摘要
为解决介质圆柱体逆散射问题,提出一种新的在线逆散射方法,通过支持向量机将逆散射问题转化成一个回归估计问题.该方法可应用于各种逆散射方面,尤其是目标的几何与电磁参数重构和埋地目标探测.文中首次将支持向量机方法应用到该领域,设置多个散射场的观测点,通过提取散射场的不同信息作为样本信息训练支持向量机,建立了介质圆柱体的逆散射模型,利用该模型重构了介质圆柱体的电磁参数,同时探测了埋地位置.数值结果显示了该方法的有效性和准确性,为目标的实时逆散射研究提供了一种有效方法.
In order to deal with the inverse scattering of dielectric circular cylinder, a new online methodology is applied to the solution of microwave inverse scattering problems. The inverse scattering problem is recast into a regression estimation one by means of a support vector machine(SVM). The approach can be applied to various inverse scattering problems, and it is very suitable to deal with the geometric and dielectric characterization reconstruction and the buried object detection. For the first time this paper applies the support vector machine to the field. The scattered electric field is measured at some points. The SVM is trained using different sample data extracted from the scattered field. The inverse scattering model of dielectric circular cylinder has been setup. The relative dielectric permittivity and the electric conductivity of dielectric circular cylinder are reconslructed and the center position of buried object are detected. The results show that this method is effective and efficient and provides a highly efficient solution for the real-time inverse scattering of objects.
出处
《地球物理学报》
SCIE
EI
CAS
CSCD
北大核心
2006年第5期1546-1551,共6页
Chinese Journal of Geophysics
基金
国家高技术研究发展计划(863计划)(2001AA132050)资助
关键词
支持向量机
介质圆柱体
逆散射
埋地目标
Support vector machine(SVM), Dielectric circular cylinder, Inverse scattering, Buried object