A Review on Deep Learning Models for Satellite Imagery

Yıl 2021, Cilt: 1 Sayı: 2, 73 - 79, 05.09.2021

Hasan Ersan Yağcı Abdullah Atçılı Sukru Sezer

Öz

Object detection and image classification from remote sensing data are used in many different fields. It has been the subject of many studies in recent years. Research in this field has increased with the development of deep learning techniques and remote sensing data, which can be satellite images or unmanned aerial vehicles (UAV), providing high resolution spatial and spectral data. In this review, we survey modern deep learning techniques are trained on remote sensing data. Term remote sensing data is widely used for satellite imagery, however the term also refers to UAV collected data. It is chosen as a topic of the this review that 'how green the metropolitans?'. There are two approaches for this question. First one is the detection of green (vegetation) in all metropolitan and the other one is classification of green types. Convolutional neural networks (CNN), generative adversarial networks (GAN), and autoencoder (AE) were compared on tensorflow's UC Merced dataset.

Anahtar Kelimeler

Deep Learning, Satellite Imagery, Remote Sensing

Kaynakça

• 1. Lei Ma, Yu Liu, Xueliang Zhang, Yuanxin Ye, Gaofei Yin, Brian Alan Johnson, Deep learning in remote sensing applications: A meta-analysis and review, ISPRS Journal of Photogrammetry and Remote Sensing, Volume 152, 2019, Pages 166-177.
• 2. Moreno-Armendáriz, M.A.; Calvo, H.; Duchanoy, C.A.; López-Juárez, A.P.; Vargas-Monroy, I.A.; Suarez-Castañon, M.S. Deep Green Diagnostics: Urban Green Space Analysis Using Deep Learning and Drone Images.Sensors 2019,19, 5287
• 3. Qin, R. An Object-Based Hierarchical Method for Change Detection Using Unmanned Aerial Vehicle Images.Remote Sens.2014,6, 7911-7932
• 4. Lu, H., Fu, X., Liu, C. et al.Cultivated land information extraction in UAV imagery based on deep convolutional neural network and transfer learning.J. Mt. Sci.14,731–741 (2017)
• 5. Tetsuro Ishida, Junichi Kurihara, Fra Angelico Viray, Shielo Baes Namuco, Enrico C. Paringit, Gay Jane Perez, Yukihiro Takahashi, Joel Joseph Marciano, A novel approach for vegetation classification using UAV-based hyperspectral imaging, Computers and Electronics in Agriculture, Volume 144, 2018, Pages 80-85.
• 6. Lei Ma, Yu Liu, Xueliang Zhang, Yuanxin Ye, Gaofei Yin, Brian Alan Johnson, Deep learning in remote sensing applications: A meta-analysis and review, ISPRS Journal of Photogrammetry and Remote Sensing, Volume 152, 2019, Pages 166-177, ISSN 0924-2716.
• 7. Satellite Applications for Geoscience Education
• 8. T. Blaschke,Object based image analysis for remote sensing,ISPRS Journal of Photogrammetry and Remote Sensing,Volume 65, Issue 1,2010,Pages 2-16,ISSN 0924-2716
• 9. Yi Yang and Shawn Newsam, "Bag-Of-Visual-Words and Spatial Extensions for Land-Use Classification," ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems (ACM GIS), 2010.
• 10. Elif Sertel & Ugur Alganci (2015): Comparison of pixel and object-based classification for burned area mapping using SPOT-6 images, Geomatics, Natural Hazards and Risk.
• 11 . Jing Wang, Weiqi Zhou, Yuguo Qian, Weifeng Li, Lijian Han, Quantifying and characterizing the dynamics of urban greenspace at the patch level: A new approach using object-based image analysis, Remote Sensing of Environment, Volume 204, 2018, Pages 94-108.
• 12. LeCun, Y., Bengio, Y., Hinton, G., 2015. Deep learning. Nature 521 (7553), 436–444.
• 13. G. Cheng, X. Xie, J. Han, L. Guo and G. -S. Xia, "Remote Sensing Image Scene Classification Meets Deep Learning: Challenges, Methods, Benchmarks, and Opportunities," in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 13, pp. 3735-3756, 2020
• 14. Xia, G.S.; Hu, J.; Hu, F.; Shi, B.; Bai, X.; Zhong, Y.; Zhang, L.; Lu, X. AID: A benchmark data set for performance evaluation of aerial scene classification. IEEE Trans. Geosci. Remote Sens. 2017, 55, 3965–3981.
• 15. Wei Zhang 1,2, Ping Tang 1 and Lijun Zhao 1, Remote Sensing Image Scene Classification CNN-CapsNet, Remote Sens. 2019, 11, 494; doi:10.3390/rs11050494
• 16. Goodfellow, I., Abadie, J., Mirza, M., Xu, B., Farley, D., Ozair, S., Courville, A., Bengio, Y., 2014. Generative adversarial nets, arXiv: 1406.2661v1.
• 17. K. Jiang, Z. Wang, P. Yi, G. Wang, T. Lu and J. Jiang, “Edge-Enhanced GAN for Remote Sensing Image Superresolution,” in IEEE Transactions on Geoscience and Remote Sensing, vol. 57, no. 8, pp. 5799–5812, Aug. 2019, doi: 10.1109/TGRS.2019.2902431.
• 18. D. Lin, K. Fu, Y. Wang, G. Xu, and X. Sun, “Marta gans: Unsupervised representation learning for remote sensing image classification,” IEEE Geoscience and Remote Sensing Letters, vol. 14, no. 11, pp. 2092– 2096, 2017
• 19. Y. Yu, X. Li, and F. Liu, “Attention gans: Unsupervised deep feature learning for aerial scene classification,” IEEE Transactions on Geoscience and Remote Sensing, vol. 58, no. 1, pp. 519–531, 2019
• 20. F. Zhang, B. Du, and L. Zhang, “Saliency-guided unsupervised feature learning for scene classification,” IEEE Transactions on Geoscience and Remote Sensing, vol. 53, no. 4, pp. 2175–2184, 2014.
• 21. B. Du, W. Xiong, J. Wu, L. Zhang, L. Zhang, and D. Tao, “Stacked convolutional denoising auto-encoders for feature representation,” IEEE transactions on cybernetics, vol. 47, no. 4, pp. 1017–1027, 2016