Unmanned Aerial Vehicle Detection and Identification Using Deep Learning

Unmanned aerial vehicle (UAV) detection and identification technology are two of the key technologies of UAV supervision. This paper proposes a UAV detection and identification process using RF signals which are transmitted from the UAV to the controller, and an innovative method to identify UAV types by comparing Power Spectrum Density (PSD) with PSD models. The PSD models are trained as a regression task with deep neural network architecture. It is also unsupervised learning which does not need any annotated data. The results show the advantages of this method in terms of efficiency, accuracy, and low-cost.