A radar target recognition method based on auto-correlation wavelet SVM

Radar high-resolution range profile (HRRP) provides potentially discriminative information on the geometry of target, which has been shown to be promising signatures for radar Automatic Recognition (ATR) application. In this paper, a radar target recognition method based on auto-correlation wavelet support vector machine (AWSVM) is proposed. As the kernel of AWSVM, the auto-correlation of a compactly supported wavelet satisfies the translation invariant property, which is very important for radar ATR with HRRP. The theoretical analysis and simulation results have shown that the new algorithm is effective, the average recognition rate of five airplanes is 97.6%, and the high recognition rate is comparatively steady when the wavelet scale factor is changed in a certainty range.