SAR图像目标峰值特征提取与方位角估计方法研究

目标峰值特征是SAR图像目标识别的重要特征之一。峰值特征提取是SAR图像目标识别的一个重要步骤，为了由SAR图像快速、精确地提取目标峰值特征．本文首先研究了SAR图像目标峰值特征提取方法，提出了一种“子像素”级精度的SAR图像目标峰值特征提取方法．并通过仿真实验分析了峰值位置、峰值幅度的估计精度。由于目标SAR图像或SAR图像特征矢量对目标方位角变化的敏感性，因此，为了提高SAR图像目标识别系统的分类效率，本文还研究了SAR图像目标方位角估计方法，提出了一种利用峰值特征基于线性回归的sAR目标方位角估计方法，和现有方法相比，该方法除了计算速度快，估计精度较高之外，还能在估计方位角的同时，给出该估计的置信区间，从而更好的满足SAR ATR的实际需要。文中通过对大量实测MSTAR SAR图像目标方位角的估计实验，验证了本文目标峰值特征提取及方位角估计方法的有效性。

Methods of target's peak extraction and azimuth estimation from SAR imagery

Target's peak feature is one of the important features for SAR image target recognition.Accordingly,peak extraction is an important process in SAR image target recognition.In order to extract target's peak from SAR image rapidly and accurately,the method of target's peak feature extraction is firstly studied in this paper,a method of target's peak extraction in sub-pixel accuracy is proposed,it's estimation accuracy of peak position and amplitude is analyzed by simulation.Because the high sensitivity of target's SAR image and SAR image's feature with target's orientation change,in order to improve the efficiency of SAR image target classification system,the method of azimuth estimation from SAR image is also studied in this paper.A method of target's azimuth estimation from SAR image using peak feature based on linear regression is proposed,besides goodish estimation accuracy and high computation efficiency,it can also provide the confidence interval of the estimation,which can meet the practical need of SAR ATR system better.Through a large number of experiments using real MSTAR SAR target imagery,the validity of methods of peak extraction and azimuth estimation is verified.