Scientists from the Academy of the State Fire Service of the Ministry of Emergency Situations have developed a passive acoustic drone detection system capable of recognizing an aircraft by sound at a range of 5–7 kilometers. As Professor Alexey Avdeenko of the academy told TASS at the International Security Forum, the complex combines two neural networks.
The first neural network processes video streams from two cameras and reconstructs the drone's trajectory in 3D space within 100 milliseconds with a classification reliability of 85%. The second analyzes the UAV's acoustic signature and activates at a distance of up to 7 kilometers, even when the aircraft is not visible on radars. The developers emphasize the system's low cost and scalability.
The solution fills a critical niche for passive detection of stealthy drones at extremely low altitudes. The acoustic detector does not reveal itself through emissions, is not dependent on the radio horizon, and can operate under radio jamming conditions. This transforms it into an element of object-based air defense, which can be deployed without capital construction of radar towers.
