Abstract: In order to obtain the better edge images of traffic lane and the better traffic lane recognition，wavelet is used in the lane edge detection and edge connection.Then the Hough transform methods are used to get the traffic lane parameters，and finally the Kalman filter is used to achieve real-time traffic lane tracking.The experimental results show that this method has good reliability，robustness and real-time which ensures smart driving and solves the security.

Key words: lane detection, edge detection, Hough transform, Kalman filter

摘要： 为了得到较为理想的车道标识线边缘图像，便于更好地对车道标识线进行识别，采用小波方法实现对车道线的边缘检测，并进行边缘连接。利用Hough变换得到车道标识线参数，并采用Kalman滤波方法实现对车道标识线的实时跟踪。实验结果表明，该方法具有很好的可靠性、鲁棒性和实时性，为解决汽车智能驾驶提供了保障。

关键词: 车道线检测, 边缘检测, Hough变换, Kalman滤波