Ballistic midcourse target RCS recognition based on DTCWT-VAE
Aiming at the problem that the radar signal of ballistic target is easily affected by the environment and the target recognition accuracy is low,a radar cross section(RCS)recognition method of ballistic target based on dual-tree complex wavelet transform(DTCWT)and variational autoencoder(VAE)is proposed.Firstly,the dynamic datas of ballistic target RCS are preprocessed by DTCWT.Then,the hidden variable features of target are extracted by VAE.Finally,the support vector machine(SVM)classifier is used to identify the data.Experimental results show that compared with the existing methods,the proposed method has higher recognition probability and better robustness.
NETL
NSTL
万方数据
