Classification and Discrimination of Birds and Small Drones Using Radar Micro-Doppler Spectrogram Images

This paper investigates the use of micro-Doppler spectrogram signatures flying targets, such as drones and birds, to aid in their remote classification. Using a custom-designed 10-GHz continuous wave (CW) radar system, measurements from different scenarios on variety targets were recorded create datasets for image Time/velocity spectrograms generated analysis multiple birds used target identification movement classification using TensorFlow. support vector machines (SVMs), results showed an accuracy about 90% drone size classification, 96% vs. bird 85% individual distinction between five classes. Different characteristics detection explored, including landscape behavior target.