In this article, we improve the deep learning solution for coastline extraction from Synthetic Aperture Radar (SAR) images by proposing a two-stage model involving image classification followed by segmentation. We hypothesize that a single segmentation model usually used for coastline detection is insufficient to characterize different coastline types. We demonstrate that the need for a two-stage workflow prevails through different compression levels of these images. Our results from experiments using a combination of CNN and U-Net models on Sentinel-1 images show that the two-stage workflow, coastline classification-extraction from SAR images (CCESAR) outperforms a single U-Net segmentation model.
@article{arxiv.2501.12384,
title = {CCESAR: Coastline Classification-Extraction From SAR Images Using CNN-U-Net Combination},
author = {Vidhu Arora and Shreyan Gupta and Ananthakrishna Kudupu and Aditya Priyadarshi and Aswathi Mundayatt and Jaya Sreevalsan-Nair},
journal= {arXiv preprint arXiv:2501.12384},
year = {2025}
}