The Role of Target Signatures in Bird-Drone Classification

Mapping and characterising low to medium airspace in an urban setting using radar presents significant challenges, especially for low observable targets such as drones and birds. This paper presents some examples of micro-Doppler signatures which make up part of a larger dataset of control drone, control bird, and opportune bird signatures measured with a pair of L-band staring radars installed at an urban location at the University of Birmingham. The results of multiple measurements over a two-year period are used to facilitate the classification of birds and drones, and the results of a machine learning classifier on the collected data is shown.