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

Abstract

Small drones, also called mini-UAVs (Unmanned Aerial Vehicles), have become very wide-spread. They have many positive applications. However, they also have negative uses and it is often necessary 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 internal parts of the target. We have used radar measurements of small drones and birds, extracted physical features from TVDs (Time Velocity Diagrams), and used a boosting classifier to distinguish between drones and birds (target detection) and types of drones (target classification) with good results. We have also compared with a SVM (Support Vector Machine) classifier. Our conclusion is that Micro-Doppler radar has the potential for reliable small drone target detection and is also promising for classifying the type of drone. The boosting classifier has some advantages over SVM.