摘要
车道线的检测与识别是汽车辅助驾驶系统中的重要研究内容,而在傍晚等弱光环境下对车道线的准确识别更是该研究领域的难点,因此,为解决弱光环境下车道线不易检测的问题,论文提出一种基于双边滤波的Retinex图像增强算法,该算法首先改善弱光环境下获取的原始RGB图像,凸显原始图像中的车道线特征,再对增强后的图像进行灰度变换及Otsu算法分割处理,并使用Sobel算子检测车道线边缘,最后通过Hough变换提取图中车道线,实验结果表明:论文中的方法能有效识别弱光环境下获取的车道线图像,具有较好的鲁棒性。
Detection and recognition of lane line is an important research content in the vehicle driving system,and in weaklight environment,the lane line is difficult to detect. Therefore,in order to solve the problem of weak light environment,a bilateralfiltering algorithm is proposed based on bilateral filtering Retinex image enhancement algorithm. Firstly,the algorithm improves theoriginal RGB image in weak light environment,highlights lane line features in the original image,and then makes gray transforma-tion and Otsu algorithm segmentation processing,and uses Sobel operator to detect lane edge,and finally extracts the lane line inthe graph by Hough transform. Experimental results show that the method in the paper can effectively identify the lane line image ac-quired in low light environment and has good robustness.
作者
王杰
陈黎卿
黄莉莉
马晓晴
王敏敏
韦溟
WANG Jie;CHEN Liqing;HUANG Lili;MA Xiaoqing;WANG Minmin;WEI Ming(Anhui Agricultural University of Faculty of Engineering,Hefei 230036)
出处
《计算机与数字工程》
2019年第2期451-456,共6页
Computer & Digital Engineering
基金
安徽省教育厅科研项目(编号:KJ2015A305)资助
