Vehicle Tracking of Information Fusion for Millimeter-wave Radar and Vision Sensor

doi:10.3969/j.issn.1004-132X.2021.18.006

Abstract

Abstract: In order to improve accuracy of vehicle forward collision prevention warning system on road environment perception, a vehicle tracking method of information fusion for millimeter-wave radar and vision sensor was proposed. An algorithm to eliminate radar jamming targets was proposed to reduce processing time of jamming targets. A symmetric detection algorithm was proposed to detect radar target ROI (region of interest) symmetrically and reduce lateral position errors of radar target ROI. In order to improve the tracking accuracy, a KCF-KF combined filtering algorithm was proposed to track and fuse vehicles. Actual vehicle tests show that the method may effectively track vehicle position information, and the tracking accuracy of X and Y coordinates in pixel coordinate system is more than 97.34% and 95.19% respectively.

Key words: millimeter-wave radar, vision sensor, information fusion, vehicle tracking

摘要： 为提高车辆前向防碰撞预警系统对前方道路环境感知的准确性，提出一种毫米波雷达与视觉传感器信息融合的车辆跟踪方法。提出的剔除雷达干扰目标算法缩短了对干扰目标的处理时间；提出的对称检测算法可对雷达目标兴趣区域进行对称检测，减小雷达目标兴趣区域的横向位置误差；提出的KCF-KF组合滤波算法可提高跟踪车辆的精度。实车试验表明，该方法可有效跟踪车辆位置信息，像素坐标系下的X、Y坐标跟踪准确率分别超过97.34%与95.19%。

关键词: 毫米波雷达, 视觉传感器, 信息融合, 车辆跟踪

CLC Number:

U121

HU Yanping, LIU Fei, WEI Zhenya, ZHAO Linfeng. Vehicle Tracking of Information Fusion for Millimeter-wave Radar and Vision Sensor[J]. China Mechanical Engineering, 2021, 32(18): 2181-2188.

胡延平, 刘菲, 魏振亚, 赵林峰. 毫米波雷达与视觉传感器信息融合的车辆跟踪[J]. 中国机械工程, 2021, 32(18): 2181-2188.

References

［1］林荣团. 高速公路尾随相撞事故及预防技术研究［D］.西安：长安大学,2014.
LIN Rongtuan. Research on Tail-in Collision on Expressway and Prevention Technology［D］. Xian:Changan University, 2014.
［2］屠大维.用于车辆防撞控制的行车环境传感研究［J］.中国机械工程,1999，10(6):109-111.
TU Dawei. Research on Driving Environment Sensing for Vehicle Anti-collision Control［J］. China Mechanical Engineering, 1999 ,10(6):109-111.
［3］柯振宇. 基于毫米波雷达的车辆纵向碰撞预警系统设计［D］. 武汉：武汉理工大学，2014.
KE Zhenyu. Design of Vehicle Longitudinal Collision Early Warning System Based on Millimeter-wave Radar［D］. Wuhan:Wuhan University of Technology, 2014.
［4］丁亚强. 基于毫米波雷达的车辆纵向防碰撞系统研究［D］. 镇江：江苏大学，2018.
DING Yaqiang. Research on Vehicle Longitudinal Anti-collision System Based on Millimeter-wave Radar［D］. Zhenjiang:Jiangsu University, 2018.
［5］UMAR R, ABDULHADI M, SHOAIB M, et al. Design, Development and Experimental Validation of Multi-target Tracking Framework for Passive Radar［C］∥2019 IEEE Radar Conference. Boston, 2019:1-6.
［6］潘杰,师黎.车载雷达防追尾预警系统中的目标跟踪研究［J］.计算机工程与应用,2010,46(22):245-248.
PAN Jie, SHI Li. Research on Target Tracking in Vehicle-mounted Radar Early Warning System for Rear-end Collision［J］. Computer Engineering and Application, 2010, 46(22):245-248.
［7］WANG X, XU L, SUN H, et al. Bionic Vision Inspired On-road Obstacle Detection and Tracking Using Radar and Visual Information［C］∥17th International IEEE Conference on Intelligent Transportation Systems. Qingdao, 2014:39-44.
［8］ALENCAR F A R, ROSERO L A, FILHO C M, et al. Fast Metric Tracking by Detection System:Radar Blob and Camera Fusion［C］∥12th Latin American Robotics Symposium and 3rd Brazilian Symposium on Robotics (LARS-SBR). Uberlandia, 2015:120-125.
［9］HAN S, WANG X, XU L, et al. Frontal Object Perception for Intelligent Vehicles Based on Radar and Camera Fusion［C］∥35th Chinese Control Conference. Chengdu, 2016:4003-4008.
［10］KIM J, HAN D S, SENOUCI B. Radar and Vision Sensor Fusion for Object Detection in Autonomous Vehicle Surroundings［C］∥Tenth International Conference on Ubiquitous and Future Networks. Prague, 2018:76-78.
［11］谭力凡. 机器视觉与毫米波雷达融合的前方车辆检测方法研究［D］. 长沙：湖南大学,2018.
TAN Lifan. Research on Forward Vehicle Detection Method integrating Machine Vision and Millimeter-wave Radar［D］. Changsha:Hunan University,2018.
［12］OH J, KIM K S, PARK M, et al. A Comparative Study on Camera-Radar Calibration Methods［C］∥15th International Conference on Control, Automation, Robotics and Vision (ICARCV). Singapore, 2018:1057-1062.
［13］HENRIQUES J F, CASEIRO R, MARTINS P, et al. High-speed Tracking with Kernelized Correlation Filters［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014, 37(3):583-596.

[1]	ZHOU Xiaochun, LIANG Jun, CHEN Long, WANG Yafei, GONG Jinfeng. Intelligent Connected Vehicle PnP Networking Model and Decision Fusion Algorithm [J]. China Mechanical Engineering, 2021, 32(16): 1983-1993.
[2]	JIANG Wuhua1;XIN Xin1;CHEN Wuwei1;XIE Youhao2. Parking Line Parking Slot Recognition and Decision Planning of Automatic Parking Systems Based on Information Fusion [J]. China Mechanical Engineering, 2020, 31(10): 1190-1196.
[3]	ZHANG Weiwei1;MI Zeyang1;XIAO Lingyun2;QIAN Yubin1. Driver Yawning Detection Based on Deep Convolutional Network and Tracking with Online Learning [J]. China Mechanical Engineering, 2019, 30(08): 902-911.
[4]	Zhang Qiang, Wang Haijian, Li Liying, Liu Zhiheng. Online Monitoring of Shearer's Pick Wear Based on ANFIS Fuzzy Information Fusion [J]. China Mechanical Engineering, 2016, 27(19): 2607-2614.
[5]	Zhang Qiang, Wang Haijian, Li Liying , Wen Xuezhen , Nguyen Viet Tuyen, . Failure Diagnosis of Shearer Picks Based on Information Fusion from Multi Sensors [J]. China Mechanical Engineering, 2016, 27(17): 2334-2340.
[6]	Xia Xintao, Zhu Wenhuan, Chen Shizhong. Adjustment Method for Machining Errors of Machine Tool Based on Poor Information Fusion Technology [J]. China Mechanical Engineering, 2016, 27(13): 1802-1809.
[7]	Zhang Qiang, Wang Haijian, Jing Wang, Mao Jun, Yuan Zhi, Hu Denggao. Shearer's Coal-rock Recognition System Based on Fuzzy Neural Network Information Fusion [J]. China Mechanical Engineering, 2016, 27(02): 201-208.
[8]	CHEN Tian-Fan-1, 2, GAO Cheng-Hui-1, HE Bing-Wei-1. Research on Point Cloud Registration about Sensor from Different View Points Based on Surface Fit [J]. China Mechanical Engineering, 2012, 23(24): 2968-2971.
[9]	JIANG Mo-Lu, LIU Sai-Yuan. Fault Diagnosis Approach Study of Bayesian Networks Based on Multi-characteristic Information Fusion [J]. China Mechanical Engineering, 2010, 21(8): 940-945,967.
[10]	LIU Jian, TUN Xiong-Chi, JI Shi-Ming. Study on Oil Quality Evaluation Method and Its Implementation Based on Multi-information Fusion [J]. China Mechanical Engineering, 2010, 21(21): 2614-2618.
[11]	Wang Tanbin;Chen Wuwei;Jiao Jun;Wang Minglei. Study on Navigation of Intelligent Vehicles Based on Multi-sensor Fusion [J]. J4, 2009, 20(11): 0-1385.
[12]	Yue Jianfeng;Zhang Cuixuan;Li Liangyu . MIG Welding Robot Welding Quality Control Based on Multi-information Fusion [J]. J4, 2009, 20(09): 0-1016.
[13]	Ding Chengjun;Duan Ping;Sui Bailong;Zhang Minglu. Research on Orientation of Mobile Manipulator  End-effector Based on Multi-Source Information Fusion  [J]. J4, 2009, 20(08): 0-1007.
[14]	Rao Hong;Fu Mingfu;Xie Mingxiang;Yang Guotai. Research on the Equipment Fault Diagnosis on the Basis of Decision Level Information Fusion [J]. J4, 2009, 20(04): 0-388.
[15]	Zheng Changsong;Ma Biao;Sun Xianlin;Ju Yinfang. Fault Diagnosis on Multi-technique Oil Analysis Information Fusion Based on D-S Theory [J]. J4, 2008, 19(9): 0-1054.