Video to Feature Data Association and Geolocation

This SBIR Phase I project proposes a probabilistic approach to determine a vehicles location using onboard video sensors and foundationalmap data. The system does not rely on only one type of information source, instead it combines proposals from a variety of locationestimators to find a vehicles location in GPS-denied environments.The system takes advantage of recent advancements in computer vision-based technologies and automated sensor exploitation and machinelearning to exploit onboard sensor data and identify cues to geo-locate itself. The Phase I effort will include: development of locationestimation framework, development of location estimator modules using reference maps and video features, development of a probabilisticfusion module, quantitative and qualitative evaluation of the technologies, and demonstration of proof of concept using real-world data frommultiple scenarios.