Tracking in Wireless Sensor Networks Using Particle Filtering: Physical Layer Considerations

In this paper, a new framework for target tracking in a wireless sensor network using particle filters is proposed. Under this framework, the imperfect nature of the wireless communication channels between sensors and the fusion center along with some physical layer design parameters of the network are incorporated in the tracking algorithm based on particle filters. We call this approach ldquochannel-aware particle filtering.rdquo Channel-aware particle filtering schemes are derived for different wireless channel models and receiver architectures. Furthermore, we derive the posterior Cramer-Rao lower bounds (PCRLBs) for our proposed channel-aware particle filters. Simulation results are presented to demonstrate that the tracking performance of the channel-aware particle filters can reach their theoretical performance bounds even with relatively small number of sensors and they have superior performance compared to channel-unaware particle filters.     

Target Tracking by Particle Filtering in Binary Sensor Networks

We present particle filtering algorithms for tracking a single target using data from binary sensors. The sensors transmit signals that identify them to a central unit if the target is in their neighborhood; otherwise they do not transmit anything. The central unit uses a model for the target movement in the sensor field and estimates the target's trajectory, velocity, and power using the received data. We propose and implement the tracking by employing auxiliary particle filtering and cost-reference particle filtering. Unlike auxiliary particle filtering, cost-reference particle filtering does not rely on any probabilistic assumptions about the dynamic system. In the paper, we also extend the method to include estimation of constant parameters, and we derive the posterior Cramer-Rao bounds (PCRBs) for the states. We show the performances of the proposed methods by extensive computer simulations and compare them to the derived bounds.     

基于分层采样粒子滤波的麦克风阵列说话人跟踪方法

针对噪声与混响环境下的说话人跟踪问题,本文提出了一种基于粒子滤波的麦克风阵列声源定位与跟踪方法.该方法在粒子滤波框架下,将无混响影响的语音建立信号作为观测信息,通过计算麦克风阵列波束形成器的输出能量来构建似然函数,同时考虑语音信号不同频率成分在声源定位中的作用,利用分层采样方法提高粒子的采样效率.实验结果表明,本文方法提高了说话人声源跟踪系统的抗噪声与抗混响能力.     

基于粒子滤波的蜂窝网移动台单站跟踪

仅使用单个基站测量信息对蜂窝网移动台进行定位跟踪实现简单并具有较高的可定位概率,但面临的挑战是如何提高定位精度。粒子滤波是基于贝叶斯推论的一种蒙特卡洛方法,特别适用于非线性非高斯信号处理。该文提出了基于粒子滤波的单站跟踪算法。仿真结果表明与快拍式定位方法相比,这种滤波算法大大提高了单站定位的精度;与扩展卡尔曼滤波相比,粒子滤波收敛速度快,性能稳健。     

单站被动目标的多假设距离粒子滤波跟踪

针对单站被动目标跟踪的无距离信息,多假设距离粒子滤波方法利用多个粒子滤波的并行运算,对不同初始距离的粒子滤波器进行计算,利用各子滤波的残差概率对并行处理的粒子滤波运算进行自适应采样实现单站纯方位目标跟踪,并与粒子滤波、多假设距离滤波方法进行比较,仿真结果表明该算法收敛速度快,跟踪精度高。     

Modeling Mobility Tracking Procedures in PCS Systems Using Stochastic Activity Networks

In this paper the capability of stochastic activity networks (SANs) has been used as a novel approach in the analysis of mobility tracking procedures. To evaluate complex systems such as cellular systems, powerful tools for modeling and analysis are required. SANs have proved to be very flexible and powerful tools in the study of location update (LU) and paging (PG) schemes. SANs can capture, in a simple manner and from the mobility models under study, much more detail than Markov models. Therefore, the analysis of mobility tracking procedures with SANs provides more accuracy than the use of Markov models. This fact is illustrated in the paper by considering the LU and PG schemes proposed in Ref. [12]. Furthermore, our results show a much better performance of these schemes than that predicted by Ref. [12].     

Saliency Combined Particle Filtering for Aircraft Tracking

Multimedia event detection has become a popular research topic due to the explosive growth of video data. The motion features in a video are often used to detect events because an event may contain some specific actions or moving patterns. Raw motion features are extracted from the entire video first and then aggregated to form the final video representation. However, this video-based representation approach is ineffective when used for realistic videos because the video length can be very different and the clues for determining an event may happen in only a small segment of the entire video. In this paper, we propose using a segment-based approach for video representation. Basically, original videos are divided into segments for feature extraction and classification, while still keeping the evaluation at the video level. The experimental results on recent TRECVID Multimedia Event Detection datasets proved the effectiveness of our approach.     

改进的粒子滤波人体目标跟踪算法

针对现有基于粒子滤波(PF)的行人目标跟踪算法跟踪精度不高、速度慢以及遮挡鲁棒性不好的问题,提出一种结合支持向量机(SVM)检测的改进跟踪算法。在跟踪的置信度小于阈值时进行行人跟踪目标的再检测,以校正跟踪位置。对粒子群优化(PSO)算法在优化时可能陷入局部解的现状,进行混沌粒子优化(CPSO)寻优全局解。实验结果表明,提出的算法在一定的粒子数目前提下精度优于其他基于粒子滤波的行人目标跟踪算法,有效降低PF所需粒子数,算法可实时跟踪。     

粒子滤波在机动目标纯方位跟踪中的应用

文章将多模粒子滤波算法用于机动目标纯方位跟踪，通过估计模型的概率而不是寻找最优算法去进行局部线性化和表征非高斯后验密度，从而减小了近似误差。在仿真研究中，与IMM—EKF的比较验证了多模粒子滤波处理机动目标纯方位跟踪问题的优越性。     

正则化粒子滤波在水下目标跟踪中的应用

针对传统卡尔曼滤波(KF)及扩展卡尔曼滤波(EKF)在非线性目标跟踪模型中,跟踪精度较差的问题,本文给出了一种基于正则化粒子滤波(RPF)的水下目标跟踪算法。文中在一种模拟水下目标跟踪环境的非线性动态模型中对所提出的算法进行了仿真试验,并将其跟踪性能与扩展卡尔曼滤波和标准粒子滤波算法(PF)进行了比较。仿真结果表明,PF算法比EKF算法滤波精度更高,RPF的跟踪性能优于PF和RPF,而且随着粒子数的增加,PF和RPF的跟踪性能也不断提高。     

分布式粒子滤波算法在面向跟踪的无线传感器网络中的应用

无线传感器网络在目标跟踪应用中的优势主要体现在跟踪更精细可靠且及时隐蔽,但是由于传感器网络中没有中心控制机制,无线通信的带宽有限,这就要求采用合理的跟踪策略,高效的分布式信息处理算法。将“ad hoc跟踪群”的概念移植到面向跟踪的无线传感器网络中作为传感器的组织策略,并和适用范围较大的粒子滤波相结合实现跟踪任务。仿真实验证明,在不影响跟踪精度要求的情况下,此方案能够降低通信能量开销。     

基于粒子滤波改进的行人跟踪算法

为了提高汽车安全辅助驾驶技术和减少道路交通事故,根据行人运动变化特点,对基于粒子滤波的跟踪算法进行改进,提出一种新的行人跟踪算法.通过将空间距离中心加权和相关信息相结合的颜色直方图的观测模型方法,实现行人目标跟踪.实验结果表明,与基于HSV空间颜色直方图的粒子滤波跟踪算法相比,该算法有效解决复杂背景下局部遮挡和全遮挡问题,并在鲁棒性方面明显地优于前一种算法.     

基于粒子滤波的交互式多模型说话人跟踪方法

 本文提出一种基于采样交互的多模型粒子滤波方法,实现了对随意运动说话人的有效跟踪。该方法根据说话人跟踪问题的特点,用马尔可夫跳变系统描述说话人的动态特性,用粒子滤波方法估计说话人的位置。在说话人跟踪过程中,通过调整滤波粒子的采样区域,完成交互式多模型方法中的输入交互,这不仅实现了各子滤波器中粒子数目的任意设定,避免了模型转换过程中的性能退化现象,而且取消了对模型后验概率密度函数的高斯分布假定,增强了说话人跟踪系统的鲁棒性。计算机仿真实验结果验证了本文方法的有效性。     

粒子优化组合的粒子滤波跟踪算法研究

为了改善运动目标跟踪问题中粒子滤波算法(PF)的估计精度,针对粒子滤波出现样本退化以及样本贫乏问题,提出了一种基于粒子优化组合的粒子滤波算法(POCPF)。该算法用一能使粒子朝后验概率分布值较大的区域运动的似然函数来改善粒子的位置,然后重估粒子的权值对粒子进行优化组合,满足粒子的多样性要求,从而克服了粒子的贫乏问题,在一定程度上减少系统状态为达到精确度所需的粒子数目,缩短运行时间。通过仿真实验证明了POCPF算法的有效性,当粒子数相同时,POCPF算法性能优于PF算法。     

被动传感器阵列中基于粒子滤波的目标跟踪

针对被动传感器阵列中的机动目标跟踪问题,该文提出了一种基于多模Rao-Blackwellized粒子滤波的机动目标跟踪新方法。算法首先基于Rao-Blackwellization理论将机动目标跟踪问题划分为模型选择和目标跟踪两个子问题;采用多模Rao-Blackwellized粒子滤波对目标运动模型进行选择,扩展Kalman滤波对目标进行更新,有效降低了抽样粒子状态维数,节省了计算时间;最后,建立了被动传感器阵列的非线性观测模型。实验结果表明,提出方法可以有效地对目标模型进行选择,算法的跟踪性能及稳定性要好于交互多模型(IMM)方法。     

远距离纯方位跟踪的改进粒子滤波算法

粒子滤波是一种基于蒙特卡罗采样和递推贝叶斯估计的滤波方法,不受模型非线性和非高斯噪声的限制,因而被用于各种非线性滤波和参数估计问题。但是对于先验信息较少和信噪比较低的问题,其庞大的计算量和缓慢的速度限制了它在实时系统中的应用。这里介绍了粒子滤波基本原理,通过改进权重计算、重采样算法,使计算速度得到提高。这种改进算法用于对海洋远距离纯方位目标进行跟踪仿真,其结果表明,具有速度快,精度高的特点。     

蜂窝网络中环状搜索移动性管理策略

位置管理是移动通信领域的一个具有挑战性的问题,涉及到位置更新和位置查找操作.在现行蜂窝系统的位置管理策略(简称"基本策略")中,一旦移动台越区,就需要进行位置更新.由于移动台的越区具有局部性,基本策略会造成系统资源的极大浪费.因此,降低位置管理的费用成为移动通信领域的一个研究热点.该文给出不需要进行位置更新的环状搜索位置管理策略(简称"环状策略"),并推导出搜索位置区平均层数的一个公式,然后利用这一公式对基本策略、指针推进策略与环状策略的费用进行了对比研究,得出:在一定条件下,环状策略的费用要比基本策略及基本指针推进策略小.     

Distributed Mobility Management for Target Tracking in Mobile Sensor Networks

Mobility management is a major challenge in mobile ad hoc networks (MANETs) due in part to the dynamically changing network topologies. For mobile sensor networks that are deployed for surveillance applications, it is important to use a mobility management scheme that can empower nodes to make better decisions regarding their positions such that strategic tasks such as target tracking can benefit from node movement. In this paper, we describe a distributed mobility management scheme for mobile sensor networks. The proposed scheme considers node movement decisions as part of a distributed optimization problem which integrates mobility-enhanced improvement in the quality of target tracking data with the associated negative consequences of increased energy consumption due to locomotion, potential loss of network connectivity, and loss of sensing coverage.     

基于改进粒子滤波算法的纯方位目标跟踪

纯方位目标跟踪是一个重要的研究课题。它要解决的问题是:利用含有噪声的方位数据来估计目标的真实运动轨迹。本文提出了一种基于粒子群优化的改进粒子滤波算法。这种算法可以将最新的观测值引入观测估计,提高了预估精度,减少所需的粒子数,从而实现对目标真实运动轨迹更好的跟踪。     

一种改进粒子滤波的双站无源定位跟踪算法

在非线性非高斯状态空间下，粒子滤波器是一种有效的非线性滤波算法，它的关键问题包括粒子权重的计算、粒子重采样和状态估计等。本文根据粒子滤波算法思想和双站无源定位跟踪的非线性，将粒子滤波算法用于双站无源定位跟踪问题，给出了一种改进的粒子滤波算法，并对其关键问题根据双站无源定位跟踪的特殊性进行了改进。利用Matlab进行了仿真实验，与最小二乘算法、扩展卡尔曼滤波算法进行了比较，结果表明所提算法定位跟踪精度优于其他方法。