UAV signal recognition method based on re-classification and separation of image transmission signal and flight control signal

Abstract

The rapid development of the drone industry brings security risks to low-altitude airspace in important places. In order to effectively defense unmanned aerial vehicles (UAV), it is of great significance to develop a system which can identify drone models by radio signal. To identify similar UAVs, a UAV signal recognition method based on re-classification and separation of image transmission signal (ITS) and flight control signal (FCS) is proposed. The OFDM time domain parameters of ITS are extracted for model pre-classification. Then, after extracting the time-frequency features of ITS and FCS respectively, the UAV can be identified with high precision by SVM. The experimental results show that the average accuracy of the four DJI UAVs can reach more than 95% when the signal-to-noise ratio (SNR) is 0dB.