摘要
提出了一种适用于辅助驾驶的高鲁棒性车道线检测算法。算法采用了根据距离的影像金字塔,有效提高了检测效率和准确率,实现了Android平台的实时检测,使用水平方向暗-亮-暗特征、二次曲线车道模型和基于卡尔曼滤波的跟踪实时提取跟踪路面车道线,实现相机俯仰角的快速标定。实验证明,基于简单特征和车道线模型算法在Android系统的行车记录仪上可稳定地进行车道跟踪。
A robust lane detection algorithm is presented for ADAS applications. Utilizing a distance based image multiscale resam-pling method, horizontal dark-bright-dark feature, parabola lane model and Kalman filter based tracking, the algorithm extracts and tracks road lane in realtime. A fast pitch angle alignment method is put forward for realtime detection on Android mobile devices.Experiments show that the algorithm runs realtime on an Android car dashcam.
出处
《电子技术应用》
北大核心
2017年第4期7-12,共6页
Application of Electronic Technique