基于改进Hough变换与双点去除R-最小二乘法的车道线检测优化算法

Lane Line Detection Optimization Algorithm Based on Improved Hough Transform and R-Least Squares with Dual Removal

针对传统Hough变换和最小二乘法的不足分别提出改进算法,并应用到车道线检测中,对道路图像进行预处理得到车道线的边缘点,对拟合车道线的两种方法进行改进,提高车道线检测的准确率和实时性。在实际检测中,设计一种结合改进Hough变换和双点去除R-最小二乘(R-least squares with dual removal,R-LSDR)法的检测算法,并运用Kalman滤波器跟踪车道线,在实车采集的道路图像序列上进行初步测试。实验结果表明,优化的车道线检测算法提高了检测准确率和运行效率。

An improved algorithm aimingon improving traditional Hough transform and least square method was proposed for lane line detection.The road image was preprocessed to obtain the edge points of the lane line.Then two methods of lane line fitting weremodifited to improve the accuracy and real-time of lane line detection.In the actual detection,a detection algorithm combining improved Hough transform and R-least squares with dual removal(R-LSDR)method was designed and Kalman filter was used to track the lane line.The preliminary experiment was carried out on the road sequence images obtained by real vehicle.The experimental results show that the optimized lane line detection algorithm improves the detection accuracy and operation efficiency.