GF-3 Polarimetric Data Quality Assessment Based on Automatic Extraction of Distributed Targets

Abstract

With the needs of continuous data quality assessment for massive Gaofen-3 (GF-3) polarimetric data, an automatic and efficient quality evaluation method is urgently needed. In this article, an automated polarimetric SAR data quality assessment method is conducted using a classic convolution neural network (VGG-16). The method is first pretrained, performance-tested, and robustness-tested on Radarsat-2 fully polarimetric data, then trained by selected SAR scenes of GF-3 for being applied on GF-3 data. The network is supposed to fulfill the work of automatically and accurately selecting those distributed targets satisfying quality evaluation under various scenes. A PolSAR data assessment method based on these distributed targets proposed by the authors in previous work is then applied to give the evaluation results. Experiments on GF-3 data and the comparison to prior works and corner reflectors on polarimetric distortion assessment results verify the effectiveness and advantages of the proposed method. The polarization data quality of GF-3 at different beams is also obtained. The technique and strategy in this article are practical and contributing to the long-term quality assessment of PolSAR data.

Keywords

• Calibration
• convolutional neural network (CNN)
• Gaofen-3 (GF-3)
• polarimetric distortion
• PolSAR data quality assessment