高级搜索

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

水平集高斯过程的非星凸形扩展目标跟踪算法

陈辉 曾文爱 连峰 韩崇昭

陈辉, 曾文爱, 连峰, 韩崇昭. 水平集高斯过程的非星凸形扩展目标跟踪算法[J]. 电子与信息学报. doi: 10.11999/JEIT220997
引用本文: 陈辉, 曾文爱, 连峰, 韩崇昭. 水平集高斯过程的非星凸形扩展目标跟踪算法[J]. 电子与信息学报. doi: 10.11999/JEIT220997
CHEN Hui, ZENG Wenai, LIAN Feng, HAN Chongzhao. Non-Star-Convex Extended Target Tracking Algorithm for Level-Set Gaussian Process[J]. Journal of Electronics & Information Technology. doi: 10.11999/JEIT220997
Citation: CHEN Hui, ZENG Wenai, LIAN Feng, HAN Chongzhao. Non-Star-Convex Extended Target Tracking Algorithm for Level-Set Gaussian Process[J]. Journal of Electronics & Information Technology. doi: 10.11999/JEIT220997

水平集高斯过程的非星凸形扩展目标跟踪算法

doi: 10.11999/JEIT220997
基金项目: 国家自然科学基金(62163023, 61873116) , 甘肃省教育厅产业支撑计划项目(2021CYZC-02), 甘肃省科技计划项目(20JR10RA184)
详细信息
    作者简介:

    陈辉:陈 辉男,教授,博士生导师,研究方向为目标跟踪和传感器管理

    曾文爱:女,硕士生,研究方向为扩展目标跟踪

    连峰:男,教授,博士生导师,研究方向为目标跟踪、信息融合与传感器管理

    韩崇昭:男,教授,博士生导师,研究方向为多源信息融合、随机控制与自适应控制、非线性频谱分析等

  • 中图分类号: TP274

Non-Star-Convex Extended Target Tracking Algorithm for Level-Set Gaussian Process

Funds: The National Natural Science Foundation of China (62163023, 61873116), The Industrial Support Project of Education Department of Gansu Province (2021CYZC-02), The Science and Technology Program of Gansu Province (20JR10RA184)
  • 摘要: 针对复杂环境下的非星凸形不规则形状扩展目标跟踪问题,该文提出基于能量泛函的水平集高斯过程扩展目标跟踪算法。首先,利用水平集随机超曲面模型(Level-Set RHM)通过多边形方法对形状内部进行建模。然后,用高斯过程(GP)学习Level-Set建模输入与输出的非线性映射关系,以求得边界函数最大值,并进一步推导Level-Set与GP相融合的非线性量测方程。在最优非线性滤波的框架下,最终推导得到水平集高斯过程(Level-Set GP)算法,并利用面积差作为不规则形状扩展目标形状估计的评价指标。仿真实验表明了所提算法对非星凸形不规则形状扩展目标形状估计的有效性。
  • 图  1  不规则扩展目标形状

    图  2  非星凸形扩展目标跟踪

    图  3  求边界形状函数最大值过程

    图  4  不同形状的跟踪效果

    图  5  不同形状的面积误差

    图  6  不同噪声下的面积误差

    图  7  动态目标跟踪

    图  8  不同时刻动态目标的面积误差

    图  9  群目标跟踪

    图  10  群目标面积误差

    算法1 Level-Set GP模型算法部分伪码
     输入:${\boldsymbol{x} }_{ { {k} } - 1|{ {k} } - 1}^{ {\rm{f} } } , { {\boldsymbol{F} }^{\rm{f} } }, {{\boldsymbol{Q}}_{ {k} } }, {\boldsymbol{x}}_0^{{\rm{p}}} , {{\boldsymbol{P}}_{ { {k} } - 1|{ {k} } - 1} }, {{\boldsymbol{C}}_{ { {k} } - 1|{ {k} } - 1} }, {\boldsymbol{F}}_{ {k} }^{{\rm{p}}} , {\boldsymbol{Q}}_{ {k} }^{{\rm{p}}}$
     步骤1 预测
     for$ {{ }}k = 1{{ : }}N $
       ${\boldsymbol{x}}_{ { {k} }|{ {k} } - 1}^{\rm{{f}}} = {{\boldsymbol{F}}^{{\rm{f}}} }{\boldsymbol{x}}_{ { {k} } - 1|{ {k} } - 1}^{f}$;
       ${{\boldsymbol{P}}_{ { {k} }|{ {k} } - 1} } = {{\boldsymbol{F}}^{\rm{f}}}{{\boldsymbol{P}}_{ { {k} } - 1|{ {k} } - 1} }{({{\boldsymbol{F}}^{\rm{f}}})^{{\rm{T}}} } + {{\boldsymbol{Q}}_{ {k} } }$;
       根据式(10)—(11),计算得到$ {{k}} $时刻扩展形状参数的预测值;
       ${{\boldsymbol{C}}_{ { {k} }|{ {k} } - 1} } = {\boldsymbol{F}}_{ {k} }^{{\rm{p}}} {{\boldsymbol{C}}_{ { {k} } - 1|{ {k} } - 1} }{({\boldsymbol{F}}_{ {k} }^{{\rm{p}}} )^{{\rm{T}}} } + {\boldsymbol{Q}}_{ {k} }^{{\rm{p}}}$;
     end for
     步骤2 更新
     for$ k = 1:N $
       for$ {{ }}j = 1:num $
         根据式(43)计算$ k $时刻边界形状函数最大值;
         计算伪量测方程传递后的样本点$ h_{k,j}^* $;
         根据式(47)—(52),更新扩展形状参数${\boldsymbol{x}}_{ {k} }^{{\rm{p}}}$和协方差${{\boldsymbol{C}}_{ { {k} }|{ {k} } } }$;
       end for
     end for
     输出:${\boldsymbol{x}}_{ {k} }^{{\rm{p}}} , {{\boldsymbol{C}}_{ { {k} }|{ {k} } } }$
    下载: 导出CSV
    算法2 面积差算法
     输入:$ {{x,}}{{y,}}{{X,}}{{Y}} $
     ${ {\rm{poly} } } 1 = { {\rm{polyshape} } } ({{x} },{{y} })$;
     ${{\rm{poly}}} 2 = {{\rm{polyshape}}} ({{X} },{{Y} })$;
     ${{\rm{intpoly}}} = {{\rm{intersect}}} ({{\rm{poly}}} 1,{{\rm{poly}}} 2)$;
     ${{\rm{intarea}}} = {{\rm{polyarea}}} ({{\rm{intpoly}}} (:,1),{{\rm{intpoly}}} (:,2))$;
     ${{\rm{unipoly}}} = { {\rm{union} } } ({ {\rm{poly} } } 1,{ {\rm{poly} } } 2)$;
     ${{\rm{uniarea}}} = {{\rm{polyarea}}} ({{\rm{unipoly}}} (:,1),{{\rm{unipoly}}} (:,2))$;
     $ {trueshape} = {polyarea} ({\text{X,Y}}) $;
     根据式(54), 计算面积误差$\epsilon$。
     输出:$\epsilon$
    下载: 导出CSV
  • [1] TUNCER B and ÖZKAN E. Random matrix based extended target tracking with orientation: A new model and inference[J]. IEEE Transactions on Signal Processing, 2021, 69: 1910–1923. doi: 10.1109/TSP.2021.3065136
    [2] GRANSTRÖM K, BAUM M, and REUTER S. Extended object tracking: Introduction, overview, and applications[J]. Journal of Advances in Information Fusion, 2017, 12(2): 139–174.
    [3] YANG Shishan, TEICH F, and BAUM M. Network flow labeling for extended target tracking PHD filters[J]. IEEE Transactions on Industrial Informatics, 2019, 15(7): 4164–4171. doi: 10.1109/TII.2019.2898992
    [4] BARTLETT N J, RENTON C, and WILLS A G. A closed-form prediction update for extended target tracking using random matrices[J]. IEEE Transactions on Signal Processing, 2020, 68: 2404–2418. doi: 10.1109/TSP.2020.2984390
    [5] GRANSTRÖM K and BRAMSTÅNG J. Bayesian smoothing for the extended object random matrix model[J]. IEEE Transactions on Signal Processing, 2019, 67(14): 3732–3742. doi: 10.1109/TSP.2019.2920471
    [6] AFTAB W, HOSTETTLER R, DE FREITAS A, et al. Spatio-temporal Gaussian process models for extended and group object tracking with irregular shapes[J]. IEEE Transactions on Vehicular Technology, 2019, 68(3): 2137–2151. doi: 10.1109/TVT.2019.2891006
    [7] DANIYAN A, LAMBOTHARAN S, DELIGIANNIS A, et al. Bayesian multiple extended target tracking using labeled random finite sets and splines[J]. IEEE Transactions on Signal Processing, 2018, 66(22): 6076–6091. doi: 10.1109/TSP.2018.2873537
    [8] AKBARI B and ZHU Haibin. Tracking dependent extended targets using multi-output spatiotemporal Gaussian processes[J]. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(10): 18301–18314. doi: 10.1109/TITS.2022.3154926
    [9] LU Zhejun, HU Weidong, LIU Yongxiang, et al. Seamless group target tracking using random finite sets[J]. Signal Processing, 2020, 176: 107683. doi: 10.1016/j.sigpro.2020.107683
    [10] 汪云, 胡国平, 甘林海. 基于多模型GGIW-CPHD滤波的群目标跟踪算法[J]. 华中科技大学学报:自然科学版, 2017, 45(2): 89–94. doi: 10.13245/j.hust.170217

    WANG Yun, HU Guoping, and GAN Linhai. Group targets tracking algorithm using a multiple models Gaussian inverse Wishart CPHD filter[J]. Journal of Huazhong University of Science and Technology:Natural Science Edition, 2017, 45(2): 89–94. doi: 10.13245/j.hust.170217
    [11] 陈辉, 杜金瑞, 韩崇昭. 基于星凸形随机超曲面模型多扩展目标多伯努利滤波器[J]. 自动化学报, 2020, 46(5): 909–922. doi: 10.16383/j.aas.c180130

    CHEN Hui, DU Jinrui, and HAN Chongzhao. A multiple extended target multi-Bernouli filter based on star-convex random hypersurface model[J]. Acta Automatica Sinica, 2020, 46(5): 909–922. doi: 10.16383/j.aas.c180130
    [12] LIU Ben, THARMARASA R, JASSEMI R, et al. Extended target tracking with multipath detections, terrain-constrained motion model and clutter[J]. IEEE Transactions on Intelligent Transportation Systems, 2021, 22(11): 7056–7072. doi: 10.1109/TITS.2020.3001174
    [13] ZHU Hongyan, HAN Chongzhao, and LI Chen. An extended target tracking method with random finite set observations[C]. 14th International Conference on Information Fusion, Chicago, USA, 2011: 1–6.
    [14] YANG Shishan and BAUM M. Tracking the orientation and axes lengths of an elliptical extended object[J]. IEEE Transactions on Signal Processing, 2019, 67(18): 4720–4729. doi: 10.1109/TSP.2019.2929462
    [15] ALQADERI H, GOVAERS F, and SCHULZ R. Spacial elliptical model for extended target tracking using laser measurements[C]. 2019 Sensor Data Fusion: Trends, Solutions, Applications, Bonn, Germany, 2019: 1–6.
    [16] 李翠芸, 林锦鹏, 姬红兵. 一种基于椭圆RHM的扩展目标Gamma高斯混合CPHD滤波器[J]. 控制与决策, 2015, 30(9): 1551–1558. doi: 10.13195/j.kzyjc.2014.0877

    LI Cuiyun, LIN Jinpeng, and JI Hongbing. A Gamma Gaussian-mixture CPHD filter based on ellipse random hypersurface models for extended targets[J]. Control and Decision, 2015, 30(9): 1551–1558. doi: 10.13195/j.kzyjc.2014.0877
    [17] FOWDUR J S, BAUM M, and HEYMANN F. An elliptical principal axes-based model for extended target tracking with marine radar data[C]. 2021 IEEE 24th International Conference on Information Fusion, Sun City, South Africa, 2021: 1–8.
    [18] BAUM M, NOACK B, and HANEBECK U D. Extended object and group tracking with elliptic random hypersurface models[C]. 2010 13th International Conference on Information Fusion, Edinburgh, UK, 2010: 1–8.
    [19] KOCH J W. Bayesian approach to extended object and cluster tracking using random matrices[J]. IEEE Transactions on Aerospace and Electronic Systems, 2008, 44(3): 1042–1059. doi: 10.1109/TAES.2008.4655362
    [20] LAN Jian and LI Xiaorong. Tracking of extended object or target group using random matrix – part II: Irregular object[C]. 2012 15th International Conference on Information Fusion, Singapore, 2012: 2185–2192.
    [21] LAN Jian and LI Xiaorong. Tracking of maneuvering non-ellipsoidal extended object or target group using random matrix[J]. IEEE Transactions on Signal Processing, 2014, 62(9): 2450–2463. doi: 10.1109/TSP.2014.2309561
    [22] BAUM M and HANEBECK U D. Extended object tracking with random hypersurface models[J]. IEEE Transactions on Aerospace and Electronic Systems, 2014, 50(1): 149–159. doi: 10.1109/TAES.2013.120107
    [23] WAHLSTRÖM N and ÖZKAN E. Extended target tracking using Gaussian processes[J]. IEEE Transactions on Signal Processing, 2015, 63(16): 4165–4178. doi: 10.1109/TSP.2015.2424194
    [24] ZEA A, FAION F, BAUM M, et al. Level-set random hypersurface models for tracking nonconvex extended objects[J]. IEEE Transactions on Aerospace and Electronic Systems, 2016, 52(6): 2990–3007. doi: 10.1109/TAES.2016.130704
    [25] JIDESH P and BALAJI B. Adaptive non-local level-set model for despeckling and deblurring of synthetic aperture radar imagery[J]. International Journal of Remote Sensing, 2018, 39(20): 6540–6556. doi: 10.1080/01431161.2018.1460510
    [26] ANDREASEN C S, ELINGAARD M O, and AAGE N. Level set topology and shape optimization by density methods using cut elements with length scale control[J]. Structural and Multidisciplinary Optimization, 2020, 62(2): 685–707. doi: 10.1007/s00158-020-02527-1
    [27] GUO Yunfei, LI Yong, THARMARASA R, et al. GP-PDA filter for extended target tracking with measurement origin uncertainty[J]. IEEE Transactions on Aerospace and Electronic Systems, 2019, 55(4): 1725–1742. doi: 10.1109/TAES.2018.2875555
    [28] KUMRU M and ÖZKAN E. 3D extended object tracking using recursive Gaussian processes[C]. 2018 21st International Conference on Information Fusion, Cambridge, UK, 2018: 1–8.
    [29] 陈辉, 李国财, 韩崇昭, 等. 高斯过程回归模型多扩展目标多伯努利滤波器[J]. 控制理论与应用, 2020, 37(9): 1931–1943. doi: 10.7641/CTA.2020.90978

    CHEN Hui, LI Guocai, HAN Chongzhao, et al. A multiple extended target multi-Bernouli filter based on Gaussian process regression model[J]. Control Theory &Applications, 2020, 37(9): 1931–1943. doi: 10.7641/CTA.2020.90978
    [30] NAUJOKS B, BURGER P, and WUENSCHE H J. Fast 3D extended target tracking using NURBS surfaces[C]. 2019 IEEE Intelligent Transportation Systems Conference (ITSC), Auckland, New Zealand, 2019: 1104–1109.
    [31] THORMANN K, BAUM M, and HONER J. Extended target tracking using Gaussian processes with high-resolution automotive radar[C]. 2018 21st International Conference on Information Fusion, Cambridge, UK, 2018: 1764–1770.
  • 加载中
图(10) / 表(2)
计量
  • 文章访问数:  56
  • HTML全文浏览量:  23
  • PDF下载量:  12
  • 被引次数: 0
出版历程
  • 收稿日期:  2023-01-11
  • 录用日期:  2023-01-11
  • 网络出版日期:  2023-01-14

目录

    /

    返回文章
    返回