Chirplet-Atoms Network Approach to High Resolution Range Profiles Automatic Target Recognition

Since radar back-scattering from a real target can be very complex, a Chirplet-atoms network approach to automatic target recognition using high resolution range profiles (HRRP) is proposed in this paper. Based on the multilayer feed-forward neural network structure, the Chirplet-atom transform is used to the input layer for feature extraction, and the hidden layer and output layer constitute a classifier. The network weights and the parameters of Chirplet-atom node are simultaneously adjusted to achieve joint feature extraction and target classification. The simulation results of four aircrafts have shown that the Chirplet-atoms network approach has better recognition rates and noisy immunity.