高分辨率SAR图像目标属性散射中心特征提取方法  

Feature Extraction of Attributed Scattering Centers on High Resolution SAR Imagery

作　　者：杨进[1] 闫冬梅[2,3] 王超[2] 张红[2] 

机构地区：[1]装备指挥技术学院,北京101416 [2]中国科学院中国遥感卫星地面站,北京100086 [3]中国科学院自动化研究所,北京100080

出　　处：《中国图象图形学报》2009年第1期35-39,共5页Journal of Image and Graphics

基　　金：国家自然科学基金项目(40601058)

摘　　要：目标属性散射中心模型是基于物理光学和几何绕射理论解的散射中心模型,该模型中提供了可供目标识别的属性散射中心特征。为了能从高分辨率SAR图像中获得这些特征,讨论了目标属性散射中心模型,研究了从高分辨率SAR图像中提取目标属性散射中心特征参数的方法。该方法是一种基于图像域的参数估计方法,它通过图像分割、模型类别选择、参数初值选择和参数优化4个步骤,得到单个散射中心的7个参数。循环进行上面的步骤,就可以从SAR图像中提取出目标所有的散射中心特征。仿真结果验证了该算法的有效性。The attributed scattering center model is based on the solutions to both physical optics and the geometric theory of infraction. The model provides the characteristic feature of attributed scattering centers which can be well used in the target recognition. In order to get the feature on high resolution SAR Imagery, the attributed scattering center model is discussed and the method of extracting the feature of attributed scattering centers from a high resolution SAR image is researched in this paper. It is a parameter estimation method based on a SAR imagery. The method includes four steps： image segmentation, the selection of the model type, the estimate of initial value and the parameter optimization. The seven parameters of each scattering center can be obtained through above four steps. After the recurrence procession, the parameters of all the scattering centers in the imagery can be attained. At last, the validity and accuracy of this method can be demonstrated by the results of simulation.

关 键 词：SAR图像属性散射中心 特征提取算法 

分 类 号：TN957.52[电子电信—信号与信息处理]