Crop Classification Based on the Combination of Polarimetric and Temporal Features of Sentinel-1 SAR Data

Polarimetric synthetic aperture radar (PolSAR) can obtain rich information of ground objects through different polarization combinations, and is widely used in terrain classification. The time-varying feature of multi-temporal polarimetric SAR data is a useful supplement, which contains information that is not available in single polarimetric data. This paper aims to introduce time-varying analysis into Sentinel-1 data, so as to effectively combine the information of both time and polarization dimensions. In this way, the accuracy of crop classification using dual-polarimetric data is improved. This paper used Sentinel-1 data, firstly we constructed the dual-polarimetric coherence (DC) based on C
2
matrices, and analyzed the DC to find optimal time by using feature importance ranking in Random Forest model. Then, the polarimetric features and DC of the selected time are combined. Finally, the spatial correlation of MRF was utilized to classify. Compared to using only polarimetric features alone, the overall accuracy is improved.