高分辨TerraSAR-X 图像舰船目标几何参数提取方法

准确提取SAR图像舰船目标几何参数是实现舰船分类的基础。由于SAR特有的成像机理， SAR图像旁瓣效应和方位模糊严重影响了舰船目标的几何参数估计，为此提出一种基于迭代线性回归的舰船几何参数提取方法。首先通过线性回归提取目标的主轴方位；然后利用循环迭代剔除远离主轴的虚假目标像素；最后用实测SAR数据进行了验证。实验结果表明，该算法对高分辨率的SAR舰船目标切片具有较好的参数估计效果。

Geometric parameters extraction method of ship target in high resolution TerraSAR-X image

It is the basis of realization ship classification to accurately extract geometric parameters of the ship target in synthetic aperture radar(SAR) images. Due to the unique SAR imaging mechanism, azimuth ambiguity and sidelobe effects seriously impact on geometric parameters estimation of the ship target. Therefore, a method is presented to extract geometric parameters of the ship based on iterative linear regression. Firstly, the orientation of the goal spindle is extracted by linear regression. Then false target pixels are removed away from the ship spindle by iteration. Finally, the proposed method is verified with the actual measured SAR image. Experimental results show that the proposed algorithm has a better results of parameter estimation for high resolution SAR image of the ship target slice.