A new classification method based on Cloude Pottier eigenvalue/eigenvector decomposition

In this paper, a new polarimetric scattering parameter, the averaged intensity (I), is introduced to present the backscatter intensity of fully polarimetric SAR data. According to the particular analysis on the properties of I, α angle and entropy H, the mapping rule of I-α-H feature space onto the intensity-hue-saturation (I-H-S) color space is proposed. We use the IHS transform instead of segmentation algorithm to finish the classification. The important advantages of this method are that the information contained in the I-α-H feature space is preserved without any loss in the resulting image, and the execution time is saved since IHS transform is faster than most complicated segmentations. The result shows that I has the additional information which is not contained in α and H, and the classification result is more readable than that of H/α/A.