Time-Frequency Analysis and Target Recognition of HRRP Based on CN-LSGAN, STFT, and CNN

Jianghua Nie,Feng Lv,Lizhen Huang,Yongsheng Xiao,Chenquan Gan

doi:10.1155/2021/6664530

Abstract

Aiming at the problem of radar target recognition of High-Resolution Range Profile (HRRP) under low signal-to-noise ratio conditions, a recognition method based on the Constrained Naive Least-Squares Generative Adversarial Network (CN-LSGAN), Short-time Fourier Transform (STFT), and Convolutional Neural Network (CNN) is proposed. Combining the Least-Squares Generative Adversarial Network (LSGAN) with the Wasserstein Generative Adversarial Network with Gradient Penalty (WGAN-GP), the CN-LSGAN is presented and applied to the HRRP denoise. The frequency domain and phase features of HRRP are gained by STFT in order to facilitate feature learning and also match the input data format of the CNN. These experimental results show that the CN-LSGAN has better data augmentation performance and can effectively avoid the model collapse compared to the generative adversarial network (GAN) and LSGAN. Also, the method has better recognition performance than the one-dimensional CNN method and the Long Short-Term Memory (LSTM) network method.

Highlights

High-Resolution Range Profile (HRRP) is the vector sum of all scatters electromagnetic echoes, which can reflect the geometric structure, scatters point distribution, and other characteristics of the target
Compared to the traditional recognition method, the HRRP target recognition method of deep learning can avoid the excessive use of manual rules to extract the target features and acquire high-order features. e recognition rate of the Deep Belief Network (DBN) reached 92.8% [12]; the Convolutional Neural Network (CNN) was applied to radar automatic target recognition (RATR) [13, 14], and the recognition rate was greatly improved; the Recurrent Neural
To solve the problem of radar target recognition of HRRP under low signal-to-noise ratio circumstances, we proposed a new kind of generative model, called the CN-Least-Squares Generative Adversarial Network (LSGAN). e CN-LSGAN can generate data similar to the real data with low signal-to-noise data as input, improving the signal-to-noise ratio of the data

Summary

Introduction

HRRP is the vector sum of all scatters electromagnetic echoes, which can reflect the geometric structure, scatters point distribution, and other characteristics of the target. With the large-scale rise of deep neural networks, deep learning provides new ideas for the research of radar automatic target recognition (RATR) of HRRP. E recognition rate of the Deep Belief Network (DBN) reached 92.8% [12]; the CNN was applied to RATR [13, 14], and the recognition rate was greatly improved; the Recurrent Neural. Network (RNN) [15] and LSTM [16] had both achieved good recognition rates. In these actual application scenarios, HRRP acquired contain noise, which affects the amplitude of HRRP. HRRP needs to be enhanced in order to improve the signal-to-noise ratio. HRRP is denoised only by an Auto Encoder (AE) [20]

Methods

Results

Conclusion