基于人工神经网络的多模型目标跟踪算法

针对在目标跟踪中单模型跟踪算法难以应对目标运动形式的变化,而多模型跟踪算法存在结构固定、跟踪精度被非匹配模型削弱且模型切换缓慢的矛盾,文章提出了一种基于人工神经网络的多模型目标跟踪算法。通过分析目标几种基本运动模式的轨迹特点,归纳出目标运动轨迹的特征向量。利用训练好的BP神经网络对滑窗里的轨迹段进行运动模型识别,按结果进行跟踪模型切换,达到使跟踪算法实时适应目标运动状态的目的。仿真结果证明了该算法的有效性,且与传统的多模型算法相比,具有结构更加简单、更强的灵活性和拓展性的特点。     

基于视觉注意机制的认知雷达数据关联算法

针对传统关联波门设计方法在应用于机动目标跟踪时容易引起失跟、以及概率数据关联算法不适于多交叉目标跟踪的问题,提出了一种基于人类视觉选择性注意机制和知觉客体的"特征整合"理论的认知雷达数据关联算法。算法以综合交互式多模型概率数据关联算法为基础,采取假设目标最大机动水平已知的"当前"统计模型和匀速运动模型作为模型集,通过实时交互使关联波门能够随目标机动动态调整,较好地兼顾了雷达计算耗时和跟踪成功率。在利用目标位置特征的基础上,进一步提取、整合目标运动特征,对关联波门交叉区域公共量测进行分类,使多交叉目标跟踪问题转化为多个单目标跟踪问题,优化了传统概率数据关联算法。仿真结果表明：与传统关联波门设计方法相比,算法跟踪失败率和计算耗时明显降低;而且在计算资源增加不大的情况下,杂波环境适应性也得到了显著增强。     

一种新的基于机动检测的机动目标跟踪算法

针对Kalman滤波跟踪机动目标发散和目前多数自适应Kalman滤波算法对运动模型适应性不强的问题,提出了一种新的基于机动检测的机动目标跟踪算法,通过实时自适应的改变滤波模型提高对机动目标跟踪精度。对这种方法与Kalman滤波算法进行了计算机仿真比较,结果表明,该方法计算量小,可实时精确地自适应匹配目标的运动模型,可实现对机动目标稳定可靠的跟踪。     

基于自适应Siamese网络的无人机目标跟踪算法

无人机已被广泛应用到军事和民用领域，目标跟踪是无人机应用的关键技术之一。针对无人机跟踪过程中目标易发生形变、遮挡等问题，提出一种基于自适应Siamese网络的无人机目标跟踪算法。首先，利用2个卷积网络构建一个5层Siamese网络，通过对模板特征与当前帧图像特征进行卷积得到目标位置；其次，利用高斯混合模型对以往的预测结果进行建模并建立目标模板库；然后，从模板库中挑选出最可靠的目标模板并以此更新Siamese网络的匹配模板，使Siamese网络能够自适应目标的外观变化；最后，引入回归模型进一步精确目标位置，降低背景对网络性能的影响。仿真实验结果表明：该算法有效降低了形变、遮挡等情况对跟踪性能的影响，具有较高的准确率。     

自由段弹道目标跟踪算法在工程中的应用

在对弹道目标跟踪预警的工程实践中,雷达系统对目标运动的信息处理速度尤为重要,因而,文章选取自适应跟踪模型与卡尔曼滤波相结合的方法解决自由段弹道目标的跟踪问题,并与扩展卡尔曼跟踪算法做了对比分析。仿真显示,2种滤波方式分别与自适应跟踪模型相结合后,卡尔曼滤波和扩展卡尔曼滤波跟踪性能相差不大,但其算法简单、运算时间短,可以较好满足自由段弹道目标跟踪的工程需求。     

The Tracking Index: A Generalized Parameter for ? ? ? and ? ? ? ? Target Trackers

A generalized, optimal filtering solution is presented for the target tracking problem. Applying optimal filtering theory to the target tracking problem, the tracking index, a generalized parameter proportional to the ratio of the position uncertainty due to the target maneuverability to that due to the sensor measurement, is found to have a fundamental role not only in the optimal steady-state solution of the stochastic regulation tracking problem, but also in the track initiation process. Depending on the order of the tracking model, the tracking index solution yields a closed form, consistent set of generalized tracking gains, relationships, and performances. Using the tracking index parameter, an initializing and tracking procedure in recursive form, realizes the accuracy of the Kalman filter with an algorithm as simple as the well-known ? ? ? filter or ? ? ? ? ? filter depending on the tracking order.     

基于IMMKF算法的ADS-B监视应用目标跟踪

目标跟踪是机载广播式自动相关监视（ADS-B）应用的基础功能,对提升航空器周边的弱机动民航飞机目标跟踪性能具有重要意义。提出一种基于交互式多模型卡尔曼滤波（IMMKF）算法的ADS-B 监视应用目标跟踪方法。首先,针对弱机动背景下的民航飞机的飞行特点,建立包含匀速模型和标准协同转弯模型的运动模型集,并对模型进行线性化近似;然后,将模型预测和ADS-B 状态矢量量测数据作为IMMKF 算法中多个并行卡尔曼滤波器的输入,进行并行滤波;最后,计算得到目标状态矢量的估计和模型近似概率,并作为下一次迭代的输入。结果表明：相比于基于匀速模型的卡尔曼滤波目标跟踪方法,IMMKF 方法的位置跟踪误差降低了59%,速度跟踪误差降低了77%,显著提升了状态估计性能,具备较高的跟踪精度、稳健性与计算效率,在ADS-B 监视应用中具有实际应用价值与借鉴意义。     

基于时空显著性建模的空中飞行器跟踪方法

以复杂背景下空中飞行器的鲁棒视觉跟踪问题为研究背景，为解决现有跟踪方法目标表征模型不够精确，算法鲁棒性严重受到目标形变、宽高比变化、复杂背景等因素干扰的问题，提出了建模跟踪场景中独立物体的显著性特性，用于构建精确的目标模型。提出的显著性估计方法有别于传统的单帧检测方法，利用跟踪算法提供的背景先验知识以及多帧图像观测数据，使用时空联合的方式进行建模估计，其结果用来指导目标跟踪算法选取有效视觉特征，建立精确目标表征模型，减小背景区域对算法模型的干扰。实验表明，提出的方法为上述难点问题提供了有效的解决方案，对空中飞行器的跟踪精度与鲁棒性优于大多数最先进的主流方法，在其他类型的目标跟踪任务中也有十分优越的性能表现。     

Interacting multiple model tracking with target amplitude feature

A recursive tracking algorithm is presented which uses the strength of target returns to improve track formation performance and track maintenance through target maneuvers in a cluttered environment. This technique combines the interacting multiple model (IMM) approach with a generalized probabilistic data association (PDA), which uses the measured return amplitude in conjunction with probabilistic models for the target and clutter returns. Key tracking decisions can be made automatically by assessing the probabilities of target models to provide rapid and accurate decisions for both true track acceptance and false track dismissal in track formation. It also provides the ability to accurately continue tracking through coordinated turn target maneuvers     

Modified input estimation technique using pseudoresiduals

An adaptive tracking filter for maneuvering targets is proposed using modified input estimation technique. Pseudoresiduals are defined using measurements and the velocity estimate at the hypothesized maneuver onset time. With the pseudoresiduals and a new target model representing transitions of nominal accelerations, a new input estimation method for tracking a maneuvering target is derived. Since the proposed detection technique is more sensitive to maneuvers than previous work, the shorter window length can be employed to detect and compensate target maneuvers. Also shown is that the tracking performance of the proposed filter is similar to that of interacting multiple model method (IMM) with 3 models, while computational loads of our method are drastically reduced     

Loopy belief propagation based data association for extended target tracking

The data association problem of multiple extended target tracking is very challenging because each target may generate multiple measurements. Recently, the belief propagation based multiple target tracking algorithms with high efficiency have been a research focus. Different from the belief propagation based Extended Target tracking based on Belief Propagation (ET-BP) algorithm proposed in our previous work, a new graphical model formulation of data association for multiple extended target tracking is proposed in this paper. The proposed formulation can be solved by the Loopy Belief Propagation (LBP) algorithm. Furthermore, the simplified measurement set in the ET-BP algorithm is modified to improve tracking accuracy. Finally, experiment results show that the proposed algorithm has better performance than the ET-BP and joint probabilistic data association based on the simplified measurement set algorithms in terms of accuracy and efficiency. Additionally, the convergence of the proposed algorithm is verified in the simulations.     

双星编队对空间非合作目标的仅测角跟踪方法

针对单星仅测角对目标跟踪误差较大和不良测量条件下跟踪精度下降的问题,提出利用编队卫星对非合作目标进行联合跟踪的方法。采用考虑地球非球形J2引力摄动的轨道动力学模型,建立多视线测量模型,融合编队卫星对目标的观测数据。然后,基于新息设计增益调节矩阵提高滤波器在测量故障条件下的鲁棒性。最后,建立仿真模型进行验证。仿真结果表明,相比单星跟踪,该方法的位置误差和速度误差分别减少了27.06%和26.96%。在系统存在异常量测时,相比常规滤波,该方法也具有更高的精确性和更好的鲁棒性。     

雷达低空目标俯仰角跟踪的C2算法研究

在单脉冲测角体制下,由于多径回波信号的干扰,极大地降低了雷达低空目标仰俯角跟踪精度,甚至丢失目标。通过对多路径反射环境模型分析,得出了岸、海基单脉冲雷达低空目标跟踪时仰俯角测量误差的产生原因,提出将传统的多目标分辨算法(C2算法)应用于低角多径环境下目标俯仰角的跟踪测量,并在不同多径反射环境下对不同高度、不同飞行速度和飞行方向的目标进行了仿真,得到良好的仿真结果,表明该算法可较大地提高俯仰角跟踪测量精度。通过对仿真结果的分析,验证了该算法在低空目标跟踪中的有效性和可行性。     

基于CDKF的快速协方差交叉融合跟踪算法研究

随着目标抗干扰能力的增强，单一寻的制导方式很难完成对目标的稳定跟踪和精确打击，需采用多种探测器作为传感器，提供多种观测数据以实现对目标的稳定跟踪和精确打击。建立了适当的目标运动模型和观测模型，利用中心差分卡尔曼滤波（CDKF）变换处理模型的非线性问题，避免了求解复杂的雅克比矩阵。对于分布式多传感器融合，传统的方法多采用协方差交叉（CI）融合方法，但是这类方法需要寻优求解。而快速协方差交叉（FCI）则不需要进行寻优过程，且计算量小。在此基础上，提出了用于多传感器目标跟踪的CDKF-FCI融合算法。最后，对算法进行了仿真分析，并进一步验证了提出算法的有效性。     

Low altitude target model for radar simulation

A simulation model of antenna array signals from a low altitude target is considered. Explicit expressions for statistical and spectral characteristics of the scattered signals are obtained in the Kirchhoff approximation. The model permits to evaluate the efficiency of different techniques of low altitude target tracking. It benefits the comprehension of the influence of multipath propagation on tracking radars     

一种基于三维到达角的无偏伪线性卡尔曼滤波

为了解决大场景下基于三维到达角的目标跟踪问题，提出了一种具有无偏性的伪线性卡尔曼滤波。首先，基于三维到达角信息对目标运动模型与量测模型进行建模；之后，对量测模型进行了伪线性化处理，得到了线性形式的目标量测模型。为了解决伪线性卡尔曼滤波存在的有偏性问题，提出了一种结合EKF（extend Kalman filter）的三维伪线性无偏卡尔曼滤波。仿真实验表明，该模型能够对非机动目标与机动目标有效跟踪，对于百公里级别的目标，当角测量误差从0.1°变化到0.5°，算法在仿真时间结束时均能将绝对位置误差降低至10 km以内，且算法的运行速度与EKF为同一个量级，同时兼顾了抗干扰能力、定位跟踪精度、运行效率的要求，能够为大场景下的目标跟踪提供有效方法。     

无人机跟踪运动目标航迹规划算法

对无人机跟踪运动目标的原理进行了分析,设计了跟踪系统的动力学模型,提出了一种基于切线法的航迹规划算法。在动力学约束条件下实现了对无人机的航迹、速度、加速度等的最优控制,从而解决了无人机跟踪运动目标问题,并给出了算法的具体设计步骤。仿真结果表明,该算法能够快速、有效地为无人机规划出跟踪运动目标的最优航迹。     

不完全量测下一类非线性光电跟踪系统滤波器设计

 随着不完全量测条件下探测概率的下降,传统光电跟踪系统的跟踪性能显著降低。为此,本文考虑将俯仰和偏航两个方向的角速度量测引入传统光电跟踪系统,并设计了不完全量测下基于置信度融合的目标跟踪滤波器。首先针对这类新型的光电跟踪系统建立了系统的量测模型,利用嵌套条件方法推导了转换量测误差前两阶矩的一致性估计;然后针对位置探测通道与角速度探测通道的4种数据探测情形设计了4个子滤波器,并根据探测通道的探测情况计算出各子滤波器的置信度,进而对各子滤波器的输出按置信度进行加权融合,得到了跟踪滤波器的全局输出;最后给出了非线性跟踪系统统计意义下的Cramer-Rao下界(CRLB)。Monte-Carlo仿真表明：在不完全量测下,相比传统光电跟踪系统,附加角速度量测的光电跟踪系统的跟踪性能有了显著提高,并且滤波器估计误差均方差(RMSE)已逼近非线性跟踪系统统计意义下的CRLB。     

Enhancements to a multiple model adaptive estimator/image-tracker

Three major enhancements to a previously devised multiple model adaptive estimator (MMAE) for target image tracking are developed and analyzed. These are: allowing some of the elemental filters to have rectangular fields of view and to be tuned for target dynamics that are harsher in one direction than others; considering both Gauss-Markov acceleration models and constant turn-rate models for target dynamics; and devising an initial target acquisition algorithm to remove important biases in the estimated target template to be used in a correlator within the tracker. Particularly good adaptation responsiveness is demonstrated in the multiple model algorithm's ability to handle harsh maneuver onset, yielding performance essentially equivalent to that of the best artificially informed tracking algorithm     

Multiple-Model Probability Hypothesis Density Filter for Tracking Maneuvering Targets

Tracking multiple targets with uncertain target dynamics is a difficult problem, especially with nonlinear state and/or measurement equations. With multiple targets, representing the full posterior distribution over target states is not practical. The problem becomes even more complicated when the number of targets varies, in which case the dimensionality of the state space itself becomes a discrete random variable. The probability hypothesis density (PHD) filter, which propagates only the first-order statistical moment (the PHD) of the full target posterior, has been shown to be a computationally efficient solution to multitarget tracking problems with a varying number of targets. The integral of PHD in any region of the state space gives the expected number of targets in that region. With maneuvering targets, detecting and tracking the changes in the target motion model also become important. The target dynamic model uncertainty can be resolved by assuming multiple models for possible motion modes and then combining the mode-dependent estimates in a manner similar to the one used in the interacting multiple model (IMM) estimator. This paper propose a multiple-model implementation of the PHD filter, which approximates the PHD by a set of weighted random samples propagated over time using sequential Monte Carlo (SMC) methods. The resulting filter can handle nonlinear, non-Gaussian dynamics with uncertain model parameters in multisensor-multitarget tracking scenarios. Simulation results are presented to show the effectiveness of the proposed filter over single-model PHD filters.