基于时频图深度学习的雷达动目标检测与分类

Radar detection and classification of moving target using deep convolutional neural networks on time-frequency graphs

雷达动目标检测技术一直是雷达信号处理领域中的关键技术,而传统的雷达动目标检测技术仅适用于匀速运动目标,检测性能有限。针对该问题提出一种基于卷积神经网络(CNN)时频图处理的雷达动目标检测方法,通过从雷达动目标回波中提取多普勒频移信息,然后利用短时傅里叶变换转换为时频图,输入卷积神经网络,进行深度特征学习,进而实现检测和分类的目的。仿真数据验证表明,所提方法能够有效检测和区分匀速、匀变速运动以及微动目标,稳健性高,与传统动目标检测方法相比具有显著优势。

Radar moving target detection technology is always a key technology in the field of radar signal processing.The traditional radar moving target detection technology is only suitable for uniformly moving targets,and the detection performance is limited.This paper proposes a radar Moving Target Detection(MTD)method based on Convolutional Neural Network(CNN)time-frequency processing.It extracts the Doppler shift information from the radar moving target echo,and then transforms it into time-frequency graph with short-time Fourier transform.After inputting the time-frequency graph into the CNN,the characteristic learning is performed to achieve the purpose of detection and classification.Simulation shows that this method is superior to traditional moving target detection methods.