Operations in Degraded Visual Environments using Millimeter Wave Imagery

Corvid Technologies and the University of North Carolina at Charlotte propose to develop Clear Path Hazard Avoidance Radar (CPHAR). CPHAR is designed to enhance situational awareness in degraded visual environments (DVE) by utilizing millimeter wave (MMW) radar imaging and advanced computer vision techniques. CPHAR will address the limitations of existing systems, such as visual cameras, night vision cameras, and LiDar, which struggle to see through low light, fog, dust, rain, snow, fire, smoke and other visual obscurants. The team will design a practical, novel, and economic MMW sensor package composed of commercial off the shelf (COTS) or original equipment manufacturer (OEM) automotive-grade components. We will select state-of-the-art MMW components and design both a MMW sensor package and a data acquisition system incorporating the MMW sensor package to facilitate creation of a new training dataset to be used in tuning AI/ML models in Phase II. We will also create a computer vision model for object detection from MMW imaging data. Finally, we will generate new radar models for objects of interest for the creation of a very large corpus of radar data that closely resembles a variety of real-world scenarios, enabling more effective training, testing, and evaluation of the system.