Parametric Inversion of 2-D Dielectric Rough Surface Based on SVM

摘要

The inverse scattering of the geometric parameters with the 2-D rough surface is studied in this paper. Relative parameters are estimated by means of a regression technique based on the use of support vector machines (SVM). The Radar Cross-Section (RCS) is used as feature value, after a proper training procedure, the proposed method is able to reconstruct the parameters of the rough surface. Numerical results are provided for the validation of the approach.