SEMANTIC SEGMENTATION OF LAND COVER IN THE UPPER DANUBE REGION ON SENTINEL-2 SATELLITE IMAGES
DOI:
https://doi.org/10.24867/29BE13MarinkovicKeywords:
semantic segmentation, machine learning, Sentinel-2, Random Forest, XG BoostAbstract
This paper describes the semantic segmen¬tation of land cover in the Upper Danube region using Sentinel-2 satellite images. The segmentation was per¬formed into 6 classes: tree canopies, water bodies, grass¬land, bare soil, agricultural land, and vegetation on water surfaces. The data utilized multispectral Sentinel-2 satel¬lite images covering the Upper Danube area. XG-Boost and Random Forest classifiers were employed for train¬ing. Drone images of the area served to establish ground truth. Vegetation indices were used as additional features during classification. Maximal accuracy was 93%.
References
[1] Svoboda, J., Štych, P., Laštovička, J., Paluba, D.; Kobliuk, N.: „Random Forest Classification of Land Use, Land-Use Change and Forestry (LULUCF) Using Sentinel-2 Data—A Case Study of Czechia“, Remote Sens. 14, 1189, 2022.
https://doi.org/10.3390/rs14051189
[2] Xue J., Su B.: „Significant Remote Sensing Vegetation Indices: A Review of Developments and Applications“, Journal of Sensors, vol. 2017, Article ID 1353691, 17 pages, 2017.
https://doi.org/10.1155/2017/1353691
[3] Breiman, L.: „Random Forests“, Machine Learning 45:5-32. 2021. http://dx.doi.org/10.1023/A:1010933404324
[4] Chen, T., Guestrin, C.: „XGBoost: A Scalable Tree Boosting System“, Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 785-794, 2016.
https://doi.org/10.1145/2939672.2939785ž
[5] Marhon, S.A., Cameron, C.J.F., Kremer, S.C.: „Recurrent Neural Networks. In: Bianchini, M., Maggini, M., Jain, L. (eds) Handbook on Neural Information Processing“, Intelligent Systems Reference Library, vol 49. Springer, Berlin, Heidelberg, 2013.
.https://doi.org/10.1007/978-3-642-36657-4_2
[6] Yamashita, R., Nishio, M., Do, R.K.G. et al.: „Convolutional neural networks: an overview and application in radiology“, Insights Imaging 9, 611–629 2018.
https://doi.org/10.3390/rs14051189
[2] Xue J., Su B.: „Significant Remote Sensing Vegetation Indices: A Review of Developments and Applications“, Journal of Sensors, vol. 2017, Article ID 1353691, 17 pages, 2017.
https://doi.org/10.1155/2017/1353691
[3] Breiman, L.: „Random Forests“, Machine Learning 45:5-32. 2021. http://dx.doi.org/10.1023/A:1010933404324
[4] Chen, T., Guestrin, C.: „XGBoost: A Scalable Tree Boosting System“, Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 785-794, 2016.
https://doi.org/10.1145/2939672.2939785ž
[5] Marhon, S.A., Cameron, C.J.F., Kremer, S.C.: „Recurrent Neural Networks. In: Bianchini, M., Maggini, M., Jain, L. (eds) Handbook on Neural Information Processing“, Intelligent Systems Reference Library, vol 49. Springer, Berlin, Heidelberg, 2013.
.https://doi.org/10.1007/978-3-642-36657-4_2
[6] Yamashita, R., Nishio, M., Do, R.K.G. et al.: „Convolutional neural networks: an overview and application in radiology“, Insights Imaging 9, 611–629 2018.
Downloads
Published
2024-11-02
Issue
Section
Electrotechnical and Computer Engineering
