基于改进欧氏聚类算法的障碍物检测跟踪
作者:
基金项目:

教育部产学合作协同育人项目(202101321016); 江苏省高等学校自然科学研究面上项目(19KJB520044); 江苏高校“青蓝工程”


Obstacle Detection and Tracking Based on Improved Euclidean Clustering Algorithm
Author:
  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [14]
  • |
  • 相似文献 [20]
  • | | |
  • 文章评论
    摘要:

    障碍物的检测与跟踪技术是移动机器人行驶过程中的一个重要技术, 有利于提高移动机器人的运动安全. 为了提高了障碍物检测的准确率, 针对欧氏聚类存在过分割和欠分割的情况, 做出了两点改进: 提出动态欧氏聚类搜索半径的方法来解决远处点云过于稀疏的问题; 提出将半径搜索改成深度方向上的拓展搜索的方法来解决点云数据在深度方向上检测不完全和拖尾等问题. 为了提高动态障碍物跟踪的准确率, 在进行两帧障碍物数据关联时, 设计了一种新的关联矩阵的计算方式, 加入了障碍物的六自由度信息和尺寸信息, 提高了动态匹配的成功率. 仿真实验表明, 经过改进后障碍物检测准确率达到了95.2%, 多目标跟踪精度达到了13.2 mm.

    Abstract:

    Obstacle detection and tracking technology is an important technology in the process of mobile robot driving, which is conducive to improving the movement safety of mobile robots. In order to improve the accuracy of obstacle detection, two improvements have been made to overcome the over-segmentation and under-segmentation of Euclidean clustering. A dynamic Euclidean clustering search radius method is proposed to solve the problem of too sparse distant point clouds, and a method of changing radius search to extended search in the depth direction is proposed to solve the problems of incomplete detection and trailing in the depth direction of point cloud data. In order to improve the accuracy of dynamic obstacle tracking, a new calculation formula of association matrix is designed when two frame obstacle data association is performed, and six degrees of freedom information and size information of the obstacle are added, which improves the success rate of dynamic matching. Simulation experiments show that the improved obstacle detection accuracy reaches 95.2%, and the multi-target tracking accuracy reaches 13.2 mm.

    参考文献
    [1] 杨大磊, 任文峰, 马庆龙. 基于三维激光雷达的障碍物检测与跟踪. 汽车实用技术, 2019(21): 53–55.
    [2] Nguyen VD, Van Nguyen H, Tran DT, et al. Learning framework for robust obstacle detection, recognition, and tracking. IEEE Transactions on Intelligent Transportation Systems, 2017, 18(6): 1633–1646.
    [3] Chen X, Deng ZD. Detection of road obstacles using 3D Lidar data via road plane fitting. Proceedings of the 2015 Chinese Intelligent Automation Conference: Intelligent Technology and Systems. Berlin: Springer, 2015. 427–435.
    [4] 谢德胜, 徐友春, 王任栋, 等. 基于三维激光雷达的无人车障碍物检测与跟踪. 汽车工程, 2018, 40(8): 952–959.
    [5] 许艳伟. 基于激光雷达的无人驾驶系统三维车辆检测. 自动化应用, 2023, 64(5): 179–182.
    [6] 王涛, 曾文浩, 于琪. 基于激光雷达的无人驾驶障碍物检测和跟踪. 西南交通大学学报, 2021, 56(6): 1346–1354.
    [7] 何小英, 王旭. 激光雷达和视觉技术的机器人移动位置跟踪系统. 激光杂志, 2023, 44(1): 232–237.
    [8] Ruoyu F, Cheng C. Computer vision based obstacle detection and target tracking for autonomous vehicles. MATEC Web of Conferences, 2021, 336: 07004.
    [9] Fortin B, Lherbier R, Noyer JC. A model-based joint detection and tracking approach for multi-vehicle tracking with lidar sensor. IEEE Transactions on Intelligent Transportation Systems, 2015, 16(4): 1883–1895.
    [10] 尚业华, 张光强, 孟志军, 等. 基于欧氏聚类的三维激光点云田间障碍物检测方法. 农业机械学报, 2022, 53(1): 23–32.
    [11] 田晨睿, 姜良存, 张明达, 等. 结合多层感知器与KM算法的POI匹配方法. 地理与地理信息科学, 2020, 36(2): 16–21.
    [12] Lee W, Kim H, Ahn J. Defect-free atomic array formation using the Hungarian matching algorithm. Physical Review A, 2017, 95(5): 053424.
    [13] Bernardin K, Stiefelhagen R. Evaluating multiple object tracking performance: The clear mot metrics. EURASIP Journal on Image and Video Processing, 2008, 2008(1): 246309.
    [14] Mariia G, Nikita K, Nikolaus D, et al. DirectTracker: 3D Multi-object tracking using direct image alignment and photometric bundle adjustment. IEEE International Conference on Intelligent Robots and Systems (IROS), 2022, 15(10): 1–8.
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

宋莹,陆宇杭,陈逸菲.基于改进欧氏聚类算法的障碍物检测跟踪.计算机系统应用,2024,33(2):284-290

复制
分享
文章指标
  • 点击次数:445
  • 下载次数: 1246
  • HTML阅读次数: 797
  • 引用次数: 0
历史
  • 收稿日期:2023-06-17
  • 最后修改日期:2023-08-11
  • 在线发布日期: 2023-12-25
  • 出版日期: 2023-02-05
文章二维码
您是第11204110位访问者
版权所有:中国科学院软件研究所 京ICP备05046678号-3
地址:北京海淀区中关村南四街4号 中科院软件园区 7号楼305房间,邮政编码:100190
电话:010-62661041 传真: Email:csa (a) iscas.ac.cn
技术支持:北京勤云科技发展有限公司

京公网安备 11040202500063号