Algorithm for Drone Recognition from Birds Based on a Neural Network Approach Using Radar Data

Unmanned Aerial Vehicles (UAVs) are widely used in civil and military applications, increasing the need for reliable detection to protect critical infrastructure. Radar is an effective method for detecting UAVs at long distances and in all weather conditions. However, the similarity in size between UAVs and birds often leads to false positives, posing a problem in distinguishing between them. This study addresses this problem by proposing a classifier based on the micro-Doppler effect that discriminates between radar signals from UAVs and birds. The classifier uses a neural network approach, achieving an accuracy of more than 90%. The Engee mathematical computing and dynamic modeling environment was used for the computations. This work highlights the potential of advanced signal processing and machine learning to improve UAV detection systems, reduce false alarms, and improve the safety of critical facilities.