Evaluation on a Drone Classification Method Using UWB Radar Image Recognition with Deep Learning

Abstract

This paper presents a method for recognizing various drones from images of ultra-wideband (UWB) radar range profile by using a convolutional neural network (CNN) model. CNN is a Deep learning algorithm that provides high accuracy for image recognition tasks. We investigated the recognition performance for five types of drones with different shapes, sizes, and the number of rotor blades (Matrice 600, 3DR Solo, Phantom 3, Mavic pro, and Bebop drone) and a radio-controlled flapping bird (Bionic bird). As a result, we have confirmed that our presented method can recognize each target with high accuracy of 90 % or more.