一种基于 Hough 变换的车道线检测新方法  

A New Method for Lane Line Detection based on Hough Transformation

作　　者：许宏科[1] 秦严严[1] 

机构地区：[1]长安大学电子与控制工程学院,西安710064

出　　处：《徐州工程学院学报（自然科学版）》2013年第4期1-4,共4页Journal of Xuzhou Institute of Technology(Natural Sciences Edition)

基　　金：国家山区公路工程技术研究中心开放基金(gsgzj-2011-08)

摘　　要：针对复杂环境中车道线检测易受图像中其它直线段的影响而出现较多误检测的问题,提出一种新的车道线检测方法.对原始RGB图像灰度化,将Otsu阈值提取方法引入Canny边缘检测算法中,得到边缘图像;判断边缘点在原RGB图像中的R、G、B三分量颜色信息,剔除非类似车道线颜色的边缘点,降低其它非车道线的直线段影响;使用Hough变换进行车道线检测.实验结果表明,该方法可以有效地滤除其它直线段的影响,在复杂环境中获得良好的车道线检测效果.The lane line detection in complex environment is easily affected by the image of the other straight lines,thus giving rise to errors. In this paper, a new method for lane line detection is put forward. Firstly,after the graying of the original RGB image, the Otsu threshold extraction method is introduced into Canny edge detection algorithm to obtain the edge image; secondly, the R G B component color information of the edge points in the RGB image will be analyzed, and the edge points without the colors similar to the lane lines will be removed so as to reduce the disturbance of the other non-lane-line straight lines;finally, the lane line detection based on Hough transformation is carried out. The experiment results show that this method can effectively remove the interference caused by other lines and has the excellent lane line detection results under complex environment.

关 键 词：车道线检测 RGB图像 HOUGH变换 Otsu阈值 边缘 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]