Share Email Print
cover

Proceedings Paper

A novel multi-band SAR data technique for fully automatic oil spill detection in the ocean
Author(s): Fabio Del Frate; Daniele Latini; Alireza Taravat; Cathleen E. Jones
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

With the launch of the Italian constellation of small satellites for the Mediterranean basin observation COSMO-SkyMed and the German TerraSAR-X missions, the delivery of very high-resolution SAR data to observe the Earth day or night has remarkably increased. In particular, also taking into account other ongoing missions such as Radarsat or those no longer working such as ALOS PALSAR, ERS-SAR and ENVISAT the amount of information, at different bands, available for users interested in oil spill analysis has become highly massive. Moreover, future SAR missions such as Sentinel-1 are scheduled for launch in the very next years while additional support can be provided by Uninhabited Aerial Vehicle (UAV) SAR systems. Considering the opportunity represented by all these missions, the challenge is to find suitable and adequate image processing multi-band procedures able to fully exploit the huge amount of data available. In this paper we present a new fast, robust and effective automated approach for oil-spill monitoring starting from data collected at different bands, polarizations and spatial resolutions. A combination of Weibull Multiplicative Model (WMM), Pulse Coupled Neural Network (PCNN) and Multi-Layer Perceptron (MLP) techniques is proposed for achieving the aforementioned goals. One of the most innovative ideas is to separate the dark spot detection process into two main steps, WMM enhancement and PCNN segmentation. The complete processing chain has been applied to a data set containing C-band (ERS-SAR, ENVISAT ASAR), X-band images (Cosmo-SkyMed and TerraSAR-X) and L-band images (UAVSAR) for an overall number of more than 200 images considered.

Paper Details

Date Published: 17 October 2013
PDF: 6 pages
Proc. SPIE 8891, SAR Image Analysis, Modeling, and Techniques XIII, 889105 (17 October 2013); doi: 10.1117/12.2031418
Show Author Affiliations
Fabio Del Frate, Univ. degli Studi di Roma Tor Vergata (Italy)
Daniele Latini, Univ. degli Studi di Roma Tor Vergata (Italy)
Alireza Taravat, Univ. degli Studi di Roma Tor Vergata (Italy)
Cathleen E. Jones, Jet Propulsion Lab. (United States)


Published in SPIE Proceedings Vol. 8891:
SAR Image Analysis, Modeling, and Techniques XIII
Claudia Notarnicola; Simonetta Paloscia; Nazzareno Pierdicca, Editor(s)

© SPIE. Terms of Use
Back to Top