摘要
提出一种基于量测驱动的自适应目标新生强度PHD/CPHD滤波算法.该算法认为新生目标是不可检测的,有效地克服了归一化失衡问题;同时,基于量测驱动自适应设计目标新生强度,利用PHD/CPHD滤波分别递归估计存活目标和新生目标的状态及其数目.最后,在序列蒙特卡罗框架下实现了该PHD/CPHD滤波算法.算例结果表明,改进算法可以有效地实时跟踪多个机动目标的状态和数目,应用前景较好.
The PHD/CPHD filter with the adaptive target birth intensity driven by measurements is proposed. The result that the newborn targets are not always detected can solve the problem of normalized unbalance. The adaptive target birth intensity can be designed based on measurement-driven and the estimated state and number of persistent targets, and the newborn targets are propagated separately by using the PHD/CPHD filter. The SMC implementation of the improved PHD/CPHD filter is described. The numerical simulation results show that the improved algorithms can efficiently and instantaneously estimate the number of targets and their states, and have great application prospection.
引文
[1]Mahler R.Multi-target Bayes filtering via first-order multi-target moments[J].IEEE Trans on Aerospace and Electronic Systems,2003,39(4):1152-1178.
[2]Clark D,Ruiz I T,Petillot Y,et al.Particle PHD filter multiple target tracking in sonar image[J].IEEE Trans on Aerospace and Electronic Systems,2007,43(1):409-416.
[3]Maggio E,Taj M,Cavallaro A.Efficient multi-target visual tracking using random finite sets[J].IEEE Trans on Circuits and Systems for Video Technology,2008,18(8):1016-1027.
[4]Tobias M,Lanterman A D.Probability hypothesis density based multi-target tracking with bistatic range and Doppler observations[J].IET Radar,Sonar and Navigation,2005,152(3):195-205.
[5]Mahler R.PHD filters of higher order in target number[J].IEEE Trans on Aerospace and Electronic Systems,2007,43(4):1523-1543.
[6]Vo B T,Vo B N,Cantoni A.Analytic implementations of the cardinalized probability hypothesis density filter[J].IEEE Trans on Signal Processing,2007,55(7):3553-3567.
[7]Vo B N,Ma W K.Sequential Monte Carlo methods for multi-target filtering with random finite sets[J].IEEE Trans on Aerospace and Electronic Systems,2005,41(4):1224-1245.
[8]Whiteley N,Singh S,Godsill S.Auxiliary particle implementation of the probability hypothesis density filter[J].IEEE Trans on Aerospace and Electronic Systems,2010,46(7):1437-1454.
[9]Vo B N,Ma W K.The Gaussian mixture probability hypothesis density filter[J].IEEE Trans on Signal Processing,2006,54(11):4091-4104.
[10]Clark D,Vo B N.Convergence analysis of the Gaussian mixture PHD filter[J].IEEE Trans on Signal Processing,2007,55(4):1204-1212.
[11]Clark D,Vo B T,Vo B N.Gaussian particle implementations of probability hypothesis density filters[C].IEEE Aerospace Conference.Montana:Big Sky,2007:1-11.
[12]Clark D,Vo B T,Vo B N,et al.Gaussian mixture implementations of probability hypothesis density filters for non-linear dynamical models[C].IET Seminar on Target Tracking and Data Fusion.London:IET,2008:21-28.
[13]Yin J J,Zhang J Q,Zhuang Z S.Gaussian sum PHD filtering algorithm for nonlinear non-Gaussian models[J].Chinese J of Aeronautics,2008,21(4):341-351.
[14]Vo B N,Vo B T,Mahler R.Closed-form solutions to forward-backward smoothing[J].IEEE Trans on Signal Processing,2012,60(1):2-17.
[15]Yazdian D M,Azimifar Z,Masnadi S M A.Competitive Gaussian mixture probability hypothesis density filter for muhiple target tracking in the presence of ambiguity and occlusion[J].IET Radar,Sonar and Navigation,2012,6(4):251-262.
[16]Beard M,Vo B N,Vo B T,et al.A partially uniform target birth model for Gaussian mixture PHD/CPHD filtering[J].IEEE Trans on Aerospace and Electronic Systems,2013,49(4):2835-2844.
[17]Tobias M,Lanterman A.Techniques for birth particle placement in the probability hypothesis density particle filter applied to passive radar[J].IET Radar,Sonar and Navigation,2008,2(5):351-365.
[18]Ristic B,Clark D,Vo B N,et al.Adaptive target birth intensity for PHD and CPHD filters[J].IEEE Trans on Aerospace and Electronic Systems,2012,48(2):1656-1668.
[19]欧阳成,华云,高尚伟.改进的自适应新生目标强度PHD滤波[J].系统工程与电子技术.2013,35(12):2452-2458.(Ouyang C,Hua Y,Gao S W.Improved adaptive target birth intensity for PHD filter[J].Systems Engineering and Electronics,2013,35(12):2452-2458.)
[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.