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.