面向复杂城市交通场景的一种实时车道线检测方法

车道线检测是智能交通监控及自动驾驶的基础步骤,为提高其鲁棒性和实时性,针对复杂城市交通场景中自动驾驶需要检测车道线的需求,提出了一种实时车道线检测算法,首先运用改进灰度化变换突显车道线的特征,并通过改进的Gabor滤波算法增强车道线的边缘信息；最后采用多约束霍夫变换筛选得到平行车道线从而实现实时车道线检测。实验表明,该方法在三种不同真实的交通道路场景下,提高了车道线检测精度及处理速度,可应用于实时车道线检测系统。

A real-time lane detection method for complex urban traffic scenes

Lane detection is the basic step of intelligent traffic monitoring and automatic driving. A real-time lane detection algorithm is proposed to improve its robustness and real-time performance for the automatic driving application in complex urban traffic scenes. The improved grayscale transformation highlights the lane feature and enhances the edge information of the lane line by the improved Gabor filtering algorithm. Finally, the multi-constrained Hough transform is used to obtain the parallel lane line to realize the real-time lane detection. The experimental results show that this method improves the accuracy and processing speed of lane detection under three different real traffic road scenarios, and our method can be applied to the real-time lane detection system.