High-resolution Coastline Extraction in SAR Images via MISP-GGD Superpixel Segmentation

TL;DR

This paper introduces a novel superpixel segmentation method using MISP-GGD for high-precision coastline extraction from SAR images, enhancing maritime monitoring accuracy.

Contribution

The paper proposes a new unsupervised superpixel segmentation algorithm tailored for SAR imagery, improving coastline detection accuracy over existing methods.

Findings

Superpixels closely follow coastline edges in SAR images.

The method achieves high accuracy in land/water classification.

Results demonstrate robustness across various SAR image types.

Abstract

High accuracy coastline/shoreline extraction from SAR imagery is a crucial step in a number of maritime and coastal monitoring applications. We present a method based on image segmentation using the Generalised Gamma Mixture Model superpixel algorithm (MISP-GGD). MISP-GGD produces superpixels adhering with great accuracy to object edges in the image, such as the coastline. Unsupervised clustering of the generated superpixels according to textural and radiometric features allows for generation of a land/water mask from which a highly accurate coastline can be extracted. We present results of our proposed method on a number of SAR images of varying characteristics.