MULTITARGET STATE AND TRACK ESTIMATION FOR THE PROBABILITY HYPOTHESES DENSITY FILTER

The particle Probability Hypotheses Density (particle-PHD) filter is a tractable approach for Random Finite Set (RFS) Bayes estimation, but the particle-PHD filter can not directly derive the target track. Most existing approaches combine the data association step to solve this problem. This paper proposes an algorithm which does not need the association step. Our basic ideal is based on the clustering algorithm of Finite Mixture Models (FMM). The intensity distribution is first derived by the particle-PHD filter, and then the clustering algorithm is applied to estimate the multitarget states and tracks jointly. The clustering process includes two steps: the prediction and update. The key to the proposed algorithm is to use the prediction as the initial points and the convergent points as the es- timates. Besides, Expectation-Maximization (EM) and Markov Chain Monte Carlo (MCMC) ap- proaches are used for the FMM parameter estimation.

A NEW DATA ASSOCIATION ALGORITHM USING PROBABILITY HYPOTHESIS DENSITY FILTER

Probability Hypothesis Density (PHD) filtering approach has shown its advantages in tracking time varying number of targets even when there are noise,clutter and misdetection. For linear Gaussian Mixture (GM) system,PHD filter has a closed form recursion (GMPHD). But PHD filter cannot estimate the trajectories of multi-target because it only provides identity-free estimate of target states. Existing data association methods still remain a big challenge mostly because they are com-putationally expensive. In this paper,we proposed a new data association algorithm using GMPHD filter,which significantly alleviated the heavy computing load and performed multi-target trajectory tracking effectively in the meantime.

Improved pruning algorithm for Gaussian mixture probability hypothesis density filter

With the increment of the number of Gaussian components, the computation cost increases in the Gaussian mixture probability hypothesis density(GM-PHD) filter. Based on the theory of Chen et al, we propose an improved pruning algorithm for the GM-PHD filter, which utilizes not only the Gaussian components' means and covariance, but their weights as a new criterion to improve the estimate accuracy of the conventional pruning algorithm for tracking very closely proximity targets. Moreover, it solves the end-less while-loop problem without the need of a second merging step. Simulation results show that this improved algorithm is easier to implement and more robust than the formal ones.

Global track extraction for probability hypothesis density filter

The probability hypothesis density(PHD), a well-known scheme for multi-target tracking in clutters, can obtain peaks of possible tracks, and its cluster-indexed method is widely accepted in further track extraction. However, the track extraction may face high risk in the case that the targets are so approached that it is hardly to discern their measurements. The concept of the distance between track sets in two adjacent times is defined and a consistency measure metric between any two peaks in two adjacent times is further proposed based on "global information", containing spatial information(topology feature) among tracks, along with the temporal information of each track. Then, a global track extraction method is proposed based on the consistency belief and four decision rules. Via the simulation comparison with the cluster-indexed method, the proposed method can avoid the track break and mistake association.

Cubature Kalman probability hypothesis density filter based on multi-sensor consistency fusion

The GM-PHD framework as recursion realization of PHD filter is extensively applied to multitarget tracking system. A new idea of improving the estimation precision of time-varying multi-target in non-linear system is proposed due to the advantage of computation efficiency in this paper. First,a novel cubature Kalman probability hypothesis density filter is designed for single sensor measurement system under the Gaussian mixture framework. Second,the consistency fusion strategy for multi-sensor measurement is proposed through constructing consistency matrix. Furthermore,to take the advantage of consistency fusion strategy,fused measurement is introduced in the update step of cubature Kalman probability hypothesis density filter to replace the single-sensor measurement. Then a cubature Kalman probability hypothesis density filter based on multi-sensor consistency fusion is proposed. Capabilily of the proposed algorithm is illustrated through simulation scenario of multi-sensor multi-target tracking.

THE PROBABILITY HYPOTHESIS DENSITY FILTER WITH EVIDENCE FUSION

The original Probability Hypothesis Density (PHD) filter is a tractable algorithm for Multi-Target Tracking (MTT) in Random Finite Set (RFS) frameworks. In this paper,we introduce a novel Evidence PHD (E-PHD) filter which combines the Dempster-Shafer (DS) evidence theory. The proposed filter can deal with the uncertain information,thus it forms target track. We mainly discusses the E-PHD filter under the condition of linear Gaussian. Research shows that the E-PHD filter has an analytic form of Evidence Gaussian Mixture PHD (E-GMPHD). The final experiment shows that the proposed E-GMPHD filter can derive the target identity,state,and number effectively.

多元假设检验GMPHD轨迹跟踪

由于在军事和民事领域逐步广泛的应用,数目不定的多目标跟踪技术正受到越来越多的关注。概率假设密度(PHD)滤波方法,特别是具有闭式递归的高斯混合概率假设密度(GMPHD)技术,在噪声和漏警等影响下仍能形成优越的群目标跟踪性能。然而PHD滤波器并不能实现多目标航迹跟踪,而其与传统数据互联的结合,复杂度高且跟踪效果不尽如人意。在该文中,各目标的航迹信息以假设形式表述,数据互联则是通过使用经典的多元假设检测方法判决假设矩阵实现。其与GMPHD的结合不仅实现了数据互联和轨迹管理,还因为积累时间信息大大降低了杂波干扰的影响。实验结果证明,该算法可以对多个目标所形成的轨迹实施正确跟踪,同时,计算量的大幅度降低带来了跟踪系统可实现性的提高。

一种基于模糊聚类的PHD航迹维持算法

针对杂波环境下数量变化的多目标航迹关联问题,提出一种基于模糊聚类的PHD航迹维持算法.该算法充分利用多帧信息,对当前时刻状态进行多步预测,并根据惯性进行加权,然后利用模糊聚类求得当前估计属于每条航迹的隶属度,从而得到最终的航迹.与传统的估计与航迹关联算法不同,该算法在更新每条航迹信息时,不仅仅是简单地对相邻帧之间的对数似然比进行求和,而是通过加权聚类等操作综合考虑了多帧信息.实验结果表明,所提算法能够更好地保持目标航迹,即使在目标出现交叉的地方也能达到很好的跟踪精度,具有较强的鲁棒性和优良的航迹维持性能.

改进的多模型粒子PHD和CPHD滤波算法

多模型粒子概率假设密度(Probability hypothesis density,PHD)滤波是一种有效的多机动目标跟踪算法,然而当模型概率过小时,该算法存在粒子退化问题,而且它对目标数的泊松分布假设会夸大目标漏检对其势估计的影响.针对上述问题,本文提出一种改进算法.该算法并不是简单地对模型索引进行采样,而是用粒子拟合目标状态的模型条件PHD强度,在不对噪声做任何先验假设的前提下,通过重采样实现存活粒子的输入交互,提高了滤波性能.在此基础上,进一步将算法在Cardinalized PHD(CPHD)的框架下加以实现,提高其目标数估计精度.仿真实验表明,所提算法在滤波性能和目标数估计精度方面均优于传统的多模型粒子PHD算法,具有良好的工程应用前景.

PHD粒子滤波中目标状态提取方法研究

采用概率假设密度(PHD)粒子滤波进行多目标跟踪时,各时刻的目标状态表现为大量的加权粒子,需以一定方法从该粒子近似中提取出来。该文提出一种增强的目标状态提取方法,先以k-means算法对粒子进行空间分布的聚类,再于各类中寻找粒子权的峰值位置作为目标状态的估计。仿真结果表明:由于综合利用了粒子的权值和空间分布信息,该算法具有比现有算法更小的目标状态估计误差。

面向快速多目标跟踪的协同PHD滤波器

考虑到存活目标与新生目标在动态演化特性上的差异性,提出了面向快速多目标跟踪的协同概率假设密度(collaborative probability hypothesis density,CoPHD)滤波框架。该框架利用存活目标的状态信息,将量测动态划分为存活目标量测集与新生目标量测集,在两个量测集分别运用PHD组处理更新基础上建立了处理模块的交互与协同机制,力图在保证跟踪精度的同时提高计算效率。该框架由于采用PHD组处理方式而具有状态自动提取功能。进一步给出了该框架的序贯蒙特卡罗算法实现。仿真结果表明,该算法在计算效率以及状态提取精度上具有明显优势。

结合聚类的GM-PHD滤波器辐射源群目标跟踪

群目标跟踪是一种情况更为复杂的多目标跟踪问题,由于军事辐射源目标经常出现雷达关机的情况,因此常用的多目标跟踪方法对于这类辐射源群目标的跟踪效果并不理想。为此,结合聚类技术提出了一种改进的高斯混合概率假设密度(Gaussian mixture-probability hypothesis density,GM-PHD)滤波器跟踪方法。该方法在GM-PHD滤波器的更新过程中,通过引入群中心产生的虚拟量测信息以提高目标跟踪性能,但不进行量测集划分。获得单一个体目标的估计状态后利用Jensen-Shannon divergence计算其相似度,然后再对估计目标进行聚类以实现群目标的跟踪。最后通过对相邻时刻的群中心轨迹点进行关联匹配,从而获得群目标的完整运动轨迹。仿真实验结果表明,所提方法能够对辐射源群目标进行有效跟踪,并具有较好的目标跟踪性能。

基于PHD滤波和数据关联的多目标跟踪

针对杂波环境下的多目标跟踪,概率假设密度(probability hypothesis density,PHD)滤波不能提供目标航迹信息的问题,提出一种基于PHD滤波和数据关联的多目标跟踪方法。利用PHD滤波消除杂波并得到各个时刻的目标个数和目标状态估计。将PHD滤波的结果重新定义为量测数据,通过数据关联进一步消除虚警和漏警并给出目标航迹。仿真结果表明,该算法可以在有效地提高杂波环境下多目标跟踪精度的同时提供各目标航迹信息。

针对交叉目标场景的带标签GM-PHD改进算法

在多目标跟踪系统中,当目标航迹较为接近或交叉时,使用带标签高斯混合概率假设密度(GM-PHD)算法会出现目标漏检的现象。为此,提出一种改进算法来解决存在交叉目标情况下的多目标跟踪问题。在更新结束后对估计得到的高斯项标签进行管理,若估计目标数目减少,则需要判断目标航迹是否较为接近或者交叉。若目标接近或交叉,则对高斯项进行标签管理和权值重置,并重新估计目标状态和航迹,否则将目标减少视为正常的目标消亡现象,直接进行航迹管理。实验结果表明,与无标签算法及常规带标签算法相比,该算法可以更好地解决由目标交叉导致的漏检问题,并具有更高的稳定性。

基于PHD的多扩展目标联合检测、跟踪与分类算法

针对杂波和噪声背景下空间距离较近的扩展目标数目和状态难以估计的问题,提出了基于扩展目标概率假设密度滤波器(ET-PHD)的多目标联合检测、跟踪与分类算法,并给出了该算法基于粒子滤波的实现方法.算法在滤波器中引入了属性量测信息,预测阶段的粒子按照其类别进行传播,更新阶段对所有粒子进行联合更新,更新结束后将粒子按照类别进行分类,各类别的粒子集表示了其相应类别目标的PHD分布.该算法具有模块化结构,计算复杂度为O(mn).数值仿真场景包含两类扩展目标并行运动和两类扩展目标交叉运动.结果表明,该算法可以同时估计扩展目标的类别、数目和状态,并且平均最优次模式分配距离相比传统算法的降低幅度超过50%.

基于ET-PHD滤波器和变分贝叶斯近似的扩展目标跟踪算法

针对未知测量噪声协方差情况下的多扩展目标跟踪问题,利用扩展目标概率假设密度(ET-PHD)滤波器和变分贝叶斯(VB)近似理论,提出了一种标准ET-PHD滤波器的扩展方法及其解析的实现方法。首先,根据标准ETPHD滤波器的目标状态方程和测量方程,定义了目标状态和测量噪声协方差的增广状态变量及二者的联合转移函数;然后,根据标准ET-PHD滤波器,构建了扩展的ET-PHD滤波器的预测和更新公式;最后,在线性高斯假设的条件下,利用高斯和逆伽马(IG)混合分布表示目标的联合后验强度函数,从而给出了扩展ET-PHD滤波器的解析实现。仿真结果表明:所提算法能提供可靠的跟踪结果,可有效地处理未知测量噪声协方差环境中的多扩展目标跟踪问题。

PHD多目标跟踪算法及参数影响分析

多目标跟踪的关键就是对目标数和目标状态的准确估计。将目标集合看成一个随机集,并且目标数也是变化的。采用一阶统计矩近似表示状态空间的概率密度,通过蒙特卡罗模拟近似表示一阶统计矩,从而实现多目标跟踪。实验表明,在杂波环境下,PHD算法可以实现多目标跟踪,并且各参数对跟踪精度有一定的影响。

基于核密度估计高斯混合PHD滤波的多目标跟踪算法

针对多目标跟踪系统中传统算法目标估计精度较低的问题,提出了基于核密度估计的高斯混合概率假设密度(probability hypothesis density,PHD)滤波算法。在该算法中,经过剪枝、合并后,引入核密度估计理论的Mean-shift算法,对高斯混合PHD分布密度函数进行核密度估计,取代了传统算法中的状态估计方法。最后,选择估计后得到的峰值作为目标状态估计值。仿真结果表明,基于核密度估计的高斯混合PHD滤波算法比传统算法具有更高的估计精度。

均方根嵌入式容积粒子PHD多目标跟踪方法

针对基于概率假设密度算法(Probability hypothesis density,PHD)的非线性多目标跟踪精度低、滤波发散等问题,提出了一种新的PHD算法—改进的均方根嵌入式容积粒子PHD算法(Advanced square-root imbedded cubature particle PHD,ASRICP-PHD).新的算法在初始化采样时将整个采样区域等概率划分为若干个区域,然后利用既定的准则从每个区域抽取粒子,并利用均方根嵌入式容积滤波方法对每个粒子进行滤波,来拟合重要密度函数,预测和更新多目标状态的PHD.仿真结果表明该算法能对多目标进行有效跟踪,相比拟随机采样法和伪随机采样,等概率采样的方法在多目标位置估计和数目估计上有更高的精度.

高斯粒子PHD滤波的多个弱小目标TBD算法

针对现有多个弱小目标检测前跟踪(track-before-detect,TBD)算法存在的跟踪精度低,算法复杂度高等问题,提出一种新的基于概率假设密度(probability hypothesis density,PHD)的TBD算法。所提算法通过高斯粒子滤波对PHD中的各高斯项进行递归运算、进行多帧能量累积,并提取高斯项的均值为目标的状态,达到检测与跟踪多个弱小目标的目的。算法在随机集滤波框架下完成未知数目的多个弱小目标跟踪,不仅充分利用粒子滤波的非线性估计能力,同时避免了传统算法利用模糊聚类进行目标状态提取所带来的跟踪精度低等问题。仿真结果表明,所提算法与传统方法相比,在降低算法复杂度的同时,对多个红外弱小目标具有更加良好的实时检测和跟踪性能。