基于均值漂移和双层群结构模型的群目标GMPHD滤波
|
摘要
针对不可分辨群目标跟踪算法中群合并、交叉及分裂前后群目标数出现漏估及量测划分数多、计算量大两个问题,提出一种基于均值漂移(MS)和双层群结构(BGS)模型的群目标高斯混合概率假设密度(GMPHD)滤波算法.该算法采用MS进行量测划分,同时依据第2层群结构反馈回的群信息判断是否需要进行2次划分;然后,采用基于椭圆随机超曲面模型(RHM)的群目标GMPHD滤波进行预测更新和状态提取;最后,使用提取出的群目标状态进行第二层群结构更新,并将所得群信息反馈回量测划分步.仿真对比实验表明,所提出算法可获得更高的实时性,能够解决群目标合并、交叉及分裂前后群数目的漏估问题.
The unresolvable group target tracking algorithm occurs underestimation when the group targets merge, cross and split, and it also occurs excessive partition number and a large amount of calculation. Therefore, this paper proposes a group target Gaussian mixture probability hypothesis density(GMPHD) filtering algorithm based on mean shift(MS) and bilayer group structure(BGS) model. The algorithm uses MS to partition the measurements, at the same time, according to the feedback information of the second layer group structure, it is necessary to judge whether or not to partition the group measurements for second time. Then, the group target GMPHD filtering based on the ellipse random hypersurface model(RHM) is used to predict, update and extract the group target state. Finally, the second group structure is updated by using the extracted state of the group, and the obtained group information is fed back to the measurement partition step. Simulation experiments show that, the proposed algorithm not only has a higher real-time performance, but also solves the underestimation problem of group target number when the group targets merge, cross and split.
The unresolvable group target tracking algorithm occurs underestimation when the group targets merge, cross and split, and it also occurs excessive partition number and a large amount of calculation. Therefore, this paper proposes a group target Gaussian mixture probability hypothesis density(GMPHD) filtering algorithm based on mean shift(MS) and bilayer group structure(BGS) model. The algorithm uses MS to partition the measurements, at the same time, according to the feedback information of the second layer group structure, it is necessary to judge whether or not to partition the group measurements for second time. Then, the group target GMPHD filtering based on the ellipse random hypersurface model(RHM) is used to predict, update and extract the group target state. Finally, the second group structure is updated by using the extracted state of the group, and the obtained group information is fed back to the measurement partition step. Simulation experiments show that, the proposed algorithm not only has a higher real-time performance, but also solves the underestimation problem of group target number when the group targets merge, cross and split.
引文
[1] Mihaylova L, Carmi A Y, Septier F. Overview of Bayesian sequential Mote Carlo methods for group and extended object tracking[J]. Digital Signal Processing,2014, 25(C):1-16.
[2] Koch J W. Bayesian approach to extended object and cluster tracking using random matrices[J]. IEEE Trans on Aerospace and Electronic Systems, 2008, 44(3):1042-1059.
[3] Clark D, Godsill S. Group target tracking with the Gaussian mixture probability hypothesis density filter[C].The 3rd Int Conf on Intelligent Sensors, Sensor Networks and Information. Melbourne:IEEE, 2007:149-154.
[4]李振兴,刘进忙,李松,等.基于箱式粒子滤波的群目标跟踪算法[J].自动化学报, 2015, 41(4):785-798.(Li Z X, Liu J M, Li S, et al. Group targets tracking algorithm based on box particle filter[J]. Acta Automatica Sinica, 2015,41(4):785-798.)
[5] Abdallah F, Gning A, Bonnifait P. Box particle filtering for nonlinear state estimation using interval analysis[J].Automatica, 2008, 44(3):807-815.
[6] Liang M, Song L P, Ji H B, et al. Box-particle CPHD filter for multi-target tracking[C]. 2015 Int Conf on Control, Automation and Information Sciences(ICCAIS).Changshu, 2015:80-84.
[7] Zhu S J, Liu W F, Wen C L. Multiple group targets tracking using the generalized labeled multi-bernoulli filter[C]. Proc of the 35th Chinese Control Conf.Chengdu, 2016:4871-4876.
[8] Lin S F, Ba T V, Sven E N. Measurement driven birth model for the generalized labeled multi-bernoulli filter[C]. 2016 Int Conf on Control, Automation and Information Sciences(ICCAIS). Ansan, 2016:94-99.
[9] Ba-Ngu V, Ba-Tuong V, Hung G H. An efficient implementation of the generalized labeled multi-bernoulli filter[J]. IEEE Trans on Signal Processing, 2017, 65(8):1975-1987.
[10]连峰,韩崇昭,刘伟峰,等.基于SMC-PHDF的部分可分辨的群目标跟踪算法[J].自动化学报, 2010, 36(5):732-741.(Lian F, Han C Z, Liu W F, et al. Tracking partly resolvable group targets using SMC-PHDF[J]. Acta Automatica Sinica, 2010, 36(5):732-741.)
[11]张慧,徐晖,王雪莹,等.一种基于椭圆随机超曲面模型的高斯混合PHD滤波器[J].光学学报, 2013, 33(9):14-23.(Zhang H, Xu H, Wang X Y, et al. A Gaussian mixture PHD filter for group targets tracking based on ellipse random hypersurface models[J]. Acta Optica Sinica,2013, 33(9):14-23.)
[12] Baum M, Noack B, Hanebeck U D. Extended object and group tracking with elliptic random hypersurface models[C]. The 13th Conf on Information Fusion.Edinburgh, 2010:1-8.
[13] Antonio Z, Florian F, Marcus B, et al. Level-set random hypersurface models for tracking nonconvex extended objects[J]. IEEE Trans on Aerospace and Electronic Systems, 2016, 52(6):2990-3007.
[14]刘风梅,葛洪伟,杨金龙,等.基于均值漂移聚类的扩展目标量测集划分算法[J].计算机工程, 2014, 40(12):182-187.(Liu F M, Ge H W, Yang J L, et al. Extended target measurement set partition algorithm based on mean shift clustering[J]. Computer Engineering, 2014, 40(12):182-187.)
[15]李翠芸,桂阳,刘靳.基于mean shift迭代的新生未知多扩展目标跟踪[J].控制与决策, 2017, 32(3):521-525.(Li C Y, Gui Y, Liu J. Unknown newly born multiple extended targets tracking based on mean shift iteration[J].Control and Decision, 2017, 32(3):521-525.)
[16] Zhang H, Xu H, Wang X Y, et al. A PHD filter for tracking closely spaced objects with elliptic random hypersurface models[C]. The 16th Int Conf on Information Fusion.Istanbul, 2013:1558-1565.
[17] Granstrom K, Lundquist C, Orguner O. Extended target tracking using a Gaussian-mixture PHD filter[J]. IEEE Trans on Aerospace and Electronic Systems, 2012, 48(4):3268-3286.
[18] Vo B N, Ma W K. The Gaussian mixture probability hypothesis density filter[J]. IEEE Trans on Signal Processing, 2006, 54(11):4091-4104.
[19]刘妹琴,兰剑.目标跟踪前沿理论与应用[M].北京:科学出版社, 2015:159-161.(Liu M Q, Lan J. Leading-edge theory and application of target tracking[M]. Beijing:Science Press, 2015:159-161.)
[20] Schuhmacher D, Vo B T, Vo B N. A consistent metric for performance evaluation of multi-object filters[J]. IEEE Trans on Signal Processing, 2008, 56(8):3447-3457.
[2] Koch J W. Bayesian approach to extended object and cluster tracking using random matrices[J]. IEEE Trans on Aerospace and Electronic Systems, 2008, 44(3):1042-1059.
[3] Clark D, Godsill S. Group target tracking with the Gaussian mixture probability hypothesis density filter[C].The 3rd Int Conf on Intelligent Sensors, Sensor Networks and Information. Melbourne:IEEE, 2007:149-154.
[4]李振兴,刘进忙,李松,等.基于箱式粒子滤波的群目标跟踪算法[J].自动化学报, 2015, 41(4):785-798.(Li Z X, Liu J M, Li S, et al. Group targets tracking algorithm based on box particle filter[J]. Acta Automatica Sinica, 2015,41(4):785-798.)
[5] Abdallah F, Gning A, Bonnifait P. Box particle filtering for nonlinear state estimation using interval analysis[J].Automatica, 2008, 44(3):807-815.
[6] Liang M, Song L P, Ji H B, et al. Box-particle CPHD filter for multi-target tracking[C]. 2015 Int Conf on Control, Automation and Information Sciences(ICCAIS).Changshu, 2015:80-84.
[7] Zhu S J, Liu W F, Wen C L. Multiple group targets tracking using the generalized labeled multi-bernoulli filter[C]. Proc of the 35th Chinese Control Conf.Chengdu, 2016:4871-4876.
[8] Lin S F, Ba T V, Sven E N. Measurement driven birth model for the generalized labeled multi-bernoulli filter[C]. 2016 Int Conf on Control, Automation and Information Sciences(ICCAIS). Ansan, 2016:94-99.
[9] Ba-Ngu V, Ba-Tuong V, Hung G H. An efficient implementation of the generalized labeled multi-bernoulli filter[J]. IEEE Trans on Signal Processing, 2017, 65(8):1975-1987.
[10]连峰,韩崇昭,刘伟峰,等.基于SMC-PHDF的部分可分辨的群目标跟踪算法[J].自动化学报, 2010, 36(5):732-741.(Lian F, Han C Z, Liu W F, et al. Tracking partly resolvable group targets using SMC-PHDF[J]. Acta Automatica Sinica, 2010, 36(5):732-741.)
[11]张慧,徐晖,王雪莹,等.一种基于椭圆随机超曲面模型的高斯混合PHD滤波器[J].光学学报, 2013, 33(9):14-23.(Zhang H, Xu H, Wang X Y, et al. A Gaussian mixture PHD filter for group targets tracking based on ellipse random hypersurface models[J]. Acta Optica Sinica,2013, 33(9):14-23.)
[12] Baum M, Noack B, Hanebeck U D. Extended object and group tracking with elliptic random hypersurface models[C]. The 13th Conf on Information Fusion.Edinburgh, 2010:1-8.
[13] Antonio Z, Florian F, Marcus B, et al. Level-set random hypersurface models for tracking nonconvex extended objects[J]. IEEE Trans on Aerospace and Electronic Systems, 2016, 52(6):2990-3007.
[14]刘风梅,葛洪伟,杨金龙,等.基于均值漂移聚类的扩展目标量测集划分算法[J].计算机工程, 2014, 40(12):182-187.(Liu F M, Ge H W, Yang J L, et al. Extended target measurement set partition algorithm based on mean shift clustering[J]. Computer Engineering, 2014, 40(12):182-187.)
[15]李翠芸,桂阳,刘靳.基于mean shift迭代的新生未知多扩展目标跟踪[J].控制与决策, 2017, 32(3):521-525.(Li C Y, Gui Y, Liu J. Unknown newly born multiple extended targets tracking based on mean shift iteration[J].Control and Decision, 2017, 32(3):521-525.)
[16] Zhang H, Xu H, Wang X Y, et al. A PHD filter for tracking closely spaced objects with elliptic random hypersurface models[C]. The 16th Int Conf on Information Fusion.Istanbul, 2013:1558-1565.
[17] Granstrom K, Lundquist C, Orguner O. Extended target tracking using a Gaussian-mixture PHD filter[J]. IEEE Trans on Aerospace and Electronic Systems, 2012, 48(4):3268-3286.
[18] Vo B N, Ma W K. The Gaussian mixture probability hypothesis density filter[J]. IEEE Trans on Signal Processing, 2006, 54(11):4091-4104.
[19]刘妹琴,兰剑.目标跟踪前沿理论与应用[M].北京:科学出版社, 2015:159-161.(Liu M Q, Lan J. Leading-edge theory and application of target tracking[M]. Beijing:Science Press, 2015:159-161.)
[20] Schuhmacher D, Vo B T, Vo B N. A consistent metric for performance evaluation of multi-object filters[J]. IEEE Trans on Signal Processing, 2008, 56(8):3447-3457.