The NRC’s break in the clouds with drone detection tool
Drones have gained a significant amount of popularity over the years. As drone hardware and software technology continues to evolve, privacy and safety continues to be a source of concern among the public. With the increasing use of recreational drones, there is a growing need for more effective detection and surveillance technologies to monitor airspace in urban areas, and to counter unauthorized drone flights. With this in mind, a team of researchers at the NRC’s Aerospace Research Centre developed an innovative artificial intelligence (AI)-based technology that aims to tackle part of the issue.
The technology was developed in collaboration with CS GROUP Canada Inc., a Canadian SME, and a team from the University of Ottawa (School of Electrical Engineering and Computer Science). CS GROUP Canada provided the radar and video data, and integrated the NRC/uOttawa AI classification algorithm in its “Raptor CsUAS C2” software (from CS GROUP Canada), more specifically its track fusion algorithm, providing the End-User with Airspace Surveillance capabilities. It is the first tool of its kind that can accurately and in near real time identify drones versus birds and other aircraft. This unique tool uses artificial intelligence to detect, monitor and classify remotely piloted aircraft systems, supporting counter-drone and intervention activities.
Since 2018, Dr. Iraj Mantegh, Senior Research Officer at the NRC, and his team have worked in close collaboration with the Correctional Service of Canada and Defence Research and Development Canada to address the gaps in current counter-drone technology. The NRC, along with its partners, executed multiple field trials to collect data and develop and test the technology in conditions as close as possible to the actual environment.
The NRC is now in the process of patenting the counter-drone technology for commercialization. It will enable both government and Canadian enterprises to improve drone surveillance and traffic management for a variety of safety and privacy matters, and also extend that to more complex problems, including the detection and classification of unidentified objects in a given airspace.