摘要: 传统的GM-PHD(Gaussian Mixture-Probability Hypothesis Density)滤波算法用当前时刻接收到的全部量测值对所有高斯项进行更新,使得大量的运算时间花费在使用无效量测对高斯项的更新上。针对此问题,提出一种快速多目标跟踪GM-PHD滤波器。首先在算法预测步骤中将高斯项 分为新生及存活目标两类;然后在更新步骤中先计算存活目标与所有量测之间的残差,使用椭球门限,用门限内的量测值来更新存活目标;接着计算新生目标与剩下量测之间的残差,再次使用落入椭球门限内的量测值来更新新生目标,这样可以最大限度地将无效量测排除掉,从而减少算法运算时间。实验结果表明,该方法在保证目标跟踪精度的同时降低了算法时间复杂度,其综合性能优于传统的GM-PHD滤波算法。
[1] Bar-Shalom Y,Li X R.Multitarget-multisensor Tracking:Principles and Techniques [M].Storrs:YBS Publishing,1995 [2] Bar-Shalom Y,Fortmann T E.Tracking and Data Association[M].San Diego:Academic Press,1988 [3] Mahler R.A theoretical foundation for the stein-winter probability hypothesis density (PHD) multi-target tracking approach [C]∥Proceedings of the MSS National Symposium on Sensor and Data Fusion.San Antonio,TX,2000:99-117 [4] Mahler R.Engineering statistics for multi-object tracking [C]∥SPIE Proceedings on Signal and Data Processing of Small Targets.Vancouver,2001:53-60 [5] Mahler R.Multitarget moments and their application to multitarget tracking [C]∥Proceedings of the Workshop on Estimation,Tracking and Fusion.Monterey,CA,2001:134-166 [6] Mahler R.Multi-target Bayes filtering via first-order multi-target moments [J].IEEE Transactions on Aerospace and Electronic Systems,2003,39(4):1152-1178 [7] Vo B N,Ma W K.The Gaussian mixture probability hypothesis density filter [J].IEEE Transactions on Signal Processing,2006,54(11):4091-4104 [8] Mahler R.PHD filters of higher order in target number [J].IEEE Transactions on Aerospace and Electronic Systems,2007,43(4):1523-1543 [9] Vo B T,Vo B N,Cantoni A.Analytic implementations of the cardinalized probability hypothesis density filter [J].IEEE Transactions on Signal Processing,2007,55(7):3553-3567 [10] Musicki D,Evans R,Stankovic S.Integrated probabilistic data association [J].IEEE Transactions on Automatic Control,1994,39(6):1237-1241 [11] Houles A,Bar-Shalom Y.Multisensor tracking of a maneuvering target in clutter [J].IEEE Transactions on Aerospace and Electronic Systems,1989,25(2):176-189 [12] Blackman S.Multiple Targets Tracking with Radar Applications [M].Artech House,Norwood,MA,1986 [13] Zhang Hong-jian,Jing Zhong-liang,Hu Shi-qiang.Gaussian mixture CPHD filter with gating technique [J].Signal Processing,2009(89):1521-1530 [14] Yang Feng,Wang Yong-qi,Liang Yan,et al.Collaborative PHD filter for fast multi-target tracking[J].Systems Engineering and Electronics,2014,36(11):2113-2121(in Chinese) 杨峰,王永齐,梁彦,等.面向快速多目标跟踪的协同PHD滤波器[J].系统工程与电子技术,2014,36(11):2113-2121 [15] Zhang Tao,Wu Ren-biao.Adaptive gating GM-CPHD for nultitarget tracking [J].Journal of Data Acquisition & Processing,2014,29(4):523-528(in Chinese) 章涛,吴仁彪.自适应门限 GM-CPHD 多目标跟踪算法 [J].数据采集与处理,2014,29(4):523-528 [16] Jiang Tong-yang,Liu Mei-qin,Zhang Sen-lin,et al.Gating technique for the Gaussian mixture multi-Bernoulli filter [C]∥IEEE American Control Conference (ACC).2014:1096-1101 [17] Zhang Tao,Lai Ran,Wu Ren-biao,et al.Collaborative PHD filter for fast multi-target tracking [J].Systems Engineering and Electronics,2013,30(12):1419-1426(in Chinese) 章涛,来燃,吴仁彪,等.观测最优分配的GM-PHD 多目标跟踪算法 [J].信号处理,2014,30(12):1419-1426 [18] Zhang Hong-jian.Finite-set statistics based multiple target tacking[D].Shanghai:Shanghai JiaoTong University,2009(in Chinese) 张洪建.基于有限集统计学的多目标跟踪算法研究[D].上海:上海交通大学,2009 |
No related articles found! |
|