DETECTING OBJECTS ON SATELLITE IMAGES USING PYTORCH
DOI:
https://doi.org/10.34185/1991-7848.itmm.2024.01.098Keywords:
aerial imagery, image recognition, Python, computer vision, machine learning, deep learning, PyTorch.Abstract
This paper is devoted to the development of a neural network for classifying satellite images of the Earth into four classes: water, sands, clouds, and green areas (forests, fields, and plant clusters). For this purpose, the Python library PyTorch is used, which is focused on the application of deep learning for computer vision tasks. The proposed approach allows for automatic classification of satellite images, facilitating the analysis of large amounts of data, and has been tested on Sentinel-2 satellite images acquired from March to August 2023 for some parts of Kherson and Mykolaiv regions, Ukraine, and achieved an overall accuracy of 95%. The results of the study are useful for specialists in the fields of remote sensing, computer vision, machine learning, and aerospace image analysis software development.
References
Kaplan, G., Aavdan, U., 2018: Sentinel-1 and Sentinel-2 Data fusion for wetlands mapping: Balikdami, Turkey. Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., 42(3), 729-734, https://doi.org/10.5194/isprs-archives-XLII-3-729-2018
HnatushenkoVik., Hnatushenko Vo., Kashtan V., Heipke C., 2023: Detection of Forest Fire Consequences on Satellite Images using a Neural Network. In: Kersten T., Tilly N. (Eds.), 43. Wissenschaftlich-TechnischeJahrestagung der DGPF e.V. -
München, Publikations DGPF, Vol. 31 https://www.dgpf.de/src/tagung/jt2023/proceedings/paper/15_dgpf2023_Hnatushenko_et_al.pdf
Zhou, Yue, et al. "Mmrotate: A rotated object detection benchmark using pytorch." Proceedings of the 30th ACM International Conference on Multimedia. 2022.
Lin, Dan, et al. "Multilabel aerial image classification with a concept attention graph neural network." IEEE Transactions on Geoscience and Remote Sensing 60 (2021): 1-12.
Khalifa, NourEldeen, Mohamed Loey, and SeyedaliMirjalili. "A comprehensive survey of recent trends in deep learning for digital images augmentation." ArtificialIntelligenceReview 55.3 (2022): 2351-2377.
Liang, Yilong, Sildomar T. Monteiro, and Eli S. Saber. "Transfer learning for high resolution aerial image classification." 2016 IEEE Applied Imagery Pattern Recognition Workshop (AIPR). IEEE, 2016.
Cheriyadat, Anil M. "Unsupervised feature learning for aerial scene classification." IEEE Transactions on Geoscience and Remote Sensing 52.1 (2013): 439-451.
