•  
  •  
 

Corresponding Author

张永华, 男, 博士, 助理研究员. E-mail: zhangyonghua@tsinghua.edu.cn

Abstract

Camera is the most widely used sensor in intelligent transportation systems (ITS),but the decline of detection and positioning accuracy caused by target occlusion and external environment interference has always been an important factor restricting the development of ITS.In order to solve this problem,a multi-mode fusion target detection and tracking method based on millimeter-wave radar (MWR ) and camera on highway side was designed.Compared with cameras,high-resolution MWR had better measurement accuracy and weather robustness,serving as a better complement to camera perception.The proposed method used the center point-based radar and camera fusion algorithm for target detection and adopted the greedy algorithm for target association.The test results show that on the public dataset nuScenes and the self-built multi-modal dataset of highway side,the proposed method achieves an AMOTA (multi-object tracking accuracy ) performance of 69.1% on the nuScenes dataset,outperforming all visual-based 3D tracking benchmark methods;the self-built dataset verifies its good applicability and accuracy,and the processing time for a single image is 35 ms.

Publication Date

12-24-2025

DOI

10.14048/j.issn.1671-2579.2025.06.030

First Page

261

Last Page

267

Submission Date

December 2025

Reference

[1]管丽萍,尹湘源.交通事件管理系统研究现状综述 [J].中外公路,2009,29(3):255-261.GUAN Liping,YIN Xiangyuan.Summary of research status of traffic incident management system [J].Journal of China & Foreign Highway,2009,29(3):255-261.
[2]李薇,蒋昀轩,熊睿,等.基于自然驾驶的山区高速公路综合交通风险评价方法 [J].公路,2025,70(6):284-292.LI Wei,JIANG Yunxuan,XIONG Rui,et al.Comprehensive traffic bisk evaluation method for mountainous expressways based on natural driving [J].Highway,2025,70(6):284-292.
[3]吴志敏,黄觉,向崎.基于 K-Means 聚类算法的高速公路事故多发路段鉴别 [J].中外公路,2022,42(6):260-264.WU Zhimin,HUANG Jue,XIANG Qi.Identification of freeway accident-prone sections based on K-Means clustering algorithm [J].Journal of China & Foreign Highway,2022,42(6):260-264.
[4]李海亮.面向 BIM设计的复杂工点三维场景建模方法研究 [J].中外公路,2021,41(6):306-309.LI Hailiang.Research on 3D scene modeling method for complex worksites based on BIM design [J].Journal of China & Foreign Highway,2021,41(6):306-309.
[5]虞将苗,唐嘉明,张肖宁,等.基于三维探地雷达的沥青路面厚度动态调整技术研究 [J].中外公路,2020,40(3):70-75.YU Jiangmiao,TANG Jiaming,ZHANG Xiaoning,et al.Research on dynamic adjustment technology of asphalt pavement thickness based on 3D ground penetrating radar[J].Journal of China & Foreign Highway,2020,40(3):70-75.
[6]FANG K,XIANG Y,LI X C,et al.Recurrent autoregressive networks for online multi-object tracking[C]// Lake Tahoe:2018 IEEE Winter Conference on Applications of Computer Vision (WACV ),2018:466-475.
[7]李旭辉,黄奕辉.基于互联网的公路施工工序质量跟踪系统构建 [J].公路,2019,64(10):215-218.LI Xuhui,HUANG Yihui.Construction of highway construction process quality tracking system based on Internet [J].Highway,2019,64(10):215-218.
[8]王孜健,张涵,么新鹏,等.高速公路二维图形与三维形貌病害数据的构建 [J].中外公路,2025,45(2):238-246.WANG Zijian,ZHANG Han,YAO Xinpeng,et al.Construction of disease dataset comprising 2D images and 3D morphologies of highways [J].Journal of China & Foreign Highway,2025,45(2):238-246.
[9]BEWLEY A,GE Z Y,OTT L,et al.Simple online and realtime tracking [C]//Phoenix:2016 IEEE International Conference on Image Processing (ICIP ),2016:3464 -3468.
[10]REDMON J,DIVVALA S,GIRSHICK R,et al.You only look once:Unified,real-time object detection [C]//Las Vegas:2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR ),2016:779-788.
[11]谢海波,朱玮峻,张璧,等.面向高强度螺栓检测的YOLOv 5-Ganomaly 联合算法研究 [J].中外公路,2024,44(4):171-179.XIE Haibo,ZHU Weijun,ZHANG Bi,et al.Research on YOLOv 5-Ganomaly joint algorithm for high-strength bolt detection [J].Journal of China & Foreign Highway,2024,44(4):171-179.
[12]WU H,HAN W K,WEN C L,et al.3D multi-object tracking in point clouds based on prediction confidence-guided data association [J].IEEE Transactions on Intelligent Transportation Systems,2022,23(6):5668 -5677.
[13]HU H N,CAI Q Z,WANG D Q,et al.Joint monocular 3D vehicle detection and tracking [C]//Seoul:2019 IEEE/CVF International Conference on Computer Vision (ICCV ),2019:5389 -5398.
[14]ZHANG W W,ZHOU H,SUN S Y,et al.Robust multi-modality multi-object tracking [C]//Seoul:2019 IEEE/CVF International Conference on Computer Vision (ICCV ),2019:2365 -2374.
[15]MENG Z L,XIA X,XU R S,et al.HYDRO- 3D:Hybrid object detection and tracking for cooperative perception using 3D LiDAR [J].IEEE Transactions on Intelligent Vehicles,2023,8(8):4069 -4080.
[16]杨浩冉,李辉,艾晓雪,等.图像与点云三维体信息交互的3D多目标跟踪网络 [J].控制与决策,2024,39(12):4127 -4135.YANG Haoran,LI Hui,AI Xiaoxue,et al.3D multi-object tracking network based on 3D volume information interaction between image and point cloud [J].Control and Decision,2024,39(12):4127 -4135.
[17]NABATI R,QI H R.CenterFusion:Center-based radar and camera fusion for 3D object detection [C]//Waikoloa:2021 IEEE Winter Conference on Applications of Computer Vision (WACV ),2021:1526 -1535.
[18]CAESAR H,BANKITI V,LANG A H,et al.NuScenes:A multimodal dataset for autonomous driving [C]//Seattle:2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR ),2020:11621 -11631.
[19]WENG X,WANG J,HELD D,et al.AB3DMOT:A baseline for 3D multi-object tracking and new evaluation metrics[J].arXiv preprint arXiv,2020:2008.08063.
[20]ZHOU X Y,KOLTUN V,KRÄHENBÜHL P.Tracking objects as points [C]//Cham:Computer Vision – ECCV 2020.Springer International Publishing,2020:474-490.
[21]CHAABANE M,ZHANG P,BEVERIDGE J R,et al.Deft:Detection embeddings for tracking [J].arXiv preprint arXiv,2021:2102.02267.
[22]BENBARKA N,SCHRODER J,ZELL A.Score refinement for confidence-based 3D multi-object tracking [C]//Prague:2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS ),2021:11315 -11321.
[23]KIM A,OŠEP A,LEAL-TAIXÉ L.EagerMOT:3D multi-object tracking via sensor fusion [C]//Xi’an：2021 IEEE International conference on Robotics and Automation (ICRA ),2021:11315 -11321.

Download

Share

COinS