Effects of Spatial Filtering on PolSAR Parameter Estimation

Speckle filtering is essential for accurate parameter estimation from polarimetric synthetic aperture (PolSAR) data. To reduce speckle, sufficiently large independent samples (i. e. N looks) are generally averaged. However, in real scene, these N-looks are not provided. To surmount this limitation, by exploiting the ergodicity of the SAR data, the multilooking is substituted by the spatial averaging of N homogenous neighboring pixels. In this letter, it has been demonstrated that the multilooking and spatial averaging are quite different. First, the spatial averaging introduced a correlation between the pixels whereas in the multilooking they remain independent. Secondly, in real scene, the spatial averaging estimation of the polarimetric parameters (i.e. intensity mean and variance, equivalent number of looks (ENL), entropy and alpha angle) is nosier and more biased than the multilooked ones. These results should be taken into account when dealing with PolSAR parameter estimation of real data from multilooked PolSAR data models.