计算机科学 ›› 2025, Vol. 52 ›› Issue (8): 154-161.doi: 10.11896/jsjkx.241100031

• 数据库&大数据&数据科学 • 上一篇    下一篇

基于运动特征的多目标航迹生成方法

张浩然, 王桂玲   

  1. 北方工业大学大规模流数据集成与分析技术北京市重点实验室 北京 100144
    北方工业大学信息学院 北京 100144
  • 收稿日期:2024-11-05 修回日期:2025-01-26 出版日期:2025-08-15 发布日期:2025-08-08
  • 通讯作者: 王桂玲(wangguiling@ncut.edu.cn)
  • 作者简介:(zhr000405@163.com)

Multi-target Trajectory Generation Method Based on Motion Features

ZHANG Haoran, WANG Guiling   

  1. Beijing Key Laboratory on Integration and Analysis of Large-scale Stream Data,North China University of Technology,Beijing 100144,China
    School of Information,North China University of Technology,Beijing 100144,China
  • Received:2024-11-05 Revised:2025-01-26 Online:2025-08-15 Published:2025-08-08
  • About author:ZHANG Haoran,born in 2000,postgraduate.His main research interest is Spatio-temporal data analysis and mi-ning.
    WANG Guiling,born in 1978,Ph.D,professor,is a member of CCF(No.17649M).Her main research interests include data integration,services computing and large-scale streaming.

摘要: 在空间跟踪船海上多目标跟踪场景中,目标船的航迹关联一直是严峻的挑战。由于海洋表面是一个高度动态的环境,海杂波的存在有很强的不规则性和随机性,使得探测到的目标点中夹杂着大量的不真实点。对此,提出了一种基于运动特征的多目标航迹生成方法,该方法包括预处理和航迹段关联两个关键环节。在预处理阶段,通过目标船数据的经纬度、速度和航向角的阈值剔除轨迹异常点,并采用基于B-spline的采样-分段-插值方法,增强目标轨迹的完整性、连续性和平滑性;在航迹段关联阶段,设计了一种结合运动特征和时间约束的多目标航迹关联策略。实际海域实验结果表明,该方法能够有效提高航迹生成的准确性和鲁棒性。

关键词: 雷达航迹关联, 航迹插值, 航迹生成, 运动特征, 多目标

Abstract: In the maritime multi-target tracking context of space tracking vessels,the trajectory correlation of target ships has remained a formidable challenge.Owing to the highly dynamic nature of the oceanic environment and the irregularity as well as randomness of sea clutter,the detected target points frequently encompass a multitude of false detections.This paper presents a motion-feature-based multi-target trajectory generation approach,which comprises two crucial stages:preprocessing and trajectory segment association.In the preprocessing stage,trajectory outliers are eliminated by imposing threshold constraints on latitude,longitude,speed,and heading angle,followed by a B-spline-based sampling-segmentation-interpolation method to enhance the completeness,continuity,and smoothness of the target trajectories.In the trajectory segment association stage,a multi-target tra-jectory association strategy is formulated,integrating motion features and temporal constraints.Experimental outcomes in real maritime scenarios illustrate that the proposed method substantially enhances the accuracy and robustness of trajectory generation.

Key words: Radar track correlation, Track interpolation, Track generation, Motion characterization, Multi-target

中图分类号: 

  • TP311
[1]LIU C,WANG Y J.Review of multi-target tracking technology for marine radar[J].Journal of Radars,2021,10(1):100-115.
[2]LU Q,WU L,CHEN Z,et al.A Review of Multi-source Trajectory Data Association for Marine Targets[J].Journal of Geo-information Science,2018,20(5):571-581.
[3]QIAO S J,HAN N,ZHU X W,et al.A Dynamic Trajectory Prediction Algorithm Based on Kalman Filter[J].Acta Elec-tronica Sinica,2018,46(2):418-423.
[4]LIU C,WEI J X,LI W H,et al.Research on improved adaptive Kalman filter in Beidou pseudorange single point positioning[J].Journal of Electronic Measurement and Instrumentation,2023,34(10):1-7.
[5]ODIC N,FAURE B,MAGNIER B.FORT:Fisheye Online Realtime Tracking with an Improved Kalman Filter[C]//2023 IEEE 25th International Workshop on Multimedia Signal Processing(MMSP).IEEE,2023:1-6.
[6]YANG S S,BAUM M.Extended Kalman filter for extended object tracking[C]//2017 IEEE International Conference on Acoustics,Speech and Signal Processing(ICASSP).2017:4386-4390.
[7]ZENG C,LI W.Application of Extended Kalman Filter fortracking high dynamic GPS signal[C]//2016 IEEE InternationalConference on Signal and Image Processing(ICSIP).2016:503-507.
[8]HUANG J.An Underwater Target Tracking Algorithm Based on Extended Kalman Filter[J].Mobile Information Systems,2023(1):9916531.
[9]TIAN F,GUO X,FU W.Target Tracking Algorithm Based on Adaptive Strong Tracking Extended Kalman Filter[J].Elec-tronics,2024,13(3):652.
[10]JULIER S J,UHLMANN J K.Unscented filtering and nonlinear estimation[C]//Proceedings of the IEEE.2004:401-422.
[11]CHEN B.An improved iterative traceless Kalman filtering algorithm[J].Computer Applications and Software,2019,36(10):274-278.
[12]ZHAO D J,PENG S S,XUE D,et al.Multi-Target Tracking Method Based on Improved Radar and Camera Data Association[R].SAE Technical Paper,2023.
[13]ZAN M E,ZHOU H,HAN D,et al.Survey of Particle Filter Target Tracking Algorithms[J].Computer Engineering and Applications,2019,55(5):8-17.
[14]SHEN M L,TANG J,HUANG D D,et al.Multi-target tracking method optimized by improved cuckoo search algorithm for particle filtering [J].Electronic Measurement Technology,2024,47(3):84-90.
[15]YANG B,JIANG T,DING Y K,et al.A correlation algorithm for trajectory discovery based on spatio-temporal distance metric[J].Technology of loT&AI,2022,54(5):14-19.
[16]XU Y S,DING C B,REN W J,et al.Multi-feature combination track-to-track association based on histogram statistics feature[J].Journal of Radars,2019,8(1):25-35.
[17]XU Z J,LI J C,CHEN Y F.Survey of track association of radar and AIS[C]//2017 2nd International Conference on Image,Vision and Computing(ICIVC).2017:960-964.
[18]GAO F,XIE X P,XIONG W.Trajectory association algorithm based on generalized absolute gray correlation[J].Radar Science and Technology,2016,14(6):642-647.
[19]CUI Y Q,HE Y,TANG T T,et al.A Deep Learning Track Correlation Method[J].Acta Electronica Sinica,2022,50(3):759-763.
[20]LI Y,ZHU S.Fast recognition algorithm for radar target track based on multilayer LSTM model[J].Radio Engineering,2023,53(2):325-332.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!