The Fraunhofer IDMT in Oldenburg has developed an intelligent acoustic sensor solution that detects and locates drones based on their characteristic sound patterns, even without visual contact.
When an unmanned aerial vehicle (UAV) approaches a sensitive area, every second counts. Security personnel must determine as quickly as possible whether a drone is approaching, its location, and how the situation is developing. Conventional detection methods provide important information, but they are not equally reliable in all environments: the line of sight can be obstructed, and radio signals can be affected by interference. Acoustic detection offers an additional detection channel. As a complementary component used in conjunction with radar, cameras, and lidar, it can strengthen existing security systems and provide clues where optical or radio-based methods reach their limits.
Identifying Drones from Their Acoustic Signatures:
Researchers at the Oldenburg branch of the Fraunhofer IDMT for Hearing, Speech and Audio Technology (HSA) are analyzing the acoustic signals emitted by drones. Each drone produces a characteristic sound pattern: an acoustic signature. Machine learning algorithms identify these patterns even in complex and noisy environments. Signals from multiple microphones can also be used to determine the direction from which the flying object is approaching. This allows researchers not only to detect drones but also to locate them and determine their spatial position.
“With our acoustic technology, we offer a cost-effective and low-maintenance complement to existing drone detection systems,” explains Christian Rollwage, head of the Audio Signal Enhancement group at the Fraunhofer IDMT in Oldenburg. “Especially in urban or wooded areas, acoustics can provide a decisive added value, as it allows drones to be detected even when they are not yet visible to other sensors.”.
Passive and efficient
While radar and camera systems can be costly and require considerable computing power, acoustic detection offers a distinct advantage due to its low energy consumption: it passively receives sound emissions and vibrations from the environment without actively transmitting signals, thus remaining undetectable. This technology can be deployed over large areas and operate autonomously. It is also suitable as a "trigger" component that activates additional sensors only when an acoustic indication of a drone's presence is detected. In the future, this technology could also be applied to other acoustic phenomena, such as vehicles or gunfire.
This development is based on many years of research at the Oldenburg headquarters. Since 2016, the Fraunhofer IDMT has made progress in the acoustic detection and localization of drones, not least through the joint projects AMBOS and ALADDIN. In other internal projects, algorithms, system components, and integration options have been continuously refined. Currently, both easily integrated software components and a fully integrated system solution are available.
