Fully automatic oil spill detection from COSMO-SkyMed imagery using a neural network approach
Ruggero G. Avezzano ; Fabio Del Frate ; Daniele Latini ; - ASI Sponsor
Nov - 2012
DOI: 10.1117/12.976830

Event Title : SAR Image Analysis, Modeling, and Techniques XII
Published in: SPIE Proceedings. Volume 8536. Maritime Applications III
Publisher: SPIE
type: Conference Proceedings

The increased amount of available Synthetic Aperture Radar (SAR) images acquired over the ocean represents an extraordinary potential for improving oil spill detection activities. On the other side this involves a growing workload on the operators at analysis centers. In addition, even if the operators go through extensive training to learn manual oil spill detection, they can provide different and subjective responses. Hence, the upgrade and improvements of algorithms for automatic detection that can help in screening the images and prioritizing the alarms are of great benefit. In the framework of an ASI Announcement of Opportunity for the exploitation of COSMO-SkyMed data, a research activity (ASI contract L/020/09/0) aiming at studying the possibility to use neural networks architectures to set up fully automatic processing chains using COSMO-SkyMed imagery has been carried out and results are presented in this paper. The automatic identification of an oil spill is seen as a three step process based on segmentation, feature extraction and classification. We observed that a PCNN (Pulse Coupled Neural Network) was capable of providing a satisfactory performance in the different dark spots extraction, close to what it would be produced by manual editing. For the classification task a Multi-Layer Perceptron (MLP) Neural Network was employed.

keywords : Neural networks ; Algorithms ; Feature extraction ; Multilayers