摘要
车道线检测是自动驾驶和辅助驾驶系统中至关重要的任务之一。车道线是指导车辆行驶的重要标志,能够帮助车辆保持稳定的行驶轨迹,减少因偏离车道而导致的交通事故。因此,研究车道线检测具有重要的实用价值。然而,现实场景中车道线存在遮挡、破损空间跨度较大以及光照条件多样等因素干扰,给车道线的检测带来了挑战。针对上述问题,本文在车道线检测中,利用全局阈值和局部参照阈值相结合的方法得到新的阈值,提高算法的响应速度和准确性,并对车道线边缘进行特征提取,采用Canny算子方法来更好地适应不同的道路环境。
Lane detection is one of the most important tasks in autonomous driving and assisted driving systems.Lane line is an important sign to guide vehicles,which can help vehicles to maintain a stable track and reduce traffic accidents caused by lane deviation.Therefore,the study of lane line detection has important practical value.However,in the real scene,there are many factors such as occlusion,large space span of damage and illumination,which bring challenges to the detection of lane lines.To solve the above problems,in this paper,a new threshold value is obtained by combining global threshold and local reference threshold in lane detection,so as to improve the response speed and accuracy of the algorithm,and Canny operator method is used to extract features from the edge of lane lines to better adapt to different road environments.
作者
严鹏程
徐燕
陆兆钠
陈陈
马柯嘉
YAN Pengcheng;XU Yan;LU Zhaona;CHEN Chen;MA Kejia(Nantong University of Technology,Nantong 226300,China)
出处
《电子测试》
2023年第3期54-58,共5页
Electronic Test
基金
南通理工学院2024届优秀毕业设计(论文)培育计划项目(BS202339)资助
关键词
车道线检测
边缘检测
阈值结合
lane detection
edge detection
threshold combination
