CLASSIFICATION OF SATELLITE IMAGES WITH DEEP CONVOLUTIONAL NEURAL NETWORKS AND ITS EFFECT ON ARCHITECTURE

Year 2022, - Vol.23 - 16th DDAS (MSTAS) Special Issue -2022, 31 - 41, 23.12.2022

Fadime Diker , İlker Erkan

https://doi.org/10.18038/estubtda.1165890

Abstract

Unlike traditional machine learning methods, deep learning methods that can learn from image, video, audio, and text data, especially recently with the increase in hardware power, are also increasing in success. Considering the success and benefits of deep learning methods in many different fields with increasing data, similar effects are expected in architecture. In this study, we focused on textures by going down to specifics rather than general images. In this direction, a total of 4500 satellite images belonging to cloud, desert, green areas and water bodies were classified in the model developed using deep convolutional neural networks. In the developed model, 0.97 accuracy for cloud images, 0.98 accuracy for desert images, 0.96 accuracy for green areas images and 0.98 accuracy for water bodies images were obtained in the classification of previously unused test data (675 images). Although there are similarities in the images of cloud and desert, and images of green areas and water bodies, this success in textures shows that it can be successful in detecting, analyzing, and classifying architectural materials. Successful recognition, analysis and classification of architectural materials and elements with deep convolutional neural networks will be able to facilitate the acquisition of appropriate and useful data through shape recognition among many data, especially at the information collection phase in the architectural design process. Thus, it will help to take more accurate decisions by obtaining more comprehensive data that cannot be obtained from manual data analysis. Learning the distinctive features for classification of data in deep convolutional neural networks also explains architectural design differences and similarities. This situation reveals the hidden relationship in the designs and thus can offer architects the opportunity to make creative and original designs.

Keywords

Deep learning, Deep convolutional neural network, Image classification, Detection of material textures, Architecture

References

• [1] Hinton GE, Salakhutdinov RR. Reducing the dimensionality of data with neural networks, Science 2006; 313(5786): 504-507.
• [2] Yoshimura Y, Cai B, Wang Z, Ratti C. Deep learning architect: classification for architectural design through the eye of artificial intelligence. In International Conference on Computers in Urban Planning and Urban Management, 2019; 249-265.
• [3] Llamas JM. Lerones P, Medina R, Zalama E, Gómez-GarcíaBermejo J. Classification of architectural heritage images using deep learning techniques, Applied Sciences, 2017; 7(10): 992.
• [4] Obeso AM, Vázquez MSG, Acosta AAR, Benois-Pineau, J. Connoisseur: classification of styles of Mexican architectural heritage with deep learning and visual attention prediction. In Proceedings of the 15th international workshop on content-based multimedia indexing, 2017; 1-7.
• [5] Yetiş G, Yetkin O, Moon K, Kılıç Ö. A novel approach for classification of structural elements in a 3d model by supervised learning. In Proceedings of the 36th eCAADe Conference, 2018; 129-136.
• [6] Diker F, Erkan İ. The fuzzy logic method in assessing window design for the visual comfort of classrooms at the early design stage, Journal of Architectural Engineering, 2022; 28(2), 04022013.
• [7] Bingöl K, Aslı ER, Örmecioğlu HT, Arzu ER. Depreme dayanıklı mimari tasarımda yapay zeka uygulamaları: Derin öğrenme ve görüntü işleme yöntemi ile düzensiz taşıyıcı sistem tespiti, Gazi Üniversitesi Mühendislik Mimarlık Fakültesi Dergisi, 2022; 35(4): 2197-2210.
• [8] Mitchell TM. Machine learning. McGraw-Hill,1997; 1(9): 414p.
• [9] Kavuncu SK. Makine öğrenmesi ve derin öğrenme: Nesne tanıma uygulaması. Kırıkkale Üniversitesi, Fen Bilimleri Enstitüsü, Master's Thesis, 2018; 157p.
• [10] Narın D, Onur TÖ. Investigation of the effect of edge detection algorithms in the detection of covid-19 patients with convolutional neural network-based features on chest x-ray images. In 2021 29th Signal Processing and Communications Applications Conference (SIU), 2021; 1-4.
• [11] Önal MK, Avci E, Özyurt F, Orhan A. Classification of minerals using machine learning methods. In 2020 28th Signal Processing and Communications Applications Conference (SIU), 2020; 1-4.
• [12] İnik Ö, Ülker E. Derin öğrenme ve görüntü analizinde kullanılan derin öğrenme modelleri, Gaziosmanpaşa Bilimsel Araştırma Dergisi, 2017; 6(3): 85-104.
• [13] Ergün GB, Güney S, Ergün TG. Köpeklerdeki uzun kemiklerin evrişimsel sinir ağları kullanılarak sınıflandırılması, Fırat Üniversitesi Mühendislik Bilimleri Dergisi, 2021; 33(1): 125-132.
• [14] Yamashita R, Nishio M, Do RKG, Togashi K. Convolutional neural networks: an overview and application in radiology, Insights into imaging, 2018; 9(4): 611-629.
• [15] Bozkurt F, Yağanoğlu M. Derin evrişimli sinir ağları kullanarak akciğer x-ray görüntülerinden covid-19 tespiti, Veri Bilimi, 2021; 4(2): 1-8.
• [16] Mining WID. Data mining: Concepts and techniques. Morgan Kaufinann, 2006; 10, 559-569.
• [17] Uğuz S. Makine öğrenmesi teorik yönleri ve python uygulamaları ile bir yapay zeka ekolü. Nobel Akademik Yayıncılık, 2019; 298p.