Target recognition algorithm based on HRRP time-spectrogram feature and multi-scale asymmetric convolutional neural network

基于HRRP时频特征和多尺度非对称卷积神经网络的目标识别算法

¹ School of Automation, Northwestern Polytechnical University, Xi'an 710129, China
² Unit 63768 of the PLA, Xi'an 710600, China
³ Key Laboratory of Information Fusion Technology of Ministry of Education, Xi'an 710114, China

Received: 26 July 2022

Abstract

A radar HRRP recognition algorithm based on time-spectrogram feature and multi-scale convolutional neural network is proposed to address the difficult feature extraction and low accuracy in space target recognition. Firstly, the normalization is used to eliminate the intensity sensitivity, the absolute alignment of multiple dominant scatterers is used to eliminate the translation sensitivity, and the radar Doppler velocity is used to eliminate the widening effect, distortion and wave crest splitting on HRRP caused by high-speed motion of the target. Then, the method applies the time-frequency analysis to the preprocessed HRRP to extract the time-frequency diagram. Finally, the time-frequency features are extracted with different scales of fineness and different directions through asymmetric convolution of different scales. The data processing results demonstrate that the present method has a high target recognition accuracy. In addition, the present improves the anti-posture sensitivity and target recognition on the same platform.

摘要

针对空间目标识别中特征提取难、准确率低等问题，提出了一种基于雷达高分辨率距离像（high range resolution profile，HRRP）时频特征和多尺度非对称卷积神经网络的目标识别算法。采用离差标准化、多特显点绝对对齐消除目标的强度敏感性和平移敏感性，利用雷达多普勒测速数据消除目标高速运动对HRRP产生的展宽、畸变、波峰分裂等影响。对HRRP进行时频分析，提取其时频特征。通过不同尺度的非对称卷积，实现时频特征不同精细程度和不同方向的特征提取。实测数据处理结果表明，文中方法目标识别准确率高，而且在同平台目标识别、抗姿态敏感性等方面具有很好的效果。