基于深度学习的摩托车车道实时检测  

Real-time Detection of Motorcycle Lanes Based on Deep Learning

作　　者：万海波 蒋磊[1] 王晓 WAN Haibo;JIANG Lei;WANG Xiao(School of Mechanical Electronic&Information Engineering,China University of Mining and Technology,Beijing 100083,China)

机构地区：[1]中国矿业大学(北京)机电与信息工程学院,北京100083

出　　处：《计算机科学》2023年第S01期450-454,共5页Computer Science

基　　金：国家自然科学基金重点资助项目(61936008)。

摘　　要：摩托车驾驶相比于其他驾驶方式更加危险,但缺乏有效的辅助驾驶系统,例如车道辅助保持系统、障碍物检测、预碰撞系统等,而判定摩托车在行驶中是否发生了偏离往往需要参照车辆行驶时车道线的位置,因此车道线检测对于辅助驾驶系统来说至关重要,因此文中提出了基于深度学习的摩托车车道实时检测算法。在Lanenet架构的基础下做出了以下3点改进:将车道坐标的绝对位置作为输入特征、使用K-means算法代替Mean-Shift聚类算法以及去除Hnet结构。由于目前缺乏公开的摩托车车道数据集,因此将使用采集的摩托车车道数据对模型进行拟合,拟合的结果证明了该算法的有效性,检测速度可达47.6fps,交并比可达0.71560,相比文献[3]中的算法在精度上提高了15.5%,在速度上提高了53.3%。Motorcycle driving is more dangerous than other driving styles but lacks effective driving assistance systems,such as lane assist systems,obstacle detection,pre-collision system,etc.The position of the lane line when driving is often used for determining whether the motorcycle has deviated.Therefore,lane line detection is very important for developing assisted driving systems,so this paper proposes a real-time detection algorithm for motorcycle lanes based on deep learning.This paper proposes three improvements based on the Lanenet architecture:(1)using the absolute position of the lane coordinates as the input feature;(2)using the K-means algorithm instead of the Mean-Shift algorithm;(3)removing the H-net structure.Due to the lack of public motorcycle lane data sets,the collected motorcycle lane data will be used to fit the model in this paper.Experimental results prove the effectiveness of the proposed algorithm.The detection speed can reach 47.6 fps,and the cross-combination ratio can reach 0.71560.Compared with the algorithm in reference[3],the accuracy improves by 15.5%and the speed improves by 53.3%.

关 键 词：摩托车驾驶 车道检测 Lanenet 实时检测 深度学习 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]