AR-Based Vehicular Safety Information System for Forward Collision Warning

摘要

This paper proposes an AR (augmented reality) based vehicular safety information system that provides warning information allowing drivers to easily avoid obstacles without being visually distracted. The proposed system consists of four stages: fusion data based object tracking, collision threat assessment, AR-registration, and a warning display strategy. It is shown experimentally that the proposed system can predict the threat of a collision from a tracked forward obstacle even during the nighttime and under bad weather conditions. The system can provide safety information for avoiding collisions by projecting information directly into the driver's field of view. The proposed system is expected to help drivers by conveniently providing safety information and allowing them to safely avoid forward obstacles.