Use of Generative Adversarial Network Algorithm in Super-Resolution Images to Increase the Quality of Digital Elevation Models Based on ALOS PALSAR Data
DOI:
https://doi.org/10.11137/1982-3908_2023_46_55296Keywords:
Deep learning, Neural networks, Digital image processingAbstract
Digital elevation models are responsible for providing altimetric information on a surface to be mapped. While global models of low and medium spatial resolution are available open source by several space agencies, the high- resolution ones, which are utilized in scales 1:25,000 and larger, are scarce and expensive. Here we address this limitation by the utilization of deep learning algorithms coupled with Single Image Super-Resolution techniques in digital elevation models to obtain better spatial quality versions from lower resolution inputs. The development of a GAN-based (Generative Adversarial Network-based) methodology enables the improvement of the initial spatial resolution of low-resolution images. In the geospatial data context, for example, these algorithms can be used with digital elevation models and satellite images. The methodological approach uses a dataset with digital elevation models SRTM (Shuttle Radar Topography Mission) (30 meters of spatial resolution) and ALOS PALSAR (12.5 meters of spatial resolution), created with the objective of allowing the study to be carried out, promoting the emergence of new research groups in the area as well as enabling the comparison between the results obtained. It has been found that by increasing the number of iterations the performance of the generated model was improved and the quality of the generated image increased. Furthermore, the visual analysis of the generated image against the high- and low-resolution ones showed a great similarity between the first two.
References
Azarang, A. & Kehtarnavaz, N. 2021, Image Fusion in Remote Sensing: Conventional and Deep Learning Approaches, Morgan & Claypool Publishers, Austin.
Capel, D. & Zisserman, A. 2003, 'Computer vision applied to super resolution', IEEE Signal Processing Magazine, vol. 20, no. 3, pp. 75-86, DOI:10.1109/MSP.2003.1203211.
Chen, Y., Zhao, Y., Jia, W., Cao, L. & Liu, X. 2020, 'Adversarial-learning-based image-to-image transformation: A survey', Neurocomputing, vol. 411, pp. 468-86, DOI:10.1016/j.neucom.2020.06.067.
Demiray, B.Z., Sit, M. & Demir, I. 2021, 'D-SRGAN: DEM Super-Resolution with Generative Adversarial Networks', SN Computer Science, vol. 2, pp. 1-11. DOI:10.1007/s42979-020-00442-2.
EMBRAPA Empresa Brasileira de Pesquisa Agropecuária 2021, ALOS – Advanced Land Observing Satellite, viewed 04 Julho 2021, http://www.Embrapa.Br/Satelites-De-Monitoramento/Missoes/Alos
Farr, T.G., Rosen, P.A., Caro, E., Crippen, R., Duren, R., Hensley, S., Kobrick, M., Paller, M., Rodriguez, E., Roth, L., Seal, D., Shaffer, S., Shimada, J., Umland, J., Werner, M., Oskin, M., Burbank, D. & Alsdorf, D. 2007, 'The Shuttle Radar Topography Mission', Reviews Of Geophysics, vol. 45, no. 2, pp. 1-33, DOI:10.1029/2005RG000183.
Galin, E., Guérin, E., Peytavie, A., Cordonnier, G., Cani, M.P., Benes, B. & Gain, J. 2019, 'A Review of Digital Terrain Modeling', Computer Graphics Forum, vol. 38, no. 2, pp. 553-77, DOI:10.1111/cgf.13657.
GITHUB 2022, GitHub, viewed 4 May 2022, <https://github.com//>.
Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A. & Bengio, Y., 2014, 'Generative Adversarial Nets', in Z. Ghahramani, M. Welling, C. Cortes, N. Lawrence & K.Q. Weinberger, Advances in Neural Information Processing Systems 27 (NIPS 2014), pp. 2672–80.
Glasner, D., Bagon, S. & Irani, M. 2009, 'Super-Resolution from a Single Image', 2009 IEEE 12th International Conference on Computer Vision, viewed 29 September 02, pp. 349-56, DOI:10.1109/ICCV.2009.5459271.
IMATEST 2022, imatest®, viewed 6 May 2022, <https://www.imatest.com/>.
Ledig, C., Theis, L., Huszár, F., Caballero, J., Cunningham, A., Acosta, A., Aitken, A., Tejani, A., Totz, J., Wang, Z. & Shi, W. 2017, 'Photo-Realistic Single Image Super-Resolution Using A Generative Adversarial Network', Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2017), Honolulu, pp. 4681-90, DOI:10.48550/arXiv.1609.04802.
Lei, S., Shi, Z. & Zou, Z. 2017, 'Super-Resolution for Remote Sensing Images Via Local–Global Combined Network', IEEE Geoscience and Remote Sensing Letters, vol. 14, no. 8, pp. 1243-7, DOI:10.1109/LGRS.2017.2704122.
Li, Z., Zhu, Q. & Gold, C. 2004, Digital Terrain Modeling: Principles and Methodology, CRC Press, Boca Raton.
Li, S., Hu, G., Cheng, X., Xiong, L., Tang, G. & Strobl, J., 2022, 'Integrating topographic knowledge into deep learning for the void-filling of digital elevation models', Remote Sensing of Environment, vol. 269, e112818. DOI:10.1016/j.rse.2021.112818.
Ma, C., Yang, C., Yang, X. & Yang, M. 2017, 'Learning a No-Reference Quality Metric for Single-Image Super-Resolution', Computer Vision and Image Understanding, vol. 158, pp. 1-16, DOI: 10.1016/J.Cviu.2016.12.009.
Perera, A.S. 2021, 'Looking back at the original vanilla GAN and its evolution over time', Towards AI, viewed 24 August 2021, <https://pub.towardsai.net/looking-back-at-the-original-vanilla-gan-and-its-evolution-over-time-3d441cedbd05>.
Rézio, A. C. C., Schwartz, W. R. & Pedrini, H. 2011, 'Super-Resolução De Imagens Baseada Em Aprendizado Utilizando Descritores De Características', Anais do X Congresso Brasileiro De Inteligência Computacional (CBIC’2011), Fortaleza, viewed 24 August 2021, <https://www.researchgate.net/profile/William-Schwartz-3/publication/303772981_Super-Resolucao_De_Imagens_Baseada_Em_Aprendizado_Utilizando_Descritores_De_Caracteristicas/links/5834752b08ae004f74c8791e/Super-Resolucao-De-Imagens-Baseada-Em-Aprendizado-Utilizando-Descritores-De-Caracteristicas.pdf >.
Romano, Y., Isidoro, J. & Milanfar, P. 2017, 'RAISR: Rapid and Accurate Image Super Resolution', IEEE Transactions on Computational Imaging, vol. 3, no. 1, pp. 110-25, DOI:10.1109/TCI.2016.2629284.
SCIKIT-IMAGE 2022, scikit-image: Image processing in Python, viewed 20 July 2022, <https://scikit-image.org/>.
Shao, Z., Wang, L., Wang, Z. & Deng, J. 2019, 'Remote Sensing Image Super-Resolution Using Sparse Representation and Coupled Sparse Autoencoder', IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 12, no. 8, pp. 2663-74, DOI:10.1109/JSTARS.2019.2925456.
Telles Junior, M.A.B.G. 2008, 'Super-Resolução de Imagens de Sensoriamento Remoto', Tese de Doutorado, Universidade de Brasília.
Yang, D., Li, Z., Xia, Y. & Chen, Z. 2015, 'Remote Sensing Image Super-Resolution: Challenges and Approaches', 2015 IEEE International Conference on Digital Signal Processing (DSP), IEEE Singapore, pp. 196-200, DOI:10.1109/ICDSP.2015.7251858.
Wang, X., Yu, K., Wu, S., Gu, J., Liu, Y., Dong, C., Qiao, Y. & Loy, C.C. 2018, 'ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks', Proceedings of the European conference on computer vision (ECCV) workshops, pp. 1-16, viewed 6 May 2022, <https://openaccess.thecvf.com/content_ECCVW_2018/papers/11133/Wang_
ESRGAN_Enhanced_Super-Resolution_Generative_Adversarial_Networks_
ECCVW_2018_paper.pdf>.
Wilson, J. P. 2012, 'Digital Terrain Modeling', Geomorphology, vol. 137, no. 1, pp. 107-21, DOI:10.1016/j.geomorph.2011.03.012.
Wu, Z. & Ma, P. 2020, 'ESRGAN-based DEM super-resolution for enhanced slope deformation monitoring in Lantau island of Hong Kong', The International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences, vol. 43, pp. 351-6, DOI:10.5194/isprs-archives-XLIII-B3-2020-351-2020.
Downloads
Published
Issue
Section
License
This journal is licensed under a Creative Commons — Attribution 4.0 International — CC BY 4.0, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.
Except where otherwise noted, content on this site is licensed under a license 