基于双曲线模型的车道识别与偏离预警

针对车道识别与偏离预警算法在准确性、可靠性和计算效率方面存在的问题,提出一种基于双曲线模型的车道识别与偏离预警算法。首先,在图像预处理基础上通过特征点搜索筛选道路边缘点,采用双曲线构建道路模型,利用最小二乘原理拟合道路参数,再根据拟合车道线及邻近点信息构建车道置信度函数,将置信度大于设定阈值的车道线作为最终检测结果;然后,根据相邻帧车道线连续变化的特点,在前帧拟合道路线附近使用粒子滤波算法进行道路边缘点筛选、拟合以及置信度计算,实现对车道线的跟踪;最后,在图像坐标系中建立时空联合预警模型,对车道偏离行为进行预警。在PC平台上进行的算法实现与道路实验结果表明:所提方法在一般路况下,具有92%的车道识别和偏离识别正确率和40ms/帧的平均处理速度,满足车道偏离预警应用要求。

Lane recognition and departure warning based on hyperbolic model

To improve the accuracy, reliability and computing efficiency of lane recognition and departure warning algorithm, a new lane detection and departure warning framework based on the hyperbolic model was proposed. Firstly, lane edge points were obtained from preprocessed image by searching feature points, and a least square fitting method was used to identify hyperbolic model of lane. The confidence factor of identified lane model was evaluated by a confidence function according to the characteristics of lane model and points adjacent to lane, and the reliability was compared with a threshold value to extract lane line. Then, in view of the continuous changing characteristics of lane between consecutive frames, particle filter algorithm was used to search lane edge points near the lane model obtained in previous frame, and an updated lane was identified and evaluated by confidence factor. Finally, based on a hyperbolic lane model established in aforementioned procedure, a spatial and temporal warning model of lane departure was proposed in image coordination system. The proposed algorithm was implemented on the PC platform and experiments on lane were done. The experimental results show that the method possesses good performances in recognition accuracy (92%) and average processing speed (40ms/frame), which can meet the application requirements.