Algorithm of Target Classification Based on Target Decomposition and Support Vector Machine
Since Huynen’s original work, there have been many other proposed target decomposition theorems. In this paper, we provide a review of the different approaches used for target decomposition theory in radar polarimetry and classify three main types of theorems: those based on Mueller matrix, those using an eigenvector analysis of the coherency matrix, and those employing coherent decomposition of the scattering matrix. Support vector machine (SVM), as a novel approach in pattern recognition, has demonstrated a success in many fields. Here we first extract scattering mechanisms of radar targets by target decomposition and color composite. Then we propose a new algorithm of target classification by combining target decomposition and support vector machine. We conduct the experiment on the polarimetric synthetic aperture radar data. Experimental results show that: it is feasible and efficient to target classification by designing SVM classifiers using target decomposition, and the effects of kernel functions and its parameters on the classification efficiency are significant.
polarimetric synthetic aperture radar target decomposition support vector machine target classification
Wang Yang Lu Jiaguo Zhang Changyao
East China Research Institute of Electronic Engineering,Hefei,Anhui 230031,China
国际会议
首届亚太合成孔径雷达会议(1st Asian and Pacific Conference on Synthetic Aperture Radar Proceedings)
安徽黄山
英文
2007-11-05（万方平台首次上网日期，不代表论文的发表时间）