Coastal line extraction from SAR multi-channel images

During last decades, algorithms able to retrieve the coastline exploiting radar data instead of optical one have been presented. In recent years, the tendency to achieve high resolution has also appeared. In this manuscript, a technique for coastal line retrieval from multichannel SAR images is presented. The method faces the detection problem via statistical estimation, in particular exploiting Bayesian estimation theory. The proposed technique is able to detect the sea boundary at full resolution and low error rate. Results on high resolution COSMO-SkyMed data sets acquired on the Bay of Naples are presented, showing the remarkable accuracy of the method.