This is a Preprint and has not been peer reviewed. The published version of this Preprint is available: https://doi.org/10.1109/TGRS.2020.3011209. This is version 1 of this Preprint.
This is a Preprint and has not been peer reviewed. The published version of this Preprint is available: https://doi.org/10.1109/TGRS.2020.3011209. This is version 1 of this Preprint.
The extraction of river planforms from remotely sensed satellite images is a task of crucial importance to many applications such as land planning, water resource monitoring or flood prediction. In this paper we present a novel framework for the extraction of rivers from Synthetic Aperture Radar (SAR) images, based on superpixel segmentation and subsequent classification. Superpixel segmentation is achieved via a modelling of the image pixels’ amplitudes and spatial coordinates as a finite mixture model, where the Generalised Gamma distribution is used to accurately model a variety of high-resolution SAR scenes. A number of features describing texture and statistics are extracted on a superpixel level, facilitating the identification of river superpixels - planforms are then extracted via unsupervised,
agglomerative clustering thus eliminating the need for labelled training data. We present results of our proposed method on ICEYE-X2 and SENTINEL-1 SAR data demonstrating its ability to produce pixel-accurate river masks.
https://doi.org/10.31223/X53K53
Computer Engineering, Electrical and Computer Engineering, Engineering, Geology, Geomorphology, Hydrology
Synthetic Aperture Radar Data, Generalised Gamma Distribution, Superpixels, River Detection, Generalised Gamma Distribution, Superpixels, River Detection
Published: 2020-10-21 14:02
Last Updated: 2020-10-21 21:02
CC BY Attribution 4.0 International
Conflict of interest statement:
None
There are no comments or no comments have been made public for this article.