Radar HRRP Group-Target Recognition Based on Combined Methods in the Backgroud of Sea Clutter

In recent years, radar target recognition based on High-resolution range profile (HRRP) has received intensive attention. However, relevant researches mainly focus on HRRP single target recognition. In this paper, we study the problem of radar HRRP group-target recognition, especially when overlap and occlusion occur among the multiple targets in the group. The group-target recognition is designed as a two-stage process. The first is to classify the specific group-target or single target based on principal component analysis (PCA) dimension reduction method, back propagation (BP) neural network and support vector machine (SVM), the second is to recognize the specific targets contained in the group based on maximum correlation coefficient (MCC) method with sliding window. In the numerical simulation with both the Gaussian white noise and sea clutter background, we present maximum correlation coefficient result and the statistical recognition rate of specific targets in the group with respect to rotation angle.