基于最近邻的集中式多传感器多目标跟踪算法

经典的集中式多传感器多目标跟踪算法通常计算量较大,经常难以满足系统的实时性要求,工程上实现起来比较困难,为进一步扩大集中式多传感器的应用范围,使其在对算法实时性要求较高、跟踪精度要求较小的实际场合中广泛应用。文章基于最近邻域思想,研究了并行处理结构的集中式多传感器最近邻域算法,并从算法跟踪精度、实时性、有效跟踪率3个方面对其与经典的顺序多传感器联合概率数据互联算法进行了仿真比较。经仿真验证,并行处理结构的集中式多传感器最近邻域算法实时性提高了60%以上,且在跟踪背景杂波适中的情况下能够有效跟踪目标。     

基于量测一致性的分布式多传感器多目标跟踪算法

针对无线传感器网络跟踪多目标过程中传感器能搭载的计算负荷有限,不宜采用复杂算法实现数据处理的问题,提出了一种基于量测一致性的分布式多传感器多目标跟踪算法。算法采用计算相对简易的最近邻域法处理多目标跟踪中的数据互联问题,针对最近邻域法容易受杂波干扰的情况,通过量测的平均一致性迭代来改进算法的性能。仿真结果证明,算法具备有效抑制因误判产生的错误量测对跟踪过程干扰的性能,实现了良好的传感器网络跟踪精度和估计信息一致性。     

多传感器数据融合的平均航迹算法

提出了一种适用于分布式多传感器的平均融合算法，对其算法机理进行了详细描述。对融合算法、未融合算法和算术平均算法三者的跟踪航迹和方差进行了仿真比较。仿真结果表明，融合算法优于算术平均算法和未融合算法。它提高了跟踪精度，改善了航迹质量。尤其在多传感器跟踪系统工作异常的情况下具有独特的优良位能。     

一种分布式异步航迹融合算法

在多被动传感器目标跟踪中,融合中心处理的信息一般是同步的,然而实际情况并非如此。另外,一些被动传感器只能得到目标的方位信息,无法单独形成有效航迹,这就需要将各传感器数据同步到相同时刻,然后应用同步融合算法。针对被动传感器探测系统,采用传感器到传感器融合和系统到传感器融合的分布式融合结构,并对各局部传感器引入全局反馈,对相关信息采用协方差交叉算法进行处理,完成被动传感器异步数据的融合,仿真结果表明,该算法具有较好的融合效果。     

基于布尔感知模型的边界线多重覆盖算法

无线传感器网络监视预警系统的区域边界具有特殊重要性,针对节点的布尔感知模型,根据节点感知圆盘的相互关系,可将整条边界线划分为不可再分割的可数个最小曲线段,利用改进的贪婪式算法研究了集中式多重覆盖算法和分布式多重覆盖算法,通过仿真实验,验证了多重覆盖带来的高检测概率以及高覆盖概率。     

基于多信息加权融合的降维航迹关联算法

针对分布式3个传感器多目标的航迹相关算法如果直接计算时间和花费都比较高这一问题,提出降维航迹关联算法。该算法先利用2个传感器的目标位置估计点构造航迹相关代价矩阵,求出最优解,再利用这个最优解与第3个传感器的目标位置估计点构建航迹相关代价矩阵,进一步得到三维航迹相关配对。针对单信息系统不稳定这一问题,提出了融合多个特征信息的加权算法。该算法利用熵权法赋予各种不同信息的权重进行加权融合,转化为单信息问题。仿真结果说明本文所给出的新算法不仅减小了目标跟踪误差而且其时间花费较少,因此,新算法是可行的。     

非线性系统中多传感器目标跟踪融合算法研究

主要阐述了在非线性系统中多传感器目标跟踪的融合算法，提出了基于变换测量卡尔曼滤波器（CMKF）的分布式融合算法，从该理论出发，导出了分布式变换测量卡尔曼滤波算法（DCMKFA）几乎能够重视集中式融合估计，仿真结果证明了这一结论，因此，DCMKFA对于非线性系统中的目标跟踪是一个有效的分布式融合算法。     

一种基于能量受限的分布式多传感器管理算法

在能量受限的分布式多传感器跟踪系统中，跟踪目标的同时，需要节省能量消耗，延长系统生存周期，本文依据一种传感器节点能量消耗模型，提出了一种以能量消耗和信息增量为效用的传感器管理算法。仿真结果表明该算法能提高跟踪精度，减少能量消耗，延长系统的使用时间。     

一种混合的多机动目标跟踪算法研究

提出了一种混合的多机动目标跟踪算法:交互多模型模糊联合概率数据关联算法(IMM-FJPDA),该算法将交互多模型算法(IMM)和模糊联合概率数据关联算法(FJPDA)相结合,它克服了IMM-JPDA算法计算量大和IMM-FDA算法在强杂波环境中跟踪精度差的问题.给出了基于模糊C均值(FCM)算法的多机动目标跟踪步骤.仿真结果表明IMM-FJPDA算法跟踪精度与IMM-JPDA算法相当,但计算量明显减小,提高了跟踪实时性.     

智能燃油计量装置故障诊断算法研究

在分布式控制系统框架下,为完善智能装置功能,以某型民用发动机燃油系统为研究对象,将其关键部件燃油计量装置作为一个智能装置节点,基于SDQ-ARMA系统算法进行位移传感器数据确认与故障诊断,并针对其计量活门的静摩擦力增大的特定性能衰退模式,在提取燃油系统传感器的时域特征的基础上,构建了基于SVM的故障检测算法流程,对燃油系统联合仿真模型进行验证,仿真实例中,故障诊断算法软硬件仿真一致,表明研究算法具有实时性,可为智能装置算法开发提供参考。     

Evaluation of multiple radar target trackers in stressfulenvironments

This paper evaluates the performance of multiple target tracking (MTT) algorithms in real-life stressful radar tracking environments. Real closely spaced maneuver radar data, generated by six F-18 fighters and other targets, were collected jointly by the defence departments of Canada and United States to support this practical MTT algorithm evaluation study. A set of performance metrics was defined here to compare the suboptimal nearest neighbor (SNN), global nearest neighbor (GNN), and various variants of the joint probabilistic data association (JPDA) MTT trackers. Results reveal an interesting result that all these MTT algorithms exhibited very close performance. In addition, the weighted sum approach of the PDA/JPDA trackers which are theoretically effective were observed to perform poorly in tracking closely spaced targets. Overall speaking, the GNN filter based on the Munkres algorithm had the best performance in terms of both tracking performance and robustness     

SEQUENTIAL ALGORITHM FOR MULTISENSOR PROBABILISTIC DATA ASSOCIATION

Jointprobabillsticdataassociation(JPDA)isanalgorithmusedinsinglesensormultipletargettrackingsystems.Itemploysthenon-uniqueassignmentof"allneighbor"strategytoadaptforthedensemultitargettrackingenvironments[1].Becauseofitswideapplications,itisnecessarytoextendJPDAintosomemultiplesensortrackingsystems.Suchamultisensorsystem,forexample,canbeformedbycollocatingradarandinfraredsearchandtrack(IRST)whichcantakeadvantagesofboththesensorsbodatafusion.Undertheconditionofthesamesensors,acommonmeasure…     

A multipath data association tracker for over-the-horizon radar

A new algorithm, multipath probabilistic data association (MPDA), for initiation and tracking in over-the-horizon radar (OTHR) is described. MPDA is capable of exploiting multipath target signatures arising from discrete propagation modes that are resolvable by the radar. Nonlinear measurement models exhibiting multipath target signatures in azimuth, slant range, and Doppler are used. Tracking is performed in ground coordinates and therefore depends on the provision of estimates of virtual ionospheric heights to achieve coordinate registration. Although the propagation mode characteristics are assumed to be known, their correspondence with the detections is not required to be known. A target existence model is included for automatic track maintenance. Numerical simulations for four resolvable propagation modes are presented that demonstrate the ability of the technique to initiate and maintain track at probabilities of detection of 0.4 per mode in clutter densities for which conventional probabilistic data association (PDA) has a high probability of track loss, and suffers from track bias. A nearest neighbor version of MPDA is also presented     

一种基于最小二乘拟合的数据关联算法

针对点航关联在多目标跟踪中精度与实时性难兼顾的问题,提出了一种基于最小二乘拟合的点航关联算法。首先采用滑窗将历史航迹截断,采用最小二乘法在不同维度分别拟合、外推融合航迹历史信息条件下的航迹点,增加外推点的多样性及信息量。同时定义了5种全概率关联事件,提取传统滤波方法的预测点,将拟合外推点与滤波预测点融合,使归属判决更加准确。最后分别推导了不同事件发生时的状态更新方程与误差协方差更新方程,给出了其中参数的确定方法。经仿真数据验证,与经典的最近邻域法和联合概率数据互联算法相比,所提算法能够更好地兼顾精度与实时性,且计算复杂度较低,易于工程实现。     

多传感器融合状态估计方法综述

随着传感器网络技术的发展，多传感器融合状态估计凭借其鲁棒性、灵活性、可扩展性以及便于故障检测等优点，长期受到国内外学者的广泛关注，并取得了大量研究成果。数据融合的方法为融合状态估计奠定了理论基础，也是早期研究的主要方向，从20世纪70年代到20世纪末，相继发展出了集中式和分散式滤波架构及相应算法。无线通信技术的成熟以及一致性算法的出现使得分布式状态估计的研究进入了快车道，自2005年以来，大量基于一致性的分布式滤波算法被提出，其中不乏实用的经典方法和优秀的开创性方法。旨在梳理多传感器融合状态估计的发展，探究从数据融合到分布式滤波的内在联系，并对一些经典方法进行了总结。     

A Probabilistic Strongest Neighbor Filter Algorithm for m Validated Measurements

A new form of the probabilistically strongest neighbor filter (PSNF) algorithm taking into account the number of validated measurements is proposed. The probabilistic nature of the strongest neighbor (SN) measurement in a cluttered environment is shown to be varied with respect to the number of validated measurements. Incorporating the number of validated measurements into design of the PSNF produces a consistent and cost effective data association method. Simulation studies show that the new filter is less sensitive to the unknown spatial clutter density and is more reliable for practical target tracking in nonhomogeneous clutter than the existing PSNF. It has similar performances to the probabilistic data association filter amplitude information (PDAF-AI) with much less computational complexities.     

基于双向最近邻准则的编队预定目标选择方法

相比传统的预定目标选择方法,基于编队形状的反舰导弹预定目标选择方法是一类性能优越的新方法。其原理是利用导弹飞行期间舰艇编队形状的相对稳定性,并将发射前装订的编队形状和末制导雷达探测到的编队形状表示为2个点集,通过点集匹配实现预定目标选择。提高这类算法性能的关键在于研究合理的点集距离函数。文章提出一种基于共同点的距离函数,研究了其抗干扰的机理,并证明其计算过程可通过双向最近邻准则实现。仿真试验表明该方法性能优于以往的MHD方法。     

Multiresolutional filtering using wavelet transform

An algorithm for optimal and dynamic multiresolutional distributed filtering is derived. The wavelet transform is utilized as a bridge linking signals at different resolution levels. The algorithm can be employed for dynamic multisensor/data fusion     

Centralized and distributed multisensor integration withuncertainties in communication networks

Algorithms in which each sensor is represented in a local coordinate system and the communication networks between sensors have uncertainties are considered. The algorithms are general and can be applied to various integration tasks. The effects of the communication network uncertainties are minimized in the local estimation and central fusion processes. In the centralized multisensor integration, the local measurements and local measurement models are transferred to the central coordinate system and the optimal integration is obtained at the central process. In contrast, the local measurements, together with the previous central estimate transmitted from the communication network, are locally processed in the distributed multisensor integration algorithm. Because the distributed algorithm uses the communication networks twice, more errors are introduced, so that when the uncertainties are large, the centralized algorithm is preferred. Although the algorithms are developed in the three-dimensional coordinate system, with straightforward extension they can be applied to N-dimensional coordinate systems