Classification of small UAVs and birds by micro-Doppler signatures

The problem of unmanned aerial vehicles classification using continuous wave radar is considered in this paper. Classification features are extracted from micro-Doppler signature. Before the classification, the micro-Doppler signature is filtered and aligned to compensate the Doppler shift caused by the target's body motion. Eigenpairs extracted from the correlation matrix of the signature are used as informative features for classification. The proposed approach is verified on real radar measurements collected with 9.5 GHz radar. Planes, quadrocopter, helicopters and stationary rotors as well as birds are considered for classification. Moreover, a possibility of distinguishing different number of rotors is considered. The obtained results show the effectiveness of the proposed approach. It provides capability of correct classification with a probability of around 95%.