计算机科学 ›› 2021, Vol. 48 ›› Issue (9): 135-139.doi: 10.11896/jsjkx.201000047

• 计算机图形学&多媒体 • 上一篇    下一篇

基于双目视觉的车辆速度测量方法

常子霆1, 施雨晴1, 王俊1, 于明鹤2, 姚兰3, 赵志滨1,3   

  1. 1 东北大学计算机科学与工程学院 沈阳110819
    2 东北大学软件学院 沈阳110819
    3 沈阳帝信人工智能产业研究院有限公司 沈阳110121
  • 收稿日期:2020-10-11 修回日期:2020-11-23 出版日期:2021-09-15 发布日期:2021-09-10
  • 通讯作者: 赵志滨(zhaozb@mail.neu.edu.cn)
  • 作者简介:1871485@stu.neu.edu.cn
  • 基金资助:
    国家自然科学基金青年科学基金项目(61902055)

Vehicle Speed Measurement Method Based on Binocular Vision

CHANG Zi-ting1, SHI Yu-qing1, WANG Jun1, YU Ming-he2, YAO Lan3, ZHAO Zhi-bin1,3   

  1. 1 School of Computer Science and Engineering,Northeast University,Shenyang 110819,China
    2 School of Software,Northeast University,Shenyang 110819,China
    3 Shenyang Dixin Artificial Intelligence Industry Research Institute Co.,Ltd,Shenyang 110121,China
  • Received:2020-10-11 Revised:2020-11-23 Online:2021-09-15 Published:2021-09-10
  • About author:CHANG Zi-ting,born in 1996,postgra-duate,is a member of China Computer Federation.His main research interests include computer vision and so on.
    ZHAO Zhi-bin,born in 1975,Ph.D,associate professor,is a member of China Computer Federation.His main research interests include big data mana-gement and query optimization,image processing,text analysis and so on.
  • Supported by:
    National Natural Science Foundation of China Project (61902055)

摘要: 为配合高速公路入口处的货车称重工作,需要测量车辆通过称重台时的实时速度。利用双目视觉技术测速具有成本低、部署简单、稳定性高的优点,具有广阔的应用前景。双目视觉测速的技术难点是目标的位移测量,其核心问题是目标在多帧图像间的精准匹配。文中提出了一种基于空间位置的匹配区域对齐算法与基于模板匹配的空间位移计算方法。具体地,利用车轮的空间位置关系来限制车轮的匹配区域,可有效降低相似车轮的误匹配问题;使用模板匹配的方法追踪车轮的关键点,进而获得多帧之间车轮的空间位移。使用某高速公路入口的真实通行视频数据进行实验验证,结果表明,与其他双目测速方法相比,所提方法使得测速结果的RMSE下降了20%~40%,且更加适用于车辆以较快速度(10~20 km/h)通过高速公路入口测速点的实际场景。

关键词: 车速测量, 匹配区域对齐, 双目视觉, 模板匹配

Abstract: Real-time speed measurement is a vital issue to assist truck weighing at the entrance of expressway when a truck passes through a scale.Binocular vision technology technically has the advantages of low cost,easy deployment and high stability,which qualify it a potential for prospective application.The key point for binocular vision based speed measurement is displacement-measuring of a target,which is subject to accurate target matching in multiple frames.This paper presents an alignment algorithm on region matching based on spatial location and a calculation method for spatial displacement based on template ma-tching.Specifically,relative spatial location of a wheel is introduced to restrain its matching area,which effectively reduces the mismatching on similar wheels; template matching is derived to track the key points of a wheel for spatial displacement between multiple frames.The practical traffic video data taken at an expressway entrance is applied to experiments.The results show that,compared with other binocular vision based speed measurement methods,our method declines the RMSE of the speed measurement results by 20%~40%,and it more suitable for the real scene when vehicles pass the speed measurement point at the entrance of expressway at a relatively high speed(10~20 km/h).

Key words: Vehicle speed measurement, Alignment on region matching, Binocular vision, Template matching

中图分类号: 

  • TP391
[1]LIU D,DENG Z,WANG Y,et al.Method for Identifying Truck Traffic Site Clustering Using Weigh-in-Motion (WIM) Data[J].IEEE Access,2020(99):1.
[2]CHEN N,LI Q,LI F,et al.A Data Processing Algorithm Based on Vehicle Weigh-in-motion Systems[C]//Ninth International Conference on Natural Computation.IEEE,2014.
[3]LIANG Y,LI K L,BI F H,et al.Research on LFMCW Radar Velocity Ranging Optimization System Based on FPGA[J].Procedia Computer Science,2020,166:187-194.
[4]XIE Y S,SHEN G S,WU Q C.Vehicle-mounted radar velocity and distance measurement system based on MSP430[J].Computer Engineering,2011,37(18):236-239.
[5]LI W T,TANG H,ZHOU J.Research on laser velocimeter for overspeed detection on highways[J].Acta Photonica Sinica,2020,49(9):149-158.
[6]MAO X,INOUE D,KATO S,et al.Amplitude-Modulated Laser Radar for Range and Speed Measurement in Car Applications[J].IEEE Transactions on Intelligent Transportation Systems,2012,13(1):408-413.
[7]DEHNAVI M,ESHGHI M.FPGA based real-time on-roadstereo vision system[J].Journal of Systems Architecture,2017,81:32-43.
[8]ZHU J,YUAN L,ZHENG Y F,et al.Stereo Visual Tracking within Structured Environments for Measuring Vehicle Speed[J].IEEE Transactions on Circuits and Systems for Video Technology,2012,22(10):1471-1484.
[9]CAI S X.A vehicle speed-measuring system based on binocular stereo vision[D].Hefei:University of Electronic Science and Technology of China,2013.
[10]LI M L.Intelligent measurement of vehicle speed trajectorybased on binocular stereo vision[D].Zhengzhou:Zhongyuan University of Technology,2019.
[11]JU Z Y,WANG C N,HE X L.Research on real-time detection algorithm of vehicle speed based on video images[J].Application Research of Computers,2017,34(9):2822-2824.
[12]LI X,ZHOU Z,LI X,et al.Vehicle Segmentation and Speed Detection Based on Binocular Stereo Vision[C]//2012 Eighth International Conference on Computational Intelligence and Secu-rity.IEEE,2012:369-373.
[13]CZYZ J,RISTIC B,MACQ B.A Particle Filter for Joint Detection and Tracking of Color Objects[J].Image and Vision Computing,2007,25(8):1271-1281.
[14]LIU W,ANGUELOY D,ERHAN D,et al.SSD:Single ShotMultibox Detector[C]//European Conference on Computer Vision.Cham:Springer,2016:21-37.
[15]CHEN J,WANG J,MI C,et al.Speed measuring method at the highway toll-gate based on the analysis of the continuous images[J].Chinese Journal of Construction Machinery,2019,17 (1):79-84.
[16]REDMON J,FARHADI A.YOLOv3:An Incremental Improve-ment[J].arXiv:1804.02767,2018.
[17]RAHMAN M A,WANG Y.Optimizing intersection-over-union in deep neural networks for image segmentation[C]//International Symposium on Visual Computing.Cham:Springer,2016:234-244.
[18]YANG Y,MA T,DU S.Robust Template Matching with Angle Location Using Dynamic Feature Pairs Updating[J].Applied Soft Computing,2019,85:105804.
[1] 祝文韬, 谢宝蓉, 王琰, 沈霁, 朱浩文. 光学遥感图像中的飞机目标检测技术研究综述[J]. 计算机科学, 2020, 47(11A): 165-171.
[2] 陈颖, 赵来旺, 詹洪陈, 丁尧. 双视系统的室内三维场景重建研究[J]. 计算机科学, 2020, 47(11A): 175-177.
[3] 赵子阳, 蒋慕蓉, 黄亚群, 郝健宇, 曾科. 结合SFS和双目模型的单幅图像深度估计算法[J]. 计算机科学, 2019, 46(6A): 161-164.
[4] 李银国, 周中奎, 白羚. 基于双目图像的大尺度智能驾驶场景重建[J]. 计算机科学, 2019, 46(11A): 251-254.
[5] 刘博艺,唐湘滟,程杰仁. 基于多生长时期模板匹配的玉米螟识别方法[J]. 计算机科学, 2018, 45(4): 106-111.
[6] 黄健, 郭志波, 林科军. 一种基于核相关滤波的视觉跟踪算法[J]. 计算机科学, 2018, 45(11A): 230-233.
[7] 王艳,徐诗艺,谌海云. 基于特征距离加权的手势识别[J]. 计算机科学, 2017, 44(Z6): 220-223.
[8] 徐启航,游安清,马社,崔云俊. 基本图像处理算法的优化过程研究[J]. 计算机科学, 2017, 44(Z6): 169-172.
[9] 李秀娟,刘伟,李珊红. 基于双目视觉导航的仿生机器人鲁棒控制算法[J]. 计算机科学, 2017, 44(8): 318-321.
[10] 赵霞,袁家政,刘宏哲. 基于视觉的目标定位技术的研究进展[J]. 计算机科学, 2016, 43(6): 10-16.
[11] 王鑫,杨延红,陈胜勇. 人体几何建模方法综述[J]. 计算机科学, 2015, 42(Z11): 104-108.
[12] 陶军,刘建明,王明文,万剑怡. 大量类别下非纹理对象实时检测与识别[J]. 计算机科学, 2015, 42(10): 321-324.
[13] 丁山,宋丽晓. 一种改进的视网膜图像中微小动脉瘤的检测算法[J]. 计算机科学, 2014, 41(12): 269-274.
[14] 王万良,金亦挺,赵燕伟,郑建炜. 基于边缘相关性距离约束的角点匹配[J]. 计算机科学, 2013, 40(5): 283-286.
[15] 陈伟,丁世飞,夏士雄. 煤矿监控图像中脸肤色和模板检测[J]. 计算机科学, 2010, 37(8): 280-282.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
[1] 庞博,金乾坤,合尼古力·吾买尔,齐兴斌. 软件定义网络中基于网络切片和ILP模型的路由方案[J]. 计算机科学, 2018, 45(4): 143 -147 .
[2] 刘琴. 计算机取证过程中基于约束的数据质量问题研究[J]. 计算机科学, 2018, 45(4): 169 -172 .
[3] 李小薪,李晶晶,贺霖,刘志勇. 基于噪声空间结构嵌入和高维梯度方向嵌入的鲁棒人脸识别方法[J]. 计算机科学, 2018, 45(4): 285 -290 .
[4] 杨沛安, 武杨, 苏莉娅, 刘宝旭. 网络空间威胁情报共享技术综述[J]. 计算机科学, 2018, 45(6): 9 -18 .
[5] 项英倬, 谭菊仙, 韩杰思, 石浩. 图匹配技术研究[J]. 计算机科学, 2018, 45(6): 27 -31 .
[6] 陈福才, 李思豪, 张建朋, 黄瑞阳. 基于标签关系改进的多标签特征选择算法[J]. 计算机科学, 2018, 45(6): 228 -234 .
[7] 陈嵘, 李鹏, 黄勇. 基于多特征融合的运动阴影去除算法[J]. 计算机科学, 2018, 45(6): 291 -295 .
[8] 敖权,陆慧梅,向勇,曹睿东. 基于QEMU的Linux应用异常通信行为分析[J]. 计算机科学, 2018, 45(5): 89 -96 .
[9] 徐凤生,于秀清,史开泉. P-数据模型与数据的智能获取[J]. 计算机科学, 2018, 45(5): 176 -179 .
[10] 赵兴旺,梁吉业,郭兰杰. 一种基于空间变换的协同过滤推荐算法[J]. 计算机科学, 2018, 45(7): 16 -21 .