Abstract:

There are many statistical models for Synthetic Aperture Radar (SAR) images. Among them, the multiplicative model is based on the assumption that the observed random field Z is the result of the product of two independent and unobserved random fields: X and Y. The random field X models the backscatter, and thus depends only on the type of area each pixel belongs to. On the other hand, the random field Y takes into account that SAR images are the result of a coherent imaging system that produces the well known phenomenon called speckle, and that they are generated by performing an average of n statistically independent images -looks- in order to reduce the speckle effect. There are various ways of modelling the random fields X and Y. Recently Frery et.al, proposed the distributions Γ-1/2 (α, γ) and Γ1/2 (n, n) for of X and Y respectively. This resulted in a new distribution for Z: the gA0 (α, γ, n) distribution. Here, the parameters α and γ depend on the ground truth of each pixel and the parameter n is the number of looks used to generate the image. The advantage of this distribution over the ones used in the past is that it models very well extremely heterogeneous areas like cities, as well as moderately heterogeneous areas like forests, and homogeneous areas like pastures. As the ground truth can be characterized by the parameters α and γ, their estimation for each pixel generates parameter maps that can be used as the input for classical classification methods. In this work, different parameter estimation procedures are used and compared on synthetic and real SAR images, and then, supervised and unsupervised classifications are performed and evaluated.