Ship detection using polarimetric RadarSat-2 data and multi-dimensional coherent Time-Frequency analysis

A polarimetric coherent Time-Frequency (TF) decomposition approach for ship detection is proposed in this paper. At first, the PolSAR data are decomposed in azimuth direction, range direction only or in both directions. Then a novel statistical descriptor called polarimetric TF coherence indicator, is applied to detect maritime targets in different environments. By using polarimetric RadarSat2 data over various scenes, experimental results demonstrate that, the proposed method can efficiently enhance contrast between targets and background clutters in terms of ship detection.