合成孔径雷达目标自动识别研究

Automatic Target Recognition with Synthetic Aperture Radar Image

讨论了基于物理光学和几何绕射理论的散射中心理论模型,对散射中心模型的各个参数在图像域进行了估计,详细分析了基于散射中心理论的SAR图像目标特征提取算法,采用了先估计目标方位后识别目标类型的目标识别方法以提高目标识别的效率,并利用Delaunay三角化技术提高了目标方位的估计精度。实测MSTAR SAR图像中目标的识别结果表明了该方法的准确性和有效性。

The theory of attributed scattering centers based on the Physics Optics （PO） and the Geometric Theory of Diffraction （GTD） is analyzed and discussed. The parameters of the model are been well estimated on regions of the Synthetic Aperture Radar （SAR） image. Using the theory of attributed scattering centers we study the feasibility of object-based Automatic Target Recognition （ATR）. The Delaunay triangulation of the strong peaks is adopted to improve the estimated angle precision of the target, and then this angle is used to determine the target classes. The ATR results of the MSTAR SAR are given to illustrate the accuracy and efficiency of the presented method.