The University of New South Wales, as the lead researcher, and the University of Sydney have teamed up to demonstrate the feasibility of using acoustic signatures to identify drones in hostile, access-denied environments by developing novel cognitive processing that enable the system to become aware of the operational context of its environment. The work is funded by a Defence Innovation Network (DIN) grant worth $134,711.
Recent research has indicated that it is possible to detect drones using the noise they emit. However, none has shown that is also possible to identify the drone from its acoustic signature.
The project successfully showed the feasibility of applying signal processing and machine learning techniques to find underlying patterns that can be used to identify drones from the noise they generate when they are used. Furthermore, the “Acoustic Prints” are unique to a drone type, and thus can be used to identify the presence of a drone and their type.
Furthermore, preliminary results indicate that the acoustic signals emanating from a device can be used to infer several other features. For example, its mode of operation, such as whether it is carrying load or hovering, and for maintenance purposes, by detecting whether it is under normal or abnormal operation.
Further information from the DIN here.