Classification of Radar Targets with Micro-Motion Based on RCS Sequences Encoding and Convolutional Neural Network

Radar cross section (RCS) sequences, an easy-to-obtain target feature with small data volume, play a significant role in radar classification. However, classification based on RCS sequences has the shortcomings of limited information and low recognition accuracy. In order to overcome RCS-based methods, this paper proposes spatial micro-motion method encoding convolutional neural network (CNN). First, we establish models targets, including precession, swing rolling. Second, introduce three approaches for as images. These types images are Gramian angular field (GAF), Markov transition (MTF) recurrence plot (RP). Third, multi-scale CNN is developed classify those maps. Finally, experimental results demonstrate that RP best at reflecting characteristics among methods. Moreover, proposed outperforms other existing networks highest