UTS, DroneShield develop drone tech to detect drone threats

The University of Technology Sydney (UTS) and defence tech company DroneShield have produced next-generation drone technology, to better identify threats from unmanned aerial systems (UAS), which carry a ‘payload’ of explosives or biological material, flown by terrorists into a crowded building or military base.

In a partnership funded by the NSW and Australian Governments, UTS and DroneShield have produced an optical system for detection, identification and tracking of fast-moving threats such as nefarious UAS, comprised of a camera and Convolutional Neural Network (CNN). The new technology was recently demonstrated at Sydney Science Park.

The NSW Minister for Jobs and Western Sydney, Stuart Ayres, said the state government is committed to helping small businesses grow through programs such as the NSW Government-funded Defence Innovation Network.

“This is a key part of how the government is supporting growth in jobs in NSW in areas such as defence tech. And seeing the technology here in Western Sydney, just outside of the future Aerotropolis, gives us a glimpse into the type of R&D and industry activity that will take place out here in the future,” Ayres said.

UTS Vice-Chancellor Attila Brungs said the project is an example of the types of partnerships UTS is committed to. Brungs added that having the NSW and Australian Governments invest in the partnership shows what can happen when universities, government and industry work together.

“UTS is committed to developing more industry co-working spaces, both on our home campus in the Sydney CBD, and here in Western Sydney at the Sydney Science Park with Celestino,” Professor Brungs said.

Project lead and Co-Director of UTS Intelligent Drone Lab (IDL) Dr Nabin Sharma said UTS has expertise and experience in collaborating with industry partners to develop and deliver innovative vision systems for UAVs.

“We are using CNNs and deep learning to provide a solution for DroneShield to identify drones which could be of potential threat. The algorithm enables the vision system to see what’s happening, to collate data and process it for ultra-fast image recognition and analysis. This delivers a speedy and efficient assessment of a threat and the decision-making in response to it. The system is able to detect different types of drones and check if there is a payload,” Dr Sharma said.

Oleg Vornik, CEO of DroneShield, said the project has been a great example of collaboration between an Australian defence SME and an educational institution, promoting development of cutting-edge defence technologies in Sydney.

“We are pleased to add this groundbreaking technology to our systems, enabling our customers a unique camera-based detection, ID and tracking of improvised threats such as UAS,” Vornik said.

Image credit: ©stock.adobe.com/au/sdecoret