U-Net Image Segmentation

Abstract— Satellite image segmentation is a core process in remote sensing applications that enables land cover classification, urban planning, and environmental monitoring. In this work, we introduce a deep learning based segmentation model based on the U-Net architecture for pixel-wise classification of high-resolution satellite images. The model is trained on a satellite image dataset and its respective labeled mask to learn geographical features properly. To enhance segmentation performance even further, we employ data augmentation and hyperparameter tuning to enhance generalization. The model is assessed based on the Intersection over Union (IoU) metric with an IoU metric score of approximately 0.8, which shows high segmentation accuracy. The experimental outcomes prove that the U-Net architecture is exceptionally suitable for satellite image segmentation and provides a promising approach to real-world remote sensing applications. Future work will explore further generalization enhancement by adding attention mechanisms and multi-scale feature fusion. Keywords—( Remote Sensing, Satellite Imagery, U-Net, Image Segmentation, Deep Learning, Feature Extraction, Semantic Segmentation)