Asynchronous Information Fusion in Intelligent Driving Systems for Target Tracking Using Cameras and Radars

In this article, an asynchronous information fusion issue is investigated for a camera and a radar in an intelligent driving system. Local camera and radar estimators with missed detections are developed independently at synchronized state update time for target tracking. A Kuhn-Munkers algorithm is used to match local tracking results of camera and radar for fusion estimation of a same target. A fusion estimator is obtained by a matrix-weighted fusion algorithm with wide detection range and reliable fused estimates. Effectiveness of the proposed asynchronous fusion estimator is displayed by experimental results on road vehicle tracking.