In this paper, an associative mapping data fusion approach to operational oil spill detection is investigated focusing on the combination of Synthetic Aperture Radar (SAR) imagery derived data, and ancillary information such as metocean and contextual data. The ancillary data related to the investigated area are processed together with the features of the detected dark objects extracted from the SAR image using Artificial Neural Networks, ultimately leading to the estimation of a reliability index of the oil spill detection. The detection reliability measure can be thought of as the likelihood of the object being an oil spill given the SAR, context and metocean available information.
VESPE Michele;
POSADA SANCHEZ Monica;
FERRARO DI SILVI E CASTIGLIONE Guido;
BULGARELLI Barbara;
VAN WIMERSMA GREIDANUS Herman;
DJAVIDNIA Samuel;
2010-03-31
International Center for Remote Sensing of Environment (ICRSE)
JRC51304
https://publications.jrc.ec.europa.eu/repository/handle/JRC51304,
| 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 |
|---|