一种用于机动目标跟踪的新自适应卡尔曼滤波算法

在“当前”模型的概念下,从工程实现的背景出发,提出了一种用于机动目标跟踪的新自适应卡尔曼滤波算法。基本思想是通过对加速度项引入加权因子来进一步突出“当前”信息的作用,为“当前”模型提供更加准确的“当前”信息。蒙特卡罗模拟结果表明,算法不仅克服了“当前”模型自适应卡尔曼滤波算法的缺陷,而且使跟踪性能得到进一步的提高。     

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。     

基于神经网络的机动目标信息融合与并行自适应跟踪

基于“当前”统计模型和 BP神经网络 ,提出一种新的机动目标神经网络信息融合与并行自适应跟踪算法 ( NIFPAT)。该算法采用双滤波器并行结构 ,利用全状态反馈 ,通过 BP网络调整系统方差以适应目标的运动变化 ,具有对目标各种运动状态的良好自适应跟踪能力     

多坐标系下目标跟踪的联合滤波

针对雷达目标观测和处理在不同的坐标系下完成，本文提出了联合滤波算法来跟踪机动目标。该算法以卡尔曼滤波器为基础，直角坐标系下和极坐标系下的算法相联合，不仅克服了两种坐标系下滤波算法的不足，而且对机动目标有很好的跟踪效果。仿真实验结果表明了该算法的有效性。     

Jerk模型用于高速机动飞行器跟踪的性能分析

针对高速机动飞行器的跟踪应用,对SJ(Singer Jerk)、CSJ(当前统计Jerk)、MCSJ(修正当前统计Jerk)和αJ等4种主要Jerk模型进行了综述。比较了它们的建模假设、设计参数以及实际应用时的限制因素。基于UKF(无迹卡尔曼滤波)算法,分别在单台和2台雷达的测量条件下,在3种滤波参数集设置下,利用各模型对近空高速滑翔飞行器进行了跟踪仿真。飞行器真实飞行轨迹根据简化动力学方程通过四阶龙格库塔数值积分方法得到。仿真结果表明:4种模型都具有很好的初值鲁棒性;在目标弱机动段落,4种模型具有较好的参数鲁棒性;但在强机动段落,SJ、CSJ、MCSJ等3种模型的参数鲁棒性很差,滤波误差发生严重突跳,αJ模型的参数鲁棒性最好。针对高速机动飞行器的跟踪应用,αJ模型的综合性能最优,而MCSJ模型最差。     

用于非线性跟踪问题的一种新的粒子滤波器

机动目标跟踪系统通常是非线性而且不完全观测的 ,所以问题的关键在于每一时刻的目标机动性都是高度不确定的。提出了一种新的平滑粒子滤波算法 ,该算法在粒子滤波器中加入了对系统模型的概率分布密度的平滑处理 ,从而很好的解决了目标的机动性估计问题。在仿真研究中 ,与辅助粒子滤波器的比较验证了本文算法处理非线性跟踪问题的优越性     

机动目标的模型与跟踪算法

 <正> 在机动目标的“当前”统计模型中,目标的加速度被描述为修正的瑞利—马尔科夫过程,对应的自适应跟踪算法呈现出较好的跟踪特性。文献[2]研究了该模型及其自适应算法在实际的机载雷达跟踪系统的应用;文献[3]进一步推广了基于“当前”模型的MPDAF算法。本文提出一个新的机动目标模型,即假定目标加速度为一高斯—马尔     

利用非线性优化滤波器跟踪图象序列中的小目标

研究一种基于相关技术的自适应跟踪装置。这种跟踪装置使用判别式非线性滤波器，对于噪声、背景和物体失真具有更好的Robust性。计算机模拟显示出了小目标跟踪的试验结果。在对相关面不进行处理的条件下展示了跟踪装置的良好的性能。研究出的算法在众所周知的线形滤波器失效的情况下也能发挥作用。     

基于期望系统噪声模型的自适应机动目标跟踪

针对防空作战中的机动目标跟踪问题,分析了使用IMM算法跟踪目标所存在的缺陷,提出了一种基于期望系统噪声模型的自适应机动目标跟踪算法（MIMM）,改变IMM算法使用固定模型集合的方法,IMM算法中作用权重较大的只是少部分更接近于实际系统的模型,通过对部分系统噪声模型进行自适应辨识,计算出最接近于系统实际噪声水平的模型——期望系统噪声模型（ESNM）。这些模型作为IMM多模型集的子集,是在一定模型框架内所寻求出的一个（或多个）最优模型（集）。仿真结果证明了MIMM算法能够更好地描述目标机动,达到更理想的跟踪性能,其跟踪精度优于使用固定模型集的IMM算法。     

一类新型的机动目标跟踪算法

针对机动目标跟踪,提出了基于截断正态概率模型的改进自适应目标跟踪算法,该算法具有结构和计算简单,鲁棒性好的特点,通过仿真结果对比,充分说明了文中所提出的跟踪算法能够较好地弥补传统的Kalman滤波方法在跟踪机动目标时的不足。     

Adaptive Tracking Filter for Maneuvering Targets

A general method of continually restructuring an optimum Bayes-Kalman tracking filter is proposed by conceptualizing a growing tree of filters to maintain optimality on a target exhibiting maneuver variables. This tree concept is then constrained from growth by quantizing the continuously sensed maneuver variables and restricting these to a small value from which an average maneuver is calculated. Kalman filters are calculated and carried in parallel for each quantized variable. This constrained tree of several parallel Kalman filters demands only modest om; puter time, yet provides very good performance. This concept is implemented for a Doppler tracking system and the performance is compared to an extended Kalman filter. Simulation results are presented which show dramatic tracking improvement when using the adaptive tracking filter.     

An Adaptive Two-Dimensional Kalman Tracking Filter

A continuously adaptive two-dimensional Kalman tracking filter for a low data rate track-while-scan (TWS) operation is introduced which enhances the tracking of maneuvering targets. The track residuals in each coordinate, which are a measure of track quality, are sensed, normalized to unity variance, and then filtered in a single-pole filter. The magnitude Z of the output of this single-pole filter, when it exceeds a threshold Z1 is used to vary the maneuver noise spectral density q in the Kalman filter model in a continuous manner. This has the effect of increasing the tracking filter gains and containing the bias developed by the tracker due to the maneuvering target. The probability of maintaining track, with reasonably sized target gates, is thus increased, The operational characteristic of q versus Z assures that the tracker gains do not change unless there is high confidence that a maneuver is in progress.     

一类新型机动目标跟踪算法

阐述了当跟踪非机动目标时,传统的Kalman滤波可以得到很好的跟踪精度。但是当日标机动时,传统的Kalman滤波不能对目标的突然变化做出及时的改正和预测,因此跟踪精度很差,甚至出现丢失目标的情况。文中采用的基于截断正态概率模型的改进自适应目标跟踪算法, 其结构和计算简单,鲁棒性好,较好地解决了使用Kalman滤波带来的不足。     

Unsupervised Tracking of Maneuvering Vehicles

The design of adaptive filters for the tracking of high-performance maneuvering targets is a fundamental problem in real-time surveillance systems. As is well known, a filter which provides heavy smoothing can not accurately track an evasive maneuver, and conversely. Consequently, one is led to the consideration of adaptive methods of filter design. This paper presents an improved self-adaptive filter algorithm for on-line solution of the above problem. Basically, this algorithm utilizes the orthogonality property of the residual time series to force the filter to automatically track the optimal gain levels in a changing environment.     

Modeling and Estimation for Tracking Maneuvering Targets

A new approach to the three-dimensional airborne maneuvering target tracking problem is presented. The method, which combines the correlated acceleration target model of Singer [3] with the adaptive semi-Markov maneuver model of Gholson and Moose [8], leads to a practical real-time tracking algorithm that can be easily implemented on a modern fire-control computer. Preliminary testing with actual radar measurements indicates both improved tracking accuracy and increased filter stability in response to rapid target accelerations in elevation, bearing, and range.     

单天基平台测向的空间非合作目标跟踪

针对仅含角度测量信息的单个天基平台可观测性较弱的问题,提出了一种含脉冲机动检测的空间非合作目标跟踪算法,并设计了非合作目标实时跟踪数据处理流程.该算法利用抗差估计技术和UKF（Unscented Kalman Filter,无迹卡尔曼滤波）算法构造目标跟踪滤波器,并综合残差多项式拟合和新息分布特征等方法实现目标机动检测,在天基平台观测信息类型有限和观测几何较差的情况下,可以同时排除孤立野值和成片测量野值的影响,实现非合作机动目标的连续稳定跟踪.数值实验验证了算法的可行性和有效性,也表明了跟踪精度和可靠性与测量精度密切相关.     

Tracking a Maneuvering Target Using Input Estimation

The conventional Kalman tracking filter incurs mean tracking errors in the presence of a pilot-induced target maneuver. Chan,Hu, and Plant proposed a solution to this problem which used themean deviations of the residual innovation sequence to make corrections to the Kalman filter. This algorithm is further developedhere for the case of a one-dimensional Kalman filter, for which an Implementable closed-form recursive relation exists. Simulation results show that the Chan, Hu, and Plant method can accurately detect and correct an acceleration discontinuity under a variety of maneuver models and radar parameters. Also, the inclusion of thislogic into a multiple hypothesis tracking system is briefly outlined.     

Tracking a maneuvering target using sensors of variable quality

In an environment subject to sudden change, the accuracy of tracking and prediction is strongly influenced both by the sensor architecture and by the quality of the sensors. An image-enhanced algorithm is presented for both path following and covariance estimation in applications where the sensors are subject to sudden and unpredictable variation in quality. For an illustrative trajectory, the performance of the algorithm is contrasted with an extended Kalman filter (EKF) and an image-enhanced algorithm based upon the nominal sensors