The fully polarimetric synthetic aperture radar (PolSAR) with high resolution and quad-polarization data has shown the ability to provide better interpretation and high classification accuracy. But PolSAR image quality is critical disturbed due to speckle noise not only in the three intensities (HH, HV, VV) of PolSAR but also in the three complex correlation terms (HH-VV, VV-HV and HV-HH). Thus, reducing speckle noise level while preserving polarization scattering mechanisms and spatial resolution of PolSAR becomes a challenging task. Several filters widely used in SAR images can achieve effective speckle reduction, but can also lead to edge blurring and strong reflective scatter depressing. To mitigate these deficiencies, in the study, we proposed an improved speckle filtering approach by combining existing filters (such as Lee or Sigma filters) with edge/strong target detectors. Before performing filtering, strong targets and edges are detected and preserved by the proposed detectors. By the detection preprocessing, the improved filtering approach can not only reduce speckle noise but also preserve the target signature. The effectiveness of the proposed improved speckle filters is validated by two kinds of PolSAR data, one obtained by NASA Airborne Synthetic Aperture Radar System (AIRSAR) and the other data obtained by Advanced Land Observing Satellite(ALOS). From experimental results, the proposed improved filter provides promising results for suppressing speckle noise and preserving the potential targets.
|