Noise-Robust HRRP Target Recognition Based on Residual Scattering Network

Extracting noise-robust features is a key issue for high-resolution range profile (HRRP) target recognition. In order to enhance the recognition performance under low signal-to-noise ratio (SNR), a novel recognition method based on scattering network is proposed in this paper. Specifically, the initial scattering network is enhanced by the incorporation of squared modulus and residual connection, making it more suitable for HRRP. And it is cascaded with ResNet to further extract information and complete the recognition. Experimental results on two different datasets demonstrate the effectiveness and robustness of the proposed method.