In this paper, a novel technique for automatic vessel size estimation in high-resolution SAR images is presented. Based on mathematical morphology, it aims at better delineating the vessel outline and thereby enabling the extraction of its actual dimensions. The technique has been tested on a set of five Sentinel-1 images at 20m resolution that have good quality ground truth available. It is found that the proposed algorithm produces very good length estimates (14% relative error) and reasonable width estimates (35%).
STASOLLA Mattia;
VAN WIMERSMA GREIDANUS Herman;
2016-09-21
TAYLOR & FRANCIS LTD
JRC101029
2150-704X,
http://www.tandfonline.com/doi/full/10.1080/2150704X.2016.1226522,
https://publications.jrc.ec.europa.eu/repository/handle/JRC101029,
10.1080/2150704X.2016.1226522,
| Name | Country | City | Type |
|---|
This document is only visible at the Commission level.
You are not authorized to publish or distribute it outside the European Commission.
This is a public document. You can share this publication.
Datasets
| ID | Title | Public URL |
|---|
Dataset collections
| ID | Acronym | Title | Public URL |
|---|
Scripts / source codes
| Description | Public URL |
|---|
Additional supporting files
| File name | Description | File type |
|---|