The Gradient Structure Tensor as an Efficient Descriptor of Spatial Texture in Polarimetric SAR Data

In this paper, the analysis of spatially nonstationary texture from polarimetric SAR data is studied. A previously introduced model named Anisotropic Gaussian Kernel (AGK) was shown to be a pertinent descriptor of local orientation and allowed a simple representation of the complex spatial structure in SAR images. Here, two methods for the estimation of the model parameters are proposed. The first one is an enhancement of the previously developed algorithm and the second one is a new approach based on the Gradient Structure Tensor (GST) operator. These two methods are employed to analyse texture in PolSAR intensity channels.