An Efficient Multi-Sensor Fusion Protocol in a Vehicle-Road Collaborative System

Abstract

Nowadays, driving safety has become an important topic in the field of intelligent driving. The key step in the intelligent transportation system (ITS) is to detect and track the vehicles on the road through various sensors equipped on the vehicle. While putting the sensors aside the road can have benefits in the vehicle-road collaborative scenario. In this paper, we propose an efficient and applicable multisensor fusion protocol for a vehicle-road collaborative system where roadside units (RSUs) are equipped with cameras and radars. To fully use the history information and the multisource heterogeneous sensing data to improve the reliability of multi-sensor fusion, we further propose a Bayesian-based two-layer fusion scheme. Moreover, we evaluate the efficiency and robustness of our proposed scheme in a real highway environment in Changsha, China.