Automatic vessel monitoring with single and multidimensional SAR images in the wavelet domain

Spaceborne Synthetic Aperture Radar (SAR) techniques constitute an extremely promising alternative compared to traditional surveillance methods thanks to the all-weather and day-and-night capabilities of Radar linked with the large coverage of SAR images. Nowadays, the capabilities of satellite based SAR systems are confirmed by a wide amount of applications and experiments all over the world. Nevertheless, specific data exploitation methods are still to be developed to provide an efficient automatic interpretation of SAR data. The aim of this paper is to present an approach based on multiscale time–frequency analysis for the automatic detection of spots in a noisy background which is a critical matter in a number of SAR applications. The technique has been applied to automatic ship detection in single and multidimensional SAR imagery and it has proven to be a rapid, robust and reliable tool, able to manage complicated heterogeneous scenes where classical approaches may fail.