主元子空间自适应双边预测探地雷达杂波抑制  

Clutter reduction for landmine detection using adaptive two-sided linear prediction in PCA subspace

作　　者：高翔[1] 姬光荣[1] 王群[2] 应娉[3] 

机构地区：[1]中国海洋大学信息科学与工程学院电子系,山东青岛266100 [2]中国人民解放军总装工程兵研究一所,江苏无锡214035 [3]中国电波传播研究所,山东青岛266107

出　　处：《电波科学学报》2010年第2期253-258,共6页Chinese Journal of Radio Science

摘　　要：基于线性预测模型,利用某扫描道前后的双边扫描道作为参考信号进行模型参数预测。在此基础上进一步考虑相邻扫描道之间的相关性,根据前一道的预测结果采用递推最小二乘估计后一道的预测系数,将双边道的参数预测与相邻道的自适应递推相结合达到杂波抑制的目的。又在主元分析子空间中进行自适应双边线性预测,综合利用线性预测模型得到的局部扫描道信息与主元分析得到的全局图像能量信息,提升了算法性能。通过仿真实验验证了所提方法的有效性。A new clutter reduction method for landmine detection was proposed based on Linear Prediction（LP） model,which utilized one centre scan and two-sided reference scans before and after to predict the model parameter.For further exploiting the correlation between adjacent scans,the new method employed recursive least square（RLS） to estimate the next scanning coefficient based on the previous scan prediction result.This scheme involved not only the two-sided prediction but also the adaptive recursion in the process of clutter reduction.Moreover,it performed better when the proposed adaptive two-sided linear prediction（ATSLP） was executed within the subspace of principal component analysis（PCA）,as it combined the local scan information from the LP and the overall image energy information from PCA.The experimental results verify the effectiveness of the proposed method.

关 键 词：线性预测 杂波抑制 主元分析 探地雷达 

分 类 号：TN95[电子电信—信号与信息处理]