Use of the multiresolution capability of wavelets for ship detection in SAR imagery

Abstract

Carrying out an effective control of fishing activities is essential to guarantee a sustainable exploitation of sea resources. As the regulated areas are extended, satellite-based synthetic aperture radar (SAR) provides a powerful surveillance capability allowing the observation of broad expanses, independently from weather effects and from the day/night cycle. This paper proposes a novel approach for ship detection based on the analysis of oceanic SAR images by means of the wavelet transform. The analysis of the detection performance over both simulated and real RADARSAT SAR images confirms the robustness of the proposed method: ships, undetectable with other conventional techniques are noticeably sharpened, whereas background noise is drastically reduced