Automated Detection, Identification and Tracking of Unmanned Aerial Systems

To address the Army’s need to automatically detect, identify, and track small unmanned aerial systems (UASs) from moving ground vehicles, using distributed aperture systems (DASs) of IR cameras mounted on the vehicles, Physical Optics Corporation (POC) proposes to mature, in Phase II, the new software for Automated Detection, Identification and Tracking of Unmanned Aerial Systems (ADITUAS) based on image registration, detection, and tracking algorithms powered by deep learning neural networks. During Phase I, POC demonstrated the feasibility of ADITUAS technology by developing and testing prototype software that successfully detected and tracked small UASs in recorded IR data provided by the Army. The Phase I effort successfully demonstrated the potential of ADITUAS methods for IR search and track (IRST) using multiple distributed aperture IR cameras for ground vehicles. During Phase II, POC will improve and enhance the detection and tracking algorithms. We will integrate the software components and implement the ADITUAS algorithms in real time on a commercial off-the shelf (COTS), graphical processing unit (GPU)-equipped computer system and integrate it on a vehicle with a DAS of uncooled IR sensors.