Phelps2020 will customize a real-time solution (APPS) that performs accurate EO/IR persistent and automatic detection of threats (people and cars) in the perimeter of secure facilities, from distances beyond $150m. Phelps2020s solution performs automatic and concurrent mitigation of several environmental degradations, including low light, fog, haze, blur, high dynamic range, backlighting, and low resolution, which was shown to highly improve the accuracy of threat detection and reduce false alarms. Object detection (OD), the second component of APPS, has been traditionally used with EO sensors for lack of data in the IR. Our Crystal preprocessor extends the use of EO-based OD to most low light situations (dusk, dawn, and many nighttime situations). We will augment our existing OD EO solution with IR OD by leveraging existing and new IR datasets for persistent EO/IR surveillance. Atmospheric distortion (AD) mitigation, EO Face and License plate recognition modules will be added and the system accelerated on an embedded platform.
