计算机科学

计算机科学 ›› 2020, Vol. 47 ›› Issue (7): 97-102.doi: 10.11896/jsjkx.190900011

• 计算机图形学&多媒体 • 上一篇    下一篇

基于标准路牌的车辆自定位

张善彬1, 袁金钊1, 陈辉1, 王玉荣1, 王杰1, 屠长河2   

  1. 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
  • 收稿日期:2019-08-31 出版日期:2020-07-15 发布日期:2020-07-16
  • 通讯作者: 陈辉(huichen@sdu.edu.cn)
  • 作者简介:bszsdu@163.com
  • 基金资助:
    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)

Vehicle Self-localization Based on Standard Road Sign

ZHANG Shan-bin1, YUAN Jin-zhao1, CHEN Hui1, WANG Yu-rong1, WANG Jie1, TU Chang-he2   

  1. 1 School of Information Science and Engineering,Shandong University,Qingdao,Shandong 266237,China
    2 School of Computer Science and Technology,Shandong University,Qingdao,Shandong 266237,China
  • Received:2019-08-31 Online:2020-07-15 Published:2020-07-16
  • About author:ZHANG Shan-bin,born in 1993,postgraduate.His main research interests include computer vision and image processing.
    CHEN Hui,born in 1963,Ph.D,professor.Her main research interests include computer vision,3D morphing and virtual reality.
  • Supported by:
    This work was supported by the Natural Science Foundation of Shandong Province,China(ZR2017MF057),Key R&D Project of Shandong Pro-vince,China(2019GGX101018) and Subtopics of National Key Fund (61332015)

PDF (PC)

1049

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30m以内定位精度可以达到0.1m,在20m以内时定位精度可以达到0.05m。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。

关键词: 标准路牌, 单目相机, 路牌数据库, 投影变换, 运动限制

Abstract: 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.

Key words: Constrained motion, Monocular camera, Projection transformation, Road sign database, Standard road sign

中图分类号: 

  • TP391.41
[1]ARMESTO L,TORNERO J.Robust and Efficient Mobile Robot Self-localization using Laser Scanner and Geometrical Maps[C]//IEEE/RSJ International Conference on Intelligent Robots &Systems.IEEE,2006.
[2]CHOI B S,LEE J J.Mobile robot localization scheme based on RFID and sonar fusion system[C]//IEEE International Symposium on Industrial Electronics,2009(ISIE 2009).IEEE,2009.
[3]BENCHEIKH S,IBRIR S,BOUKRAA S.Attitude observersfor accelerated vehicles using IMU and GPS measurements[C]//International Multi-conference on Systems.IEEE,2015.
[4]CARON F,DUFLOS E,POMORSKI D,et al.GPS/IMU data fusion using multisensor Kalman filtering:introduction of contextual aspects[J].Information Fusion,2006,7(2):221-230.
[5]RUCHTI P,STEDER B,RUHNKE M,et al.Localization on OpenStreetMap data using a 3D laser scanner[C]//IEEE International Conference on Robotics & Automation.IEEE,2015.
[6]HATA A Y,WOLF D F.Feature Detection for Vehicle Localization in Urban Environments Using a Multilayer LIDAR[J].IEEE Transactions on Intelligent Transportation Systems,2015,17(2):1-10.
[7]WEI D,JI X,LI W,et al.Vehicle localization based on odometry assisted magnetic matching[C]//International Conference on Indoor Positioning & Indoor Navigation.IEEE,2017.
[8]WEI L,CAPPELLE C,RUICHEK Y.Camera/Laser/GPS Fu-sion Method for Vehicle Positioning Under Extended NIS-Based Sensor Validation[J].IEEE Transactions on Instrumentation and Measurement,2013,62(11):3110-3122.
[9]LATEGAHN H,SCHREIBER M,ZIEGLER J,et al.Urban Localization with Camera and Inertial Measurement Unit[C]//IEEE Intelligent Vehicles Symposium.IEEE,2013.
[10]REZAEI S,SENGUPTA R.Kalman Filter-Based Integration of DGPS and Vehicle Sensors for Localization[J].IEEE Transactions on Control Systems Technology,2007,15(6):1080-1088.
[11]UCHIYAMA H,DEGUCHI D,TAKAHASHI T,et al.Ego-localization using streetscape image sequences from in-vehicle cameras[C]//Intelligent Vehicles Symposium.IEEE,2009.
[12]WONG D,DEGUCHI D,IDE I,et al.Vision-Based Vehicle Localization Using a Visual Street Map with Embedded SURF Scale[C]//Computer Vision－ECCV 2014 Workshops.Sprin-ger International Publishing,2014:167-179.
[13]NUR D,DHARMIZA S,SALLEH A,et al.Monocular visual odometry with road probability distribution factor for lane-level vehicle localization[C]//2016 14th International Conference on Control,Automation,Robotics and Vision (ICARCV).IEEE,2016.
[14]YU Y,ZHAO H,DAVOINE F,et al.Monocular visual localization using road structural features[C]//2014 IEEE Intelligent Vehicles Symposium (IV).IEEE,2014.
[15]SCHLECHTRIEMEN J,WEDEL A,HILLENBRAND J,et al.A lane change detection approach using feature ranking with maximized predictive power[C]//IEEE Intelligent Vehicles Symposium.IEEE,2014.
[16]YUAN J Z,CHEN H,ZHAO B,et al.Estimation of Vehicle Pose and Position with Monocular Camera at Urban Road Intersections[J].Journal of Computer Science and Technology,2017,32(6):1150-1161.
[17]MARCHAND E,UCHIYAMA H,SPINDLER F.Pose Estimation for Augmented Reality:A Hands-On Survey[J].IEEE Transactions on Visualization and Computer Graphics,2016,22(12):2633-2651.
[18]YANG G,SANIIE J.Indoor navigation for visually impaired using AR markers[C]//2017 IEEE International Conference on Electro Information Technology (EIT).IEEE,2017.
[19]MAIDI M,DIDIER J Y,ABABSA F,et al.A performance study for camera pose estimation using visual marker based tracking[J].Machine Vision & Applications,2010,21(3):365-376.
[20]WU W.Vison-based auxiliary navigation method using augmented reality for unmanned aerial vehicles[C]//IEEE International Conference on Industrial Informatics.IEEE,2012.
[21]SANI M F,KARIMIAN G.Automatic navigation and landing of an indoor AR.drone quadrotor using ArUco marker and inertial sensors[C]//International Conference on Computer & Drone Applications.2017:102-107.
[1] 常嘉义,秦瑞,李庆,陈曦,徐坚俊.
基于全景鸟瞰视图的障碍物检测方法研究
Research of Obstacle Detection Based on Aerial Panorama Image
计算机科学, 2014, 41(Z11): 78-82.
[2] 鲁斌,秦瑞,李庆,陈大鹏.
车载环视拼接方法的研究
Study of Vehicle-surrounding Image Stitch Algorithm
计算机科学, 2013, 40(9): 293-295.
[3] 伍晓亮,田怀文.
一种基于正等轴测草图的三维重构算法
Method of 3D Reconstruction Based on Given Axonometric Sketching
计算机科学, 2013, 40(9): 275-278.
[4] 陈雪龙 王延章 许永涛.
地理信息系统中地图无级漫游的实现方法之研究

计算机科学, 2006, 33(5): 166-168.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发