This paper introduces the use of a Chebychev moments' based feature for micro-Doppler based Classification, Recognition and Fingerprinting of Drones. This specific feature has been selected for its low computational cost and orthogonality property. The capability of the proposed feature extraction framework is assessed at three different levels of major classification steps, namely classification, recognition and fingerprinting, demonstrating the effectiveness of the proposed approach to discriminate drones from birds, fixed wings from multi-rotors and drones carrying different payloads on real measured radar data.@en

In this paper a method capable of automatically classify radar signals of human hand-gestures exploiting the micro-Doppler signature is designed. In particular, the methodology focuses on the extraction of the Chebyshev moments from the cadence velocity diagram (CVD) of each recorded signal. The algorithm benefits from interesting properties of these moments such as the fact that they are defined on a discrete set and hence computed without approximations, as well as the symmetry property that allows to minimize the computational time. The experiments computed on the challenging real-recorded DopNet dataset show interesting results that confirm the effectiveness of the approach.@en