吉林大学学报(工学版) ›› 2024, Vol. 54 ›› Issue (7): 2104-2114.doi: 10.13229/j.cnki.jdxbgxb.20221174

• 通信与控制工程 • 上一篇    

基于路侧毫米波雷达的群体车辆目标识别与跟踪

李立1(),吴晓强1,杨文臣2,3,周瑞杰1,汪贵平1()   

  1. 1.长安大学 电子与控制工程学院，西安 710064
    2.云南省交通规划设计研究院有限公司 陆地交通气象灾害防治技术国家工程实验室，昆明 650200
    3.云南省数字交通重点实验室，昆明 650103
  • 收稿日期:2022-09-11 出版日期:2024-07-01 发布日期:2024-08-05
  • 通讯作者: 汪贵平 E-mail:lili@chd.edu.cn;gpwang@chd.edu.cn
  • 作者简介:李立（1985-），男，副教授，博士.研究方向：智能交通. E-mail： lili@chd.edu.cn
  • 基金资助:
    陕西省自然科学基础研究计划项目(2023-JC-YB-507);国家自然科学基金项目(71901040);云南交投科技研发项目(YCIC-YF-2002-06);云南省数字交通实验室建设项目(202205AG070008)

Target recognition and tracking of group vehicles based on roadside millimeter-wave radar

Li LI1(),Xiao-qiang WU1,Wen-chen YANG2,3,Rui-jie ZHOU1,Gui-ping WANG1()   

  1. 1.School of Electronic and Control Engineering，Chang'an University，Xi'an 710064，China
    2.National Engineering Laboratory for Surface Transportation Weather Impacts Prevention，Broadvision Engineering Consultants Co. ，Ltd，Kunming 650200，China
    3.Yunnan Key Laboratory of Digital Communications，Kunming 650103，China
  • Received:2022-09-11 Online:2024-07-01 Published:2024-08-05
  • Contact: Gui-ping WANG E-mail:lili@chd.edu.cn;gpwang@chd.edu.cn

RICH HTML

 2   

PDF (PC)

157

摘要：

为了提升道路交通流检测精度，本文提出了一种基于路侧毫米波雷达的群体车辆识别与跟踪方法。首先，基于预处理后的城市多车道主干路交通流毫米波雷达检测数据，提出了一种基于高斯核距离的带噪声密度空间聚类（DBSCAN）算法，实现对群体车辆所反射有效雷达信号的时空聚类；其次，提出了一种无迹卡尔曼滤波（UKF）和线性高斯混合概率假设密度（GMPHD）融合算法，以提升非线性运动群体车辆的跟踪精度；最后，在仿真和实际环境中进行算法测试，仿真结果验证了UK-GMPHD算法能够精准、稳定地跟踪非线性运动车辆。实测结果表明：基于核距离的DBSCAN算法能够有效改善经典算法特征向量的调参问题；与GMPHD算法对比，UK-GMPHD算法对目标跟踪的距离、速度和角度均方根误差分别减少了21.03%、23.41%和20.67%。

关键词: 智能交通, 毫米波雷达, 群体车辆, 目标识别, 车辆跟踪, 滤波, 高斯混合概率假设密度

Abstract:

A method of group vehicle recognition and tracking based on roadside millimetre-wave radar was proposed to improve roadway traffic detection accuracy. Based on pre-processed detection data of millimetre-wave radar on multi-lane traffic flow in an urban arterial road， a Gaussian kernel-distance based spatial clustering algorithm with noise density （DBSCAN） was proposed to conduct spatio-temporal clustering of effective radar signals reflected by group vehicles. Then， a fusion algorithm of unscented Kalman filter （UKF） and linear Gaussian mixture probability hypothesis density （GMPHD） was proposed to improve tracking accuracy of group vehicles which move nonlinearly on the road. The algorithms were tested in simulation and onsite environment. Simulation results verified that the UK-GMPHD algorithm can accurately and stably track nonlinear moving vehicles. Results of onsite test showed that the kernel-distance based DBSCAN algorithm can solve the problem of classical algorithm effectively that the parameter tuning of feature vector was difficult to adjust. The UK-GMPHD algorithm reduced the root mean square error of target tracking in term of target distance， velocity and angle by 21.03%， 23.41% and 20.67% in comparison with GMPHD algorithm.

Key words: intelligent transportation, millimeter wave radar, group vehicles, target recognition, vehicle tracking, filter, Gaussian mixture probability hypothesis density

中图分类号: 

  • TN953

表1

毫米波雷达参数"

参数短距长距
距离测量/m0.2~700.2~250
距离精度/m±0.1±0.4
测速范围/（km·h-1）-400~+200（-为远离，+为接近）-400~+200（-为远离，+为接近）
速度精度/（km·h-1）±0.1±0.1
方位角/（°）-60~+60-9~+9

图1

数据采集示意图"

表2

毫米波雷达数据帧"

信号含义符号单位
目标编号ID—
纵向距离（X轴方向）Rxm
横向距离（Y轴方向）Rym
纵向速度（X轴方向）vxm/s
横向速度（Y轴方向）vym/s
目标反射截面SrcsdBm2

图2

目标运动参数频率直方图"

图3

UK-GMPHD算法流程"

图4

目标识别算法效果对比"

图5

不同目标检测概率下平均OSPA距离"

图6

目标跟踪仿真结果"

图7

目标跟踪性能对比"

表3

算法性能对比"

目标参数GMPHD算法UK-GMPHD算法误差减少量
距离4.536 m3.582 m21.03%
速度1.162 m/s0.89 m/s23.41%
角度1.432°1.136°20.67%

图8

行车场景、实测数据及车辆跟踪结果"

图9

GMPHD和UK-GMPHD算法对比图"

1 Jiang Q, Zhang L, Meng D. Target detection algorithm based on MMW radar and camera Fusion[C]∥ 2019 IEEE Intelligent Transportation Systems Conference (ITSC). Auckland, 2019: No.19211454.
2 Brodeski D, Bilik I, Giryes R. Deep radar detector[C]∥2019 IEEE Radar Conference, Boston, 2019: No.18993501.
3 Wang Z, Miao X, Huang Z, et al. Research of target detection and classification techniques using millimeter-wave radar and vision sensors[J]. Remote Sensing, 2021, 13(6): 1064-1086.
4 Cao L, Wang T, Wang D, et al. Lane determination of vehicles based on a novel clustering algorithm for intelligent traffic monitoring[J]. IEEE Access, 2020(8): 63004-63017.
5 张钰, 林雨田, 高利, 等. 基于毫米波雷达的静态目标识别与跟踪[C]∥2021中国汽车工程学会年会论文集. 北京:机械工业出版社, 2021: 96-102.
Zhang Yu, Lin Yu-tian, Gao Li, et al. Static target recognition and tracking based on Millimeter Wave Radar[C]∥ 2021 the Annual Meeting of China Society of Automotive Engineering. Beijing: China Machine Press, 2021: 96-102.
6 Ikram M, Ali M. 3D object tracking in millimeter-wave radar for advanced driver assistance systems[C]∥ 2013 IEEE Global Conference on Signal and Information Processing, Austin, 2013: 723-726.
7 Cui H, Wu J, Zhang J. 3D detection and tracking for on-road vehicles with a monovision camera and dual low-cost 4D mm wave radars[C]∥ 2021 IEEE International Intelligent Transportation Systems Conference, Indianapolis, 2021: 2931-2937.
8 Ma J, Tian Z, Li Y, et al. Vehicle tracking method in polar coordinate system based on radar and monocular camera[C]∥ 2020 Chinese Control and Decision Conference(CCDC), Hefei, 2020: 93-98.
9 Huang C, Wu X. Cooperative vehicle tracking using particle filter integrated with interacting multiple models[C]∥ 2019 IEEE International Conference on Communications, Shanghai, 2019: No.18866635.
10 Liu H, Li N, Guan D, et al. Data feature analysis of non-scanning multi target millimeter-wave radar in traffic flow detection applications[J]. Sensors, 2018, 18: 2756-2775.
11 Belgiovane D, Chen C, Ming C, et al. 77 GHz radar scattering properties of pedestrians[C]∥ 2014 IEEE Radar Conference, Cincinnati, 2014: 735-738.
12 Han X, Armenakis C, Jadidi M. DBSCAN optimization for improving marine trajectory clustering and anomaly detection[J]. The International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences, 2020, 43: 455-461.
13 Jian L, Yu W, Yan B. Memory effect in DBSCAN algorithm[C]∥ 2009 4th International Conference on Computer Science & Education, Nanning, 2009: 31-36.
14 Guo L, Ge P, He D, et al. Multi-vehicle detection and tracking based on Kalman filter and data association[C]∥ International Conference on Intelligent Robotics and Applications, Shenyang, 2019: 439-449.
15 Shi K, Shi Z, Yang C, et al. Road-map aided GM-PHD filter for multivehicle tracking with automotive radar[J]. IEEE Transactions on Industrial Informatics, 2022, 18(1): 97-108.
16 Liu H, Zhang H, Mertz C. DeepDA: LSTM-based deep data association network for multi-targets tracking in clutter[C]∥ The 22nd International Conference on Information Fusion, Ottawa, 2019: No.19411161.
17 Guo F H, Xu Y. Vehicle analysis system based on DeepSORT and YOLOv5[C]∥ 2022 3rd International Conference on Computer Vision, Image and Deep Learning & International Conference on Computer Engineering and Applications (CVIDL & ICCEA), Changchun, 2022: 175-179.
[1] 樊学平,刘月飞. 基于改进高斯混合粒子滤波新算法的桥梁极值应力动态预测[J]. 吉林大学学报(工学版), 2024, 54(4): 1038-1044.
[2] 杨秀建,贾晓寒,张生斌. 考虑汽车队列动态特性的混合交通流特性[J]. 吉林大学学报(工学版), 2024, 54(4): 947-958.
[3] 张海龙,张萌,张亚州,王杰,冶鑫晨,王万琼,李嘉,杜旭,张婷. 基于临界采样多相滤波器组的宽带信号信道化[J]. 吉林大学学报(工学版), 2023, 53(8): 2388-2394.
[4] 王小艺,刘迪一,于家斌,何卓昀,赵峙尧. 复杂风场环境下的多旋翼无人机编队故障检测方法[J]. 吉林大学学报(工学版), 2023, 53(3): 823-831.
[5] 樊敏,宋世军. 基于多源大数据分析的图像特征智能识别模型[J]. 吉林大学学报(工学版), 2023, 53(2): 555-561.
[6] 高海龙,徐一博,侯德藻,王雪松. 基于深度异步残差网络的路网短时交通流预测算法[J]. 吉林大学学报(工学版), 2023, 53(12): 3458-3464.
[7] 马为駽,张䶮,马传香,朱飒. 不同光照条件下含噪遥感图像边缘检测算法[J]. 吉林大学学报(工学版), 2023, 53(1): 241-247.
[8] 刘洲洲,孙传新,王晓柱,张杨梅. 采用VGG19和低通滤波的红外与微光图像融合方法[J]. 吉林大学学报(工学版), 2023, 53(1): 255-262.
[9] 马彦,郭则宣. 基于改进BPNN⁃MPF算法的锂离子电池SoE估计[J]. 吉林大学学报(工学版), 2023, 53(1): 263-272.
[10] 马永杰,陈敏. 基于卡尔曼滤波预测策略的动态多目标优化算法[J]. 吉林大学学报(工学版), 2022, 52(6): 1442-1458.
[11] 高明华,杨璨. 基于改进卷积神经网络的交通目标检测方法[J]. 吉林大学学报(工学版), 2022, 52(6): 1353-1361.
[12] 李向军,涂洁莹,赵志宾. 基于多尺度融合卷积神经网络的熔解曲线有效性分类[J]. 吉林大学学报(工学版), 2022, 52(3): 633-639.
[13] 李茂月,刘硕,田帅,肖桂风. 薄壁件铣削加工颤振的图像特征提取与识别[J]. 吉林大学学报(工学版), 2022, 52(2): 425-432.
[14] 张友俊,程顺延. 基于卷积神经网络的微带滤波器结构参数估计[J]. 吉林大学学报(工学版), 2022, 52(12): 3022-3028.
[15] 李文航,倪涛,赵丁选,张泮虹,师小波. 基于集合卡尔曼滤波的高机动救援车辆主动悬挂控制方法[J]. 吉林大学学报(工学版), 2022, 52(12): 2816-2826.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
版权所有 © 《吉林大学学报(工学版)》编辑部
地址：长春市人民大街5988号　电话：+86-431-85095297　传真：+86-431-85094074　E-mail: xbgxb@jlu.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发