Abstract: In the face of the increasing popularity of micro-UAVs and malicious abuse, as well as its characteristics of low-altitude navigation, slow speed, small size, and difficult identification, a UAV identification method based on the short-time Fourier transform (STFT) and Pseudo-Wigner-Ville distribution (PWVD) joint analysis of micro-Doppler features is proposed. The electromagnetic simulation software FEKO was used to simulate the radar echoes of four different types of UAVs, and the joint method were simulated and verified. The 77GHz millimeter-wave radar was used to actually collect the echoes of different types of UAVs. The target echo signal was transformed by STFT-PWVD to obtain a sample set. AlexNet was used classify and identify the sample set. The experimental results based on the measured data show that the accuracy of UAV classification using this method is 98.2422%.