基于多传感器信息融合的车辆目标识别方法

摘要

In view of the inherent defects of traditional collison avoidance systems in respects of perception range, and recognition accuracy etc. due to adopting single sensor for target recognition, a target recognition method based on the information fusion of radar and machine vision is proposed. With the method, after target sequence is obtained, Mahalanobis distance is introduced to conduct observed values matching on the basis of taget level fusion method. Then joint probability data association ( JPDA) algorithm is applied to data fusion, and the observation model and state model of the system are set up to achieve target recognition based on information fusion. The results of verification test show that the method based on radar and camera data can fulfill accurate target recognition and positioning with wider adaptive engineering field.%鉴于传统车辆避撞系统中,因采用单一传感器进行目标识别,在感知范围、识别准确性等方面存在的固有缺陷,本文中提出了一种基于雷达与机器视觉信息融合的目标识别方法.该方法获取目标序列后,在目标级融合方法的基础上,引入马氏距离进行观测值匹配.再应用联合概率数据关联(JPDA)算法进行数据融合,建立系统观测模型与状态模型,从而实现了基于信息融合的目标识别.试验验证结果表明,该方法基于雷达与摄像头数据,可实现目标的准确识别与定位,其工程适应面更广.