基于路面图像对称性的车道偏离识别方法研究  

A Study on Lane Departure Detection Based on Edge Distribution Function

作　　者：刘志强[1] 陈彦博[1] 葛如海[1] 

机构地区：[1]江苏大学汽车与交通工程学院,镇江212013

出　　处：《汽车工程》2007年第7期626-629,共4页Automotive Engineering

基　　金：江苏省科技厅2005年高新项目(BG2005028)资助

摘　　要：利用车道边缘信息定义了边缘分布函数EDF,通过分析车道线在道路图像中的方向变化来判断车辆是否偏离了车道中央。将车道偏离识别问题通过EDF函数本身重要形态特征对称轴转换成一个数学问题,减少了动态道路场景噪声的影响,无需在测量车道方向时考虑摄像机自身的参数,提高了适应随机和动态道路环境的能力,是一种可靠的车道偏离识别方法。A lane departure detection technique based on edge distribution function （EDF） is in which edge information is used to define EDF, and it can be judged whether the vehicle deviates from of the lane through the analysis on the variation in orientation of lane mark line on road image. By taking presented, the centre the advantage of the important shape features of the EDF-symmetric axis, the effect of the noise related to dynamic road scene is reduced, and the measurement of lane orientation is made possible without considering camera-related parameters, thus enhancihg the adaptability to the random and dynamic environment of a road scene.

关 键 词：车道偏离 机器视觉 边缘分布函数 

分 类 号：U495[交通运输工程—交通运输规划与管理]