一种新的基于Canny算子的道路标线检测算法

A new road marking detection algorithm based on Canny operator

针对传统Canny算子对道路标线检测不全、阈值选取困难及检测结果中噪声和伪边缘较多的问题,提出了一种新的道路标线检测算法。根据提出的程序框图对图像进行形态学预处理,结合提出的两个标准,自动寻找到Canny算子提取道路标线的最佳阈值,并利用该阈值对图像进行边缘检测,使用提出的两种后续处理方式剔除伪边缘和路面干扰。实验结果表明,该算法能够克服传统Canny算子在道路标线检测中存在的上述问题,实现道路标线准确检测。

In order to solve the problems of traditional Canny operator incomplete detection of road markings,difficult threshold selection,and more noise and false edges in the detection results,a new road marking detection algorithm was proposed.The image is morphologically preprocessed according to the proposed block diagram,the optimal threshold of the Canny operator is automatically found with combination of the two proposed criteria,and the threshold is used to detect the edge of the image.The two subsequent processes are used to eliminate false edges and road interference.Experimental results show that the algorithm can overcome the problems of traditional Canny operators in road marking detection and achieve accurate road marking detection.