| Popis: |
This paper uses RADARSAT-2 quad Polarimetrie Synthetic Aperture Radar and TerraSAR-X dual polarimetrie SAR data to estimate agriculture crop growth stages. Ten RADARSAT-2 Fine Quad Wide beam modes data and 13 sets of Stripmap TerraSAR-X data with duel HH and VV polarizations were used in this study. Polarimetrie features such as differential reflectivity bands ratio, entropy, anisotropy, alpha angle, lambda, scattering diversity and polarization index were extracted and evaluated for wheat and canola crop types. The results from both RADARSAT-2 and TerraSAR-X data were compared; they demonstrated clear correlations between crop growth stages obtained from the ground truth data and polarimetric parameters. A stepwise regression feature selection technique was employed for determine the most suitable parameters for different crop types by utilizing both RADARSAT-2 and TerraSAR-X data. By integrating of the selected polarimetrie parameters from both Radarsat-2 and TerraSAR-X data, the more aeeurate estimate of the erop growth stages was aehieved and validated using erop growth stage ground truth data. The estimation of erop growth stages was performed on the elassified erop image subsets aequired at different dates. The results indieates that the mean square errors of the estimated erop growth stages are redueed using integrated/combined polarimetrie parameters from both RADARSAT-2 and TerraSAR-X data, as opposed to using a single sensor. |
