Publication

Abstract : Satellite image processing techniques have become increasingly important for monitoring and analyzing the Earth's surface and its features. Water bodies in particular are of great interest due to their ecological, hydrological, and societal importance. In this paper, it explores the possibility of identifying water bodies from satellite images and calculating their area using various image processing techniques. The use of visible light and microwave sensors as well as the application of image processing techniques such as threshold and segmentation for identifying water bodies. This also uses deep learning architectures such as the U-Net classifier for water body segmentation in satellite images. One approach for image segmentation is the U-Net architecture, which is composed of an encoder network responsible for extracting high-level features from the input image, and a decoder network that generates the segmentation map based on the encoded features. This paper examines how U-Net can be trained on a data set of labeled satellite images to identify water bodies and produce accurate segmentation maps. Finally, this highlights the importance of accurate water body segmentation for various applications such as hydrological modeling, water resource management, and environmental monitoring.