基于标准路牌的车辆自定位  

Vehicle Self-localization Based on Standard Road Sign

作　　者：张善彬 袁金钊[1] 陈辉[1] 王玉荣[1] 王杰 屠长河[2] ZHANG Shan-bin;YUAN Jin-zhao;CHEN Hui;WANG Yu-rong;WANG Jie;TU Chang-he(Schoolof Information Science and Engineering,Shandong University,Qingdao,Shandong 266237,China;School of Computer Science and Technology,Shandong University,Qingdao,Shandong 266237,China)

机构地区：[1]山东大学信息科学与工程学院,山东青岛266237 [2]山东大学计算机科学与技术学院,山东青岛266237

出　　处：《计算机科学》2020年第7期97-102,共6页Computer Science

基　　金：山东省自然科学基金(ZR2017MF057);山东省重点研发计划项目(2019GGX101018);国家重点基金子课题(61332015)。

摘　　要：车辆自定位是自动驾驶及高级辅助驾驶的关键技术之一,快速准确的车辆自定位可及时为导航或智能驾驶系统提供自车位置信息。针对自动驾驶和高级辅助驾驶领域中复杂环境下的车辆定位问题,提出了一种基于标准路牌的车辆自定位方法。设计了一个包含标准路牌的简易数据库,该数据库中预存标准路牌的字符、尺寸和控制点坐标等信息。通过车载单目相机采集包含标准路牌的视频流图像,提取标识区域质心坐标为控制点,计算每一帧视频流图像与数据库基准图像之间的平面投影变换矩阵,采用运动约束和矩阵分解求取车载相机的稳定位置。在真实道路环境中对该方法进行实验测试,结果表明,所提方法在30 m以内定位精度可以达到0.1 m,在20 m以内时定位精度可以达到0.05 m。该方法成本低、简单可靠,可利用车载单目相机与标准路牌实现车辆在复杂交通路段的精准自定位。Vehicle self-localization is one of the key technologies of automatic driving and advanced assistant driving.Fast and accurate vehicle self-localization can provide vehicle location information for navigation or intelligent driving system in time.Aiming at the problem of vehicle positioning in complex environment in the field of automatic driving and advanced assistant driving system,a vehicle self-localization method based on standard road signs is proposed.A simple database containing standard road signs is designed,in which information such as fonts,sizes and control point coordinates of the road signs are pre-stored.The video stream images containing the standard road signs are captured by a vehicle-mounted monocular camera.Centroid coordinates of the identification area are extracted as control points,and the planar projection transformation matrix between each frame of the video stream image and the database reference image is calculated.Motion constrains and matrix decomposition are used to obtain the stable position of the on-board camera.Experimental tests are performed in the real road environment.The results show that the positioning accuracy of proposed method within 30 meters can reach 0.1 meters,and 0.05 meters within 20 meters.This method is low-cost,simple and reliable,and can use on-board monocular camera and standard road signs to realize precise self-localization of vehicles in complex traffic sections.

关 键 词：标准路牌 路牌数据库 单目相机 投影变换 运动限制 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]