Integrated Sensor Unit for Signalized Intersections

The DOT seeks an integrated unit capable of identifying and tracking individual vehicles with high accuracy using multiple vehicle detection inputs, including video images, radar-based detection, and vehicle-to-everything radio signal inputs (DSRC, cellular-V2X), with a deep learning-based engine to fuse collected data. To address this DOT need, Physical Optics Corporation (POC) proposes to continue the development of a new Deep Learning-based Vehicle Tracking with Multiple Sensors (DETRAM) system based on a deep learning engine. DETRAM uses multiple deep neural networks to extract intelligence from a diverse set of sensors and fuses information from this variety of signal sources to identify and track individual vehicles under all environmental conditions with a precision currently unmatched by state-of-the-art systems that use a subset of these signal sources. During Phase I, POC demonstrated DETRAM’s feasibility with a proof-of-concept design that included a concept of operations, systems requirement, systems design, data management platform, and prototype demonstration that successfully extracted accurate trajectories by fusing data streams from a camera and a radar. In Phase II, POC will optimize the DETRAM prototype to perform field operational tests in coordination with a state or local highway agency and demonstrate it at Turner-Fairbank Highway Research Center or elsewhere.