survey on transfer learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345-1359.  https://doi.org/10.1109/TKDE.2009.191
  28. Ryu, H. (2019). A case study on space design characteristics of public buildings in Korea - focusing on citizen cultural space -. Journal of the Korea Institute of the Spatial Design, 14(1), 93-104.  https://doi.org/10.35216/kisd.2019.14.1.93
  29. Shorten, C., & Khoshgoftaar, T.M. (2019). A survey on image data augmentation for deep learning. Journal of Big Data, 6, 1-48.  https://doi.org/10.1186/s40537-018-0162-3
  30. Wani, M. A., Bhat, F. A., Afzal, S., & Khan, A. I. (2020). Basics of supervised deep learning. Advances in Deep Learning, Studies in Big Data, vol 57. Springer, 13-29  https://doi.org/10.1007/978-981-13-6794-6_2
  31. Yoshimura, Y., Cai, B., Wang, Z., & Ratti, C. (2019). Deep learning architect: classification for architectural design through the eye of artificial intelligence. Computers in Urban Planning and Urban Management for Smart Cities, CUPUM 2019, 249-265 
  32. Youm, C. H., & Lim, H. S. (2010). Establishment of architectural process design guideline for public office buildings, auri, 2010(2), 1-252.