Abstract: Accurately estimating the micro-motion parameters of micro-rotor UAV is of great significance for the identification of UAV. For the extraction of weak micro-motion features of micro-rotor UAV, the feature extraction method of RSP-CFD (Reassigned Spectrogram-Cadence Frequency Diagram, RSP-CFD) is proposed in this paper. First, the high-resolution time-frequency analysis method RSP is used to analyze the micro-motion characteristics of the rotor UAV, then on the basis of RSP, the micro-motion characteristics of the rotor UAV are extracted by CFD method, and finally the rotor speed and blade length can be estimated by the maximum value parameter estimation method. The results show that RSP-CFD method has high accuracy in extracting the micro-motion features of the rotor UAV, which makes up for the shortcomings of the traditional methods, and then provides theoretical foundation and technical support for the classification of the rotor UAV.