Coastline extraction from ALOS-2 satellite SAR images

TL;DR

This paper presents a deep-learning-based method for extracting coastlines from ALOS-2 satellite SAR images, enabling precise shoreline detection even under challenging conditions, validated by a global competition.

Contribution

The paper introduces a comprehensive deep-learning pipeline tailored for SAR image coastline extraction, including novel preprocessing, inference, and postprocessing techniques.

Findings

Achieved high accuracy in coastline detection from SAR images.

Validated method was the runner-up in an international competition.

Demonstrated robustness in challenging imaging conditions.

Abstract

The continuous monitoring of a shore plays an essential role in designing strategies for shore protection against erosion. To avoid the effect of clouds and sunlight, satellite-based imagery with synthetic aperture radar is used to provide the required data. We show how such data can be processed using state-of-the-art methods, namely, by a deep-learning-based approach, to detect the coastline location. We split the process into data reading, data preprocessing, model training, inference, ensembling, and postprocessing, and describe the best techniques for each of the parts. Finally, we present our own solution that is able to precisely extract the coastline from an image even if it is not recognizable by a human. Our solution has been validated against the real GPS location of the coastline during Signate's competition, where it was runner-up among 109 teams across the whole world.