Abstract
Deep Learning, and most notable Deep Neural Networks, have largely driven Artificial Intelligence in the area of remote sensing, mainly image classification tasks. In this paper, we present an approach based on Convolutional Neural Networks to classify Earth Observation satellite images as environmental preserved or non-preserved areas. One interesting feature of our approach is the fact that we used sensors with different spatial resolutions to assess the performance of a traditional network. We relied on images from the Tocantins Cerrado obtained by the Wide-Scan Multispectral and Panchromatic Camera of the CBERS-4A satellite, with a spatial resolution of 8m to create the training dataset. For testing, we set up a set of images of the Sentinel satellite, with a spatial resolution of 10m from Goiás Cerrado. Results imply that Convolutional Neural Networks are feasible and are a good alternative for classifying remote sensing areas even when dealing with images from various sensors, and also with different spatial resolutions, where the model used in this study obtained an accuracy of 0.87. This study demonstrates the flexibility of Convolutional Neural Networks concerning the ability to generalize knowledge for classifying remote sensing images.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Anwer, R.M., Khan, F.S., de Weijer, J., Molinier, M., Laaksonen, J.: Binary patterns encoded convolutional neural networks for texture recognition and remote sensing scene classification. ISPRS J. Photogrammetry Remote Sens. 138, 74–85 (2018). https://doi.org/10.1016/j.isprsjprs.2018.01.023
Assis, L., et al.: Terrabrasilis: a spatial data analytics infrastructure for large-scale thematic mapping. ISPRS Int. J. Geo-Information 8, 513 (2019). https://doi.org/10.3390/ijgi8110513, http://terrabrasilis.dpi.inpe.br
Assis, T., Amaral, S.: Landscape and population in deforestation areas of the brazilian cerrado: The case of cerrado baiano. In: Proceedings of the XIX Brazilian Symposium on Remote Sensing (2019). https://bityli.com/3TdqJ
Brazil: An area of native vegetation suppressed in the cerrado biome in 2019 was 6,484 km\(^{2}\). National Institute for Space Research (2019). https://bityli.com/d1Jtd
Corrêa, R.: Cerrado: the wealth of tocantins. Portal Tocantins (2020). https://portal.to.gov.br/noticia/2020/9/11/cerrado-a-riqueza-do-tocantins/
Ghassemi, S., Magli, E.: Convolutional neural networks for on-board cloud screening. Remote Sens. 11 (2019). https://doi.org/10.3390/rs11121417
Gonçalves, R.J.: Mining and territorial fracture of the cerrado in goiás. Élisée - Revista De Geografia Da UEG 9 (2020). https://www.revista.ueg.br/index.php/elisee/article/view/10852
Granatyr, J.: Deep learning com python de a a z - o curso completo. Udemy (2019). https://www.udemy.com/share/101uu0AEETcFpXRX8B/
Guo, Y., Liu, Y., Oerlemans, A., Lao, S., Wu, S., Lew, M.S.: Deep learning for visual understanding: a review. Neurocomputing 187, 27–48 (2016)
Keras: Adam. Keras (2021). https://keras.io/api/optimizers/adam/
Keras: Dropout layer. Keras (2021). encurtador.com.br/drxLT
Keras: Layer activation functions. Keras (2021). https://keras.io/api/layers/activations/
Keras: Maxpooling2d layer. Keras (2021). encurtador.com.br/hszCH
Keras: Probabilistic losses. Keras (2021). encurtador.com.br/rCJ23
Khatami, R., et al.: A meta-analysis of remote sensing research on supervised pixel-based land-cover image classification processes: general guidelines for practitioners and future research. Remote Sens. Environ. 177, 89–100 (2016)
Körting, T.S., Namikawa, L., et al.: How to effectively obtain metadata from remote sensing big data? In: GEOBIA 2016: Solutions and Synergies (2016)
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. IEEE 86(11), 2278–2324 (1998)
Ma, L., Liu, Y., Zhang, X., Ye, Y., Yin, G., Johnson, B.A.: Deep learning in remote sensing applications: a meta-analysis and review. ISPRS J. Photogrammetry Remote Sens. 152, 166–177 (2019)
Ma, L., Li, M., Ma, X., Cheng, L., Du, P., Liu, Y.: A review of supervised object-based land-cover image classification. ISPRS J. Photogrammetry Remote Sens. 130, 277–293 (2017)
Mohammadi, M., et al.: A comprehensive survey and taxonomy of the svm-based intrusion detection systems. J. Netw. Comput. Appl. 178, 102983 (2021)
Ribeiro, J. F.; Walter, B.M.T.: Fitofisionomias do bioma cerrado. Cerrado: Ecologia e Flora, EMBRAPA, pp. 152–212 (2008)
Santiago Júnior, V.A., Silva, L.A.R., Andrade Neto, P.R.: Testing environmental models supported by machine learning. In: Proceedings of the III Brazilian Symposium on Systematic and Automated Software Testing, SAST 2018, pp. 3–12. Association for Computing Machinery, New York (2018). https://doi.org/10.1145/3266003.3266004
Shawky, O.A., Hagag, A., El-Dahshan, E.S.A., Ismail, M.A.: Remote sensing image scene classification using cnn-mlp with data augmentation. Elsevier 221, 165356 (2020). https://doi.org/10.1016/j.ijleo.2020.165356
Zhang, W., Tang, P., Zhao, L.: Remote sensing image scene classification using cnn-capsnet. Remote Sens. 11, 494 (2019). https://doi.org/10.3390/rs11050494
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Miranda, M.d.S., de Santiago, V.A., Körting, T.S., Leonardi, R., de Freitas, M.L. (2021). Deep Convolutional Neural Network for Classifying Satellite Images with Heterogeneous Spatial Resolutions. In: Gervasi, O., et al. Computational Science and Its Applications – ICCSA 2021. ICCSA 2021. Lecture Notes in Computer Science(), vol 12955. Springer, Cham. https://doi.org/10.1007/978-3-030-87007-2_37
Download citation
DOI: https://doi.org/10.1007/978-3-030-87007-2_37
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-87006-5
Online ISBN: 978-3-030-87007-2
eBook Packages: Computer ScienceComputer Science (R0)