Target Detection and Classification of Small Drones by Deep Learning on Radar Micro-Doppler

Small drones, also called mini-UAVs (Unmanned Aerial Vehicles), have become very wide-spread. In security applications it is often desirable to detect and classify them. In this paper we employ radar micro-Doppler for detection and classification of small drones. Micro-Doppler are Doppler shifts generated by the movements of parts of the target. We have used radar measurements of small drones and birds, generated TVDs (Time Velocity Diagrams), and used a deep learning classifier to distinguish between drones and birds (target detection) and types of drones (target classification) with very good results. Our deep learning classifier is an improvement in classification performance compared to our earlier boosting and SVM (Support Vector Machine) classifiers on the same data.