一种基于雷达和机器视觉信息融合的车辆识别方法

Vehicle Detection Based on Information Fusion of Radar and Machine Vision

为提高先进驾驶员辅助系统对车辆前方环境识别的准确性,提出一种基于雷达和视觉传感器信息融合的车辆识别方法。系统工作前预先对毫米波雷达和摄像头进行联合标定,并确定雷达坐标系和摄像头坐标系的变换关系。车辆识别过程中,首先根据雷达信息确定图像坐标系中的车辆识别感兴趣区域;然后对感兴趣区域进行对称性分析获得车辆对称中心,并对车辆底部阴影特征进行分析处理完成车辆边缘检测;最后根据逆透视变换得到车辆识别宽度,根据识别宽度对识别结果进行验证。结果表明该算法具有较强的环境适应性和准确率,弥补了单一传感器在车辆识别中的不足。

For increasing the detection accuracy of advanced driver assisted system of the frontal surroundings of vehicle, a vehicle detection method based on the information fusion of radar and vision sensor is put forward. Before the system starts operation, a co-calibration of millimeter-wave radar and camera is conducted, and the transformation relationship between radar and camera coordinates is obtained. The process of vehicle detection stars with the determination of the region of interest （ROI） for vehicle detection in image coordinates based on radar information. Then a symmetry analysis is performed on ROI to get the symmetrical center of vehicle, and the features of vehicle bottom shadow are analyzed and processed with vehicle edge detection completed. Finally, through inverse perspective mapping the width of vehicle is obtained, based on which the results of detection are verified. It is demonstrated that the algorithm proposed has strong environment adaptability and good accuracy, remedying the defects of vehicle detection with single sensor.