A Multi-feature HRRP Target Recognition Method Based on ReliefF Algorithm

To solve the problem of high feature dimension and low recognition rate in the process of multi-feature recognition, this paper proposes to a multi-feature recognition method based on ReliefF algorithm. We first extract the following three features from the high resolution range profile (HRRP): time domain mean range profiles, distance radial, and PCA transform feature. We select the connected features by the Re-liefF algorithm. And ReliefF algorithm is combined with multi-classifier decision fusion recognition method. We use the simulation data and actual measurement data to test the proposed method. The experimental results shows that the proposed method can effectively improve the recognition accuracy.