基于单目视觉的车道线和道路边界同步检测

Synchronous Detection of the Lane Marking and Road Boundary on Monocular Vision

针对智能车辆视觉导航中的车道保持问题,采用了单目视觉技术检测结构化道路上的车道线和道路边界.详细介绍了标线灰度特性与道路边缘信息的特征提取,并在此基础上结合公路几何线形进行道路模型匹配.算法整体采用初始检测和后继跟踪的循环处理流程,大大提高了实时性和抗噪性.通过CCD测试结果表明,方法能够快速、准确、同步地检测出车道线和道路边界.

To prevent an intelligent vehicle from departing the lane in the vision-based navigation, an integrated method based on monocular vision is proposed to detect the lane marking and road boundary in structural road environment. The method extracts the characters of the line and the roadway edge, and matches them to the model of lane shape. With the circular calling of detecting and tracking program block, the whole algorithm shows a real time and high antinoise capability. Experimental results proved that the method can detect lane marking and road boundary rapidly, exactly and synchronously.