Mini-UAV Movement Classification Based on Sparse Decomposition of Micro-Doppler Signature

It is necessary for radar sensors used in security and privacy surveillance systems to determine the movements of mini-unmanned aerial vehicles (UAVs) to evaluate and analyze their flight intent or purpose. For a typical quadrotor, its movement depends on the different rotation rates and directions of the four rotors individually positioned at the end of the cross frame. To extract the micro-Doppler signature of the multiple rotors, we define the exponential complex sinusoidal basis (ECSB) according to the modulation properties of the micro-Doppler echo. This allows us to convert the parameter estimation of the multidimensional signal into a sparse decomposition process in the 1-D space of the signal. Based on this, the micro-Doppler signal is decomposed using the proposed exponential orthogonal matching pursuit (EOMP). The approach decomposes the signal’s exponent into a series of complex sinusoidal components, and the sparse solution can accurately indicate the rotation status of the UAV rotors. To assess the performance of the proposed method, two machine learning (ML) classification models, support vector machine (SVM) and decision tree (DT), are investigated. The proposed approach has been validated using simulation and experimental data. The results indicate that the SVM model outperforms the DT model in terms of classification performance, achieving an accuracy of 97.3%. These findings suggest that the approach could be a promising tool for surveilling UAVs.