Sensor Fusion of Camera and Cloud Digital Twin Information for Intelligent Vehicles

TL;DR

This paper presents a sensor fusion approach combining camera images and cloud-based Digital Twin data to enhance visual guidance and safety in intelligent vehicles, achieving high accuracy in object matching and improved driving safety.

Contribution

A novel sensor fusion methodology integrating camera images with cloud Digital Twin information for improved visual guidance in intelligent vehicles.

Findings

Achieved 79.2% accuracy in object matching at 0.7 IoU threshold.

Depth images as additional features improve matching accuracy.

Simulation results show enhanced driving safety with the proposed system.

Abstract

With the rapid development of intelligent vehicles and Advanced Driving Assistance Systems (ADAS), a mixed level of human driver engagements is involved in the transportation system. Visual guidance for drivers is essential under this situation to prevent potential risks. To advance the development of visual guidance systems, we introduce a novel sensor fusion methodology, integrating camera image and Digital Twin knowledge from the cloud. Target vehicle bounding box is drawn and matched by combining results of object detector running on ego vehicle and position information from the cloud. The best matching result, with a 79.2% accuracy under 0.7 Intersection over Union (IoU) threshold, is obtained with depth image served as an additional feature source. Game engine-based simulation results also reveal that the visual guidance system could improve driving safety significantly cooperate with the cloud Digital Twin system.