Buildings Classification from Satellite Images by Transfer Learning

Main Article Content

Piyanate Touncha-em
Ekarat Rattagan


Satellite imaging technology is essential for various applications such as real estate analysis, disaster monitoring, and more. However, as satellite data is big data, it is time-consuming and challenging for humans to analyze it, even a simple task such as detecting the types of buildings in a large area. In this paper, we develop a satellite imaging-analytics technique by applying the transfer learning algorithm to learn and classify different types of buildings in Thailand. The proposed model is learnt and tested on our created datasets, namely 4CateSAT, including the images of buildings including (1) airports, (2) stadiums (football fields), (3) schools, and (4) temples in Thailand. We also apply well-known algorithms to handle the imbalanced data, and the experimental results show that the accuracy of the best model is 96.88%.


Download data is not yet available.

Article Details

Research Article


O. Russakovsky et al., “ImageNet Large Scale Visual Recognition Challenge,” Int. J. Comput. Vis., vol. 115, no. 3, pp. 211–252, 2015.

TensorFlow 2.6.0. (2021). Google.

N. V. Chawla, K. W. Bowyer, L. O. Hall, and W. P. Kegelmeyer, “SMOTE: Synthetic minority over-sampling technique,” 2011. [Online]. Available: arXiv:1106.1813.

R. R. Selvaraju, M. Cogswell, A. Das, R. Vedantam, D. Parikh, and D. Batra, “Grad-CAM: Visual explanations from deep networks via gradient-based localization,” in Proc. IEEE Int. Conf. Comput. Vis., Venice, Italy, Oct. 2017, pp. 618–626, doi: 10.1109/ICCV.2017.74.

T. Siriborvornratanakul. (2021). CNN Wrap-up [PowerPoint slides]. Available:

M. Pritt and G. Chern, “Satellite image classification with deep learning,” in Proc. IEEE Appl. Imagery Pattern Recognit. Workshop (AIPR), Washington, DC, USA, Oct. 10–12, 2017, pp. 1–7.

P. Helber, B. Bischke, A. Dengel, and D. Borth, “EuroSAT: A novel dataset and deep learning benchmark for land use and land cover classification,” IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., vol. 12, no. 7, pp. 2217–2226, 2019.

D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization,” 2014. [Online]. Available: arXiv:1412.6980.

K. He, X. Zhang, S. Ren, and J. Sun, “Delving deep into rectifiers: Surpassing human-level performance on ImageNet classification,” in Proc. IEEE Int. Conf. Comput. Vis., 2015, pp. 1026–1034, doi: 10.1109/ICCV.2015.123.

Google Earth. (2015). Google. Accessed: Feb. 1, 2021. [Online]. Available:

K. Simonyan, and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” 2014. [Online]. Available: arXiv:1409.1556.

C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna, “Rethinking the inception architecture for computer vision,” 2015. [Online]. Available: arXiv:1512.00567.

K. He, X. Zhang, S. Ren, and J. Sun, “Identity mappings in deep residual networks,” 2016. [Online]. Available: arXiv:1603.05027.

G. Huang, Z. Liu, L. Van Der Maaten, and K. Q. Weinberger, “Densely connected convolutional networks,” in Proc. IEEE Conf. Comput. Vis. and Pattern Recognit (CVPR), Honolulu, HI, USA, Jul. 2017, pp. 2261–2269, doi: 10.1109/CVPR.2017.243.

F. Chollet, “Xception: Deep learning with depthwise separable convolutions,” 2016. [Online]. Available: arXiv: 1610.02357.