基于简易视觉标签的高精度室内定位技术
作者单位:

1.东风柳州汽车有限公司;2.重庆大学

基金项目:

国家重点实验室开放基金(KFY2209);汽车协同创新中心揭榜挂帅项目(2022CDJDX-004)和重庆市技术创新与应用发展专项( CSTB2022TIAD-KPX0139)


Indoor Location Technology with High Accuracy Based on Simple Visual Labels
Author:
Affiliation:

1.Technology Center of Passenger Car,Dongfeng Liuzhou Automobile Co,Ltd;2.College of Mechanical and Vehicle Engineering,Chongqing University

  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [19]
  • | |
  • 引证文献
  • | |
  • 文章评论
    摘要:

    为实现低成本高精度的室内定位,在综合考虑定位需求和计算复杂性的基础上,设计了一种基于简易视觉标签的室内高精度定位技术。该技术采用简单的颜色和形状特征检测视觉标签,从而降低检测复杂度,减少数据存储需求。进一步针对简易标签特征不唯一问题,设计了基于相机视场和标签方位角的快速查询匹配方法。并通过分析标签分布特性与定位误差关系,设计加权最小二乘位姿估计算法,建立迭代求解和最优估计的协同策略,实现了算法复杂度和定位精度的良好平衡。仿真和实验结果表明所提定位方法能够有效处理超定方程组奇异问题,抑制不良标签组的负面影响,与超宽带技术相比定位误差降低超62%。

    Abstract:

    To achieve low-cost and high-precision, an indoor location system with simple visual labels is designed by comprehensively considering the requirement and computation complexity. Only the color and shape features are used for label detection, by which both detection complexity and data storage requirement are reduced. To deal with the nonunique solution problem caused by the simple label features, a fast query and matching method is further presented by using the view field of camera and azimuth of label. Then based on the relationship analysis between the distribution characteristics of labels and location error, a pose and position estimation method using the weighted least square algorithm is designed and cooperated with the interactive algorithm by the designed switching strategy. A good balance has been made between the algorithm complexity and location accuracy by the presented techniques. The simulation and experiment results show that the proposed method can deal with the singular problem of the overdetermined equations effectively and attenuate the negative effect of bad label groups. Compared with the ultra-wide band technology, the location error is reduced more than 62%.

    参考文献
    [1] 张华. 基于机器视觉的室内定位系统设计与研究[D]. 华北电力大学, 2018.HANG H. Research on automatic driving vehicle state based on Gaussian pseudospectral method[D]. North China Electric Power University. 2018.
    [2] GUAN K, MA L, TAN X, et al. Vision-based indoor localization approach based on SURF and landmark[C]. 2016 International Wireless Communications and Mobile Computing Conference (IWCMC). IEEE, 2016: 655-659.
    [3] HONG W, XIA H, AN X, et al. Natural landmarks based localization algorithm for indoor robot with binocular vision[C]. 2017 29th Chinese Control And Decision Conference (CCDC). IEEE, 2017: 3313-3318
    [4] 戴进. 基于语义的视觉定位算法研究[D]. 哈尔滨工业大学, 2019.AI J. Research on visual location algorithm based on semantics[D]. Harbin Institute of Technology,2019.
    [5] 关静. 人工路标拓扑模式构建与识别及其应用研究[D]. 江苏科技大学, 2017.UAN J. Research on construction and recognition of artificial landmark topological pattern and its application [D]. Jiangsu University of science and technology, 2017.
    [6] 冯玮. 用于视觉定位的二维码快速识别技术研究[D]. 山东理工大学, 2018.ENG W. Research on two dimensional code fast recognition technology for visual location[D]. Shandong University of Technology, 2018.
    [7] 徐聪. 基于计算机视觉的室内定位关键技术研究[D]. 电子科技大学, 2019.U C. Research on key technology of indoor positioning based on computer vision[D]. University of Electronic Science and technology, 2019.
    [8] 周丽莎. 基于模板匹配的视觉定位技术研究与应用[D]. 大连理工大学, 2012.HOU L S. Research and application of visual location technology based on template matching[D]. Dalian University of Technology, 2012.
    [9] SHAO F, LIN W, GU S, et al. Perceptual Full-Reference Quality Assessment of Stereoscopic Images by Considering Binocular Visual Characteristics[J]. IEEE Transactions on Image Processing, 2013,22(5): 1940-1953.
    [10] 谢洪乐, 朱齐丹, 刘鹏. 基于极大似然估计的全景立体视觉机器人自定位方法[J]. 应用科技, 2017,44(05): 40-45.IE H L, ZHU Q D, LIU P. Self localization method of panoramic stereo vision robot based on maximum likelihood estimation[J]. Applied Technology, 2017,44(05): 40-45.
    [11] 江利中, 雷威, 王珺. 基于机器视觉的雷达测角精度评估系统[J]. 计算机测量与控制, 2014,22(9): 2842-2843, 2866.IANG L Z, LEI W, WANG J. Radar angle measurement accuracy evaluation system based on machine vision[J]. Computer measurement and control, 2014,22(9): 2842-2843, 2866.
    [12] 张栩. 面向室外移动机器人的路标定位系统[D]. 上海交通大学, 2010.HANG Y. Landmark positioning system for outdoor mobile robot[D]. Shanghai Jiaotong University, 2010.
    [13] LEE J, WANG Y, LU C, et al. The Enhancement of Graphic QR Code Recognition using Convolutional Neural Networks[C]. 2019 8th International Conference on Innovation, Communication and Engineering (ICICE). IEEE, 2019: 94-97.
    [14] MACII P N D F. Optimal Placement of Landmarks for Indoor Localization using Sensors with a Limited Range[C]. 2016 International Conference on Indoor Positioning and Indoor Navigation (IPIN). IEEE, 2016: 4586-4593.
    [15] Point in triangle test[EB/OL]. [2021-1-7]. https://blackpawn.com/texts/pointinpoly/.
    [16] ARRAS K O. An Introduction To Error Propagation: Derivation, Meaning and Examples of Equation Cy= Fx Cx FxT[J]. Autonomous Systems Lab Institute of Robotic Systems, 1998:1-21.
    [17] 袁建平. 卫星导航原理与应用[M]. 第1版. 中国宇航出版社, 2003: 373.UAN J P. Principle and application of satellite navigation[M]. First edition. China Aerospace Press, 2003: 373.
    [18] COHEN C J, KOSS F V. Comprehensive study of three-object triangulation[C]. Mobile Robots VII. SPIE, 1993: 95-106.
    [19] 程琦, 胡杰, 王均晖. 基于数据驱动的无人机加权最小二乘定位算法[J]. 指挥信息系统与技术, 2020,11(06): 76-80.HEN Y, HU J, WANG J H. Data driven weighted least square localization algorithm for UAV[J]. Command information system and technology, 2020,11(06): 76-80.
    相似文献
    引证文献
引用本文
相关视频

分享
文章指标
  • 点击次数:194
  • 下载次数: 0
  • HTML阅读次数: 0
  • 引用次数: 0
历史
  • 收稿日期:2023-03-17
  • 最后修改日期:2023-04-28
  • 录用日期:2023-05-04
文章二维码