SURVEY TEKNIK PENGKLASIFIKASIAN GAYA ARSITEKTUR PADA FASAD BANGUNAN MENGGUNAKAN PENDEKATAN DEEP LEARNING CNN

Edy Sutomo

doi:10.35760/dk.2020.v19i2.2619

SURVEY TEKNIK PENGKLASIFIKASIAN GAYA ARSITEKTUR PADA FASAD BANGUNAN MENGGUNAKAN PENDEKATAN DEEP LEARNING CNN

Edy Sutomo
Program Studi Teknik Arsitektur, Universitas Gunadarma
Indonesia

DOI: http://dx.doi.org/10.35760/dk.2020.v19i2.2619

Abstract

Teknik pengklasifikasian gaya arsitektur pada fasad bangunan menjadi bagian penting pada dunia perancangan, guna mempercepat proses dalam melakukan kajian tipologinya. Dewasa ini dengan semakin berkembangnya teknologi informasi, sangat memungkinkan bila seiring waktu dengan berbagai kemajuan metode dalam mengekstraksi obyek bangunan utamanya fasad bangunan. Penelitian dalam pengklasifikasian fasad bangunan banyak dilakukan untuk menelusuri jenis bangunan maupun aspek estetika lainnya. Demi tujuan tersebut studi survey ini dimaksudkan untuk mengetahui teknik komputasi Deep Learning (DL) yang dapat digunakan dalam mengidentifikasi fasad bangunan secara lebih akurat dengan membedakan dan mengelompokkannya agar lebih mudah dikenali tipe bangunannya. Metode yang digunakan dalam melakukan penelitian ini menggunakan teknik seleksi dan eliminasi, berasal dari penelitian di berbagai jurnal yang relevan terhadap pengklasifikasian gaya arsitektur bangunan. Hasil survey literatur menunjukkan bahwa terdapat kesenjangan, hasil akurasi dari yang tertinggi ke terendah sebesar 48,19 % sehingga diperlukan adanya inovasi pada perangkat sistemnya. Teknik DL paling banyak digunakan dengan pendekatan Convolutional Neural Network (CNN) yang dikombinasikan dengan sistem perangkat lain, daripada fiturnya sendiri guna meningkatkan nilai akurasi.

Keywords

Gaya Arsitektur; Fasad; Deep Learning

References

Arandjelovic, R., Gronat, P., Torii, A., Pajdla, T., & Sivic, J. (2018). NetVLAD: CNN Architecture for Weakly Supervised Place Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40(6), 1437–1451. https://doi.org/10.1109/TPAMI.2017.2711011[viewed on 01/02/2021]

Fathalla, R., & Vogiatzis, G. (2017). A deep learning pipeline for semantic facade segmentation. British Machine Vision Conference 2017, BMVC 2017, 1–13. https://doi.org/10.5244/c.31.120 [viewed on 17/04/2020]

Gupta, U., & Chaudhury, S. (2016). Deep transfer learning with ontology for image classification. 2015 5th National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics, NCVPRIPG 2015, 1–4. https://doi.org/10.1109/NCVPRIPG.2015.7490037 [viewed on 17/04/2020]

Huang, S. (2019). Building segmentation in oblique aerial imagery. 58[viewed on 17/04/2020].

Kolenbrander, T., Ruiter, F. De, & Yue, T. (2017). Facade labelling using neural networks. Delft University of Technology. [viewed on 01/02/2021]

Laupheimer, D., Tutzauer, P., Haala, N., & Spicker, M. (2018). NEURAL NETWORKS for the CLASSIFICATION of BUILDING USE from STREET-VIEW IMAGERY. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences. https://doi.org/10.5194/isprs-annals-IV-2-177-2018 [viewed on 17/04/2020]

Laupheimer, Dominik, & Haala, N. (2018). Deep Learning for the Classification of Building Facades. 38. Wissenschaftlich-Technische Jahrestagung Der DGPF Und PFGK18 Tagung in München, 19, 701–709. [viewed on 17/04/2020]

Liu, H., Zhang, J., Zhu, J., & Hoi, S. C. H. (2017). Deepfacade: A deep learning approach to facade parsing. IJCAI International Joint Conference on Artificial Intelligence, 2301–2307. https://doi.org/10.24963/ijcai.2017/320 [viewed on 17/04/2020]

Lotte, R. G., Haala, N., Karpina, M., de Aragão, L. E. O. e. C., & Shimabukuro, Y. E. (2018). 3D façade labeling over complex scenarios: A case study using convolutional neural network and structure-from-motion. Remote Sensing, 10(9). https://doi.org/10.3390/rs10091435 [viewed on 17/04/2020]

Meltser, R. D., Banerji, S., & Sinha, A. (2018). What’s that Style? A CNN-based Approach for Classification and Retrieval of Building Images. 2017 9th International Conference on Advances in Pattern Recognition, ICAPR 2017, 9–14. https://doi.org/10.1109/ICAPR.2017.8593206 [viewed on 17/04/2020]

Obeso, A. M., Benois-Pineau, J., Acosta, A. Á. R., & Vázquez, M. S. G. (2016). Architectural style classification of Mexican historical buildings using deep convolutional neural networks and sparse features. Journal of Electronic Imaging, 26(1), 011016. https://doi.org/10.1117/1.jei.26.1.011016 [viewed on 17/04/2020]

Para, W. (2019). Facade Segmentation in the Wild. King Abdullah University of Science and Technology Thuwal, Kingdom of Saudi Arabia. [viewed on 17/04/2020]

Pesto, C. (2016). Classifying U.S. Houses by Architectural Style Using Convolutional Neural Networks. 1–9. http://cs231n.stanford.edu/reports/2017/pdfs/126.pdf [viewed on 17/04/2020]

Petrovska, B., Zdravevski, E., Lameski, P., Corizzo, R., Štajduhar, I., & Lerga, J. (2020). Deep learning for feature extraction in remote sensing: A case-study of aerial scene classification. Sensors (Switzerland), 20(14), 1–22. https://doi.org/10.3390/s20143906 [viewed on 01/02/2021]

Pezzica, C., Schroeter, J., Prizeman, O. E., Jones, C. B., & Rosin, P. L. (2019). Between images and built form: Automating the recognition of standardised building components using deep learning. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 4(2/W6), 123–132. https://doi.org/10.5194/isprs-annals-IV-2-W6-123-2019 [viewed on 17/04/2020]

Ramadanta, A. (2010). KAJIAN TIPOLOGI DALAM PEMBENTUKAN KARAKTER VISUAL DAN STRUKTUR KAWASAN (Studi kasus: Kawasan Ijen, Malang). Jurnal SMARTEK, Vol. 8, No, 130–142. [viewed on 17/04/2020]

Sarkar, D., Bali, R., Sharma, T., Sarkar, D., Bali, R., & Sharma, T. (2018). Deep Learning for Computer Vision. In Practical Machine Learning with Python. https://doi.org/10.1007/978-1-4842-3207-1_12 [viewed on 17/04/2020]

Sastra, S. (2016). Kajian Estetika Bentuk Pada Fasade Perumahan Real Estate Di Yogyakarta. Inersia, 12(1), 78–84. https://doi.org/10.21831/inersia.v12i1.10355 [viewed on 17/04/2020]

Taoufiq, S., Nagy, B., & Benedek, C. (2020). Hierarchynet: Hierarchical CNN-based urban building classification. Remote Sensing, 12(22), 1–20. https://doi.org/10.3390/rs12223794 [viewed on 01/02/2021]

Tutzauer, P., & Haala, N. (2017). Processing of crawled urban imagery for building use classification. International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives, 42(1W1), 143–149. https://doi.org/10.5194/isprs-archives-XLII-1-W1-143-2017 [viewed on 17/04/2020]

Yoshimura, Y., Cai, B., Wang, Z., & Ratti, C. (2018). Deep learning architect: Classification for architectural design through the eye of artificial intelligence. Lecture Notes in Geoinformation and Cartography, 249–265. https://doi.org/10.1007/978-3-030-19424-6_14 [viewed on 17/04/2020]

Zhuo, X., Monks, M., Esch, T., & Reinartz, P. (2019). Facade segmentation from oblique UAV imagery. 2019 Joint Urban Remote Sensing Event, JURSE 2019. https://doi.org/10.1109/JURSE.2019.8809024 [viewed on 17/04/2020]