基于同步压缩短时傅里叶变换的微型无人机识别

针对利用雷达微多普勒效应的微型无人机识别问题，提出了一种基于同步压缩短时傅里叶变换（Synchrosqueezing Short-Time Fourier Transform,SSTFT）的分类识别方法。首先对无人机的微多普勒回波信号进行SSTFT从而获得信号时频谱，然后对时频谱进行多维度特征提取获得回波信号的时频特征及频率变化特征，最后将所获得联合特征输入到支持向量机（Support Vector Machine,SVM）中进而实现无人机的分类识别。基于实际雷达数据的实验结果表明，所提无人机分类方法准确率可达到97.03%。

Recognition of Micro-drones Based on Synchrosqueezing Short-Time Fourier Transform

To solve the problem of the micro-drones recognition based on radar micro-Doppler effect,a recognition method based on synchrosqueezing short-time Fourier transform(SSTFT) is proposed.First,time-frequency spectrograms of the signal are obtained through SSTFT on the micro-Doppler echo signal of drones.Then,the multi-dimension feature extraction of the time-frequency spectrogram is carried out to obtain the time-frequency feature and frequency change feature of the echo signal.Finally,the acquired features are input into the support vector machine(SVM) to implement the recognition of micro-drones.The experimental results based on the actual radar data demonstrate that the accuracy of the proposed micro-drones recognition method can reach 97.03%.