Landsat Uydu Görüntülerinde Derin Öğrenme Tabanlı Tek Görüntülü Süper-Çözünürlük Deneyleri

Yıl 2020, Cilt: 5 Sayı: 3, 194 - 204, 25.12.2020

Serdar Çiftçi Muhittin Karaman

https://doi.org/10.46578/humder.819176

Cited By: 2

Öz

Halka açık sunulan uydu görüntülerinin çözünürlükleri genellikle düşüktür. Düşük çözünürlük bilgi kaybına yol açtığından uzaktan algılama alanında çalışılan problemin türüne bağlı olarak istenilen başarım sergilenemeyebilmektedir. Böyle bir durumda düşük çözünürlüklü görüntülerin yüksek çözünürlüklü hale getirilmesi için süper-çözünürlük algoritmaları kullanılır. Bu çalışmada derin öğrenme tabanlı hazır eğitilmiş EDSR ve DBPN modelleri kullanılmış ve sonuçlarının pan-keskinleştirmeye ne kadar yakın olduğu incelenmiştir. Yapılan deneyler sonucunda EDSR ve DBPN modelleriyle elde edilen görüntülerin görüntü işleme tabanlı Bicubic yöntemine nazaran daha keskin geçişli ama objektif değerlendirmede daha zayıf olduğu gözlenmiştir.

Anahtar Kelimeler

Süper-çözünürlük, EDSR, DBPN, Bicubic, Landsat-8, Pan-sharpenning

Kaynakça

• [1] Gao, S., & Gruev, V. (2011). Bilinear and bicubic interpolation methods for division of focal plane polarimeters. Optics express, 19(27), 26161-26173.
• [2] Wang, Z., Chen, J., & Hoi, S. C. (2020). Deep learning for image super-resolution: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence.
• [3] Anwar, S., Khan, S., & Barnes, N. (2019). A deep journey into super-resolution: A survey. arXiv preprint arXiv:1904.07523.
• [4] USGS, https://earthexplorer.usgs.gov, [Online], 11.08.2020.
• [5] Avrupa Uzay Ajansı, www.esa.int, [Online], 28.10.2020.
• [6] Lim, B., Son, S., Kim, H., Nah, S., & Mu Lee, K. (2017). Enhanced deep residual networks for single image super-resolution. In Proceedings of the IEEE conference on computer vision and pattern recognition workshops (pp. 136-144).
• [7] Haris, M., Shakhnarovich, G., & Ukita, N. (2018). Deep back-projection networks for super-resolution. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 1664-1673).
• [8] Nasrollahi, K., & Moeslund, T. B. (2014). Super-resolution: a comprehensive Nasrollahi, K., & Moeslund, T. B. (2014). Super-resolution: a comprehensive survey. Machine vision and applications, 25(6), 1423-1468.survey. Machine vision and applications, 25(6), 1423-1468.
• [9] Suganya, P., Mohanapriya, N., & Vanitha, A. (2013). Survey on image resolution techniques for satellite images. International Journal of Computer Science and Information Technologies, 4(6), 835-838.
• [10] Demirel, H., & Anbarjafari, G. (2011). Discrete wavelet transform-based satellite image resolution enhancement. IEEE transactions on geoscience and remote sensing, 49(6), 1997-2004.
• [11] Wang, Z., Bovik, A. C., Sheikh, H. R., & Simoncelli, E. P. (2004). Image quality assessment: from error visibility to structural similarity. IEEE transactions on image processing, 13(4), 600-612.
• [12] EDSR-PyTorch, https://github.com/thstkdgus35/EDSR-PyTorch, [Online], 29.10.2020.
• [13] Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017). Densely connected convolutional networks. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 4700-4708).
• [14] DBPN-PyTorch, https://github.com/alterzero/DBPN-Pytorch, [Online], 30.10.2020.
• [15] Bicubic-interpolation, https://github.com/rootpine/Bicubic-interpolation, [Online], 29.10.2020.
• [16] Barsi, J.A., Lee, K., Kvaran, G., Markham, B.L., Pedelty, J.A., (2014). The Spectral Response of the Landsat-8 Operational Land Imager. Remote Sensing, 6, 10232-10251.
• [17] Landsat Handbook (2016). Landsat 8 (L8) Data Users Handbook. LSDS-1574 Version 2.0, USGS –EROS, Sioux Falls, South Dakota, USA, 29 March 2016.
• [18] Bernstein, L.S., 2012. Quick atmospheric correction code: algorithm description and recent upgrades. Opt. Eng. 51, 111719. https://doi.org/10.1117/1.oe.51.11.111719.
• [19] Laben C.A., Bernard V., Brower W. (2000) - Process for enhancing the spatial resolution of multispectral imagery using pan-sharpening. US Patent 6011875 A.
• [20] Sarp, G. (2014). Spectral and spatial quality analysis of pan-sharpening algorithms: A case study in Istanbul. European Journal of Remote Sensing, 47(1), 19-28.
• [21] Maruer, T. (2013). How To Pan-Sharpen Images Using The Gram-Schmidt Pan-Sharpen Method-A Recipe. International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, (s. 239-244). Hannover: ISPRS.
• [22] L3harrisgeospatial, https://www.l3harrisgeospatial.com/docs/GramSchmidtSpectralSharpening.html, [Online], 28.10.2020.
• [23] Hore, A., & Ziou, D. (2010). Image quality metrics: PSNR vs. SSIM. In 2010 20th international conference on pattern recognition (pp. 2366-2369). IEEE.
• [24] Wang, Z., & Bovik, A. C. (2002). A universal image quality index. IEEE signal processing letters, 9(3), 81-84.
• [25] Sheikh, H. R., & Bovik, A. C. (2006). Image information and visual quality. IEEE Transactions on image processing, 15(2), 430-444.