Automatic Entity Recognition Identifying Antennas Locally


AERIAL is a prototype computer vision system capable of running on computationally limited hardware, such as mobile phones and UAV/sensor network payloads.

The result of novel basic and applied research performed by Digital Operatives, AERIAL’s initial motivation and first application was in automatically detecting antennas solely based upon their visual signature. Autonomous networking technology (e.g., ad-hoc, peer-to-peer, and “off-the-grid” cellular networks) can bypass centralized security force monitoring by avoiding the use of an intermediate organization that manages the network infrastructure.

A recent study by the RAND Corporation concludes with a warning that, “Absent some preparation to deal with this challenge [of autonomous networking technology], [our adversaries’] communications will be largely undetectable to the security force.” Existing approaches for antenna detection rely solely on the identifying radio emissions via spectrum analysis. As such, antennas are only detectable while they are transmitting; non-transmitting antennas that are simply used for receiving communications will go undetected. In contrast, AERIAL is capable of detecting antennas in real time, even if there are no radio emissions.

AERIAL was developed by Digital Operatives LLC with funding from the Defense Advanced Research Projects Agency (DARPA). The views, opinions, and/or findings contained in these articles/presentations are those of Digital Operatives LLC and should not be interpreted as representing the official views or policies, either expressed or implied, of the Defense Advanced Research Projects Agency or the Department of Defense. Reference herein to any specific commercial product, process, or service by trade name, trademark or other trade name, manufacturer or otherwise, does not necessarily constitute or imply endorsement by DARPA, the Defense Department or the United States Government, and shall not be used for advertising or product endorsement purposes.