Energy-balanced multiple-sensor collaborative scheduling for maneuvering target tracking in wireless sensor networks

An energy-balanced multiple-sensor collaborative scheduling is proposed for maneuvering target tracking in wireless sensor networks (WSNs). According to the position of the maneuvering target, some sensor nodes in WSNs are awakened to form a sensor cluster for target tracking collaboratively. In the cluster, the cluster head node is selected to implement tracking task with changed sampling interval. The distributed interactive multiple model (IMM) filter is employed to estimate the target state. The estimat...     

Interacting multiple model filter-based distributed target tracking algorithm in underwater wireless sensor networks

This paper deals with the problem of accurately tracking a single target, which has various trajectories, moving through the environment of underwater wireless sensor networks (UWSNs). This paper addresses the issues of estimating the states of the target, improving energy efficiency by using a distributed architecture. Each underwater wireless sensor node composing the UWSNs is battery-powered, so the energy conservation problem is a critical issue. This paper provides algorithms increasing the energy efficiency of each sensor node by using the proposed Wake-Up/Sleep (WUS) scheme. An interacting multiple model (IMM) filter is applied to the proposed distributed architecture in order to cope with a target maneuver. Simulation results illustrate the performance of the proposed tracking filter according to the various target maneuver patterns.     

Local node selection for target tracking based on underwater wireless sensor networks

Traditional sonar-array-based target tracking algorithms may be unsuitable for on-demand tracking missions, since they assume that the sonar arrays should be towed or mounted by a submarine or a ship. Alternatively, underwater wireless sensor networks can offer a promising solution approach. First, each underwater node is battery-powered, so saving energy expenditure is a critical issue. Instead of keeping all sensor nodes active, this paper provides a local node selection (LNS) scheme which increases energy efficiency by waking up only a small part of nodes at each time. Second, considering node's limited computing ability and the real-time requirement for the tracking algorithm, instead of employing the centralised fusion structure, we utilise the distributed Kalman filtering fusion with feedback in this paper. Finally, instead of assuming one sensor node can uniquely determine target's location, a more practical range-only measurement model is proposed. Then the LNS scheme and distributed fusion with feedback are extended to our range-only measurement model. The simulation results demonstrate the efficiency of our scheme.     

传感器网络下机动目标动态协同跟踪算法

对传感器网络下的机动目标跟踪问题提出一种分布式传感器节点动态分簇、协同跟踪算法. 通过在线优化目标跟踪的性能函数和通讯代价, 自适应地选择节点并动态分簇, 通过多传感器节点的协同感知以及信息融合提高了跟踪精度. 由于问题的非线性和传感器节点的随机性, 本文基于粒子滤波器在线预测和估计目标状态的概率分布, 使用混合高斯粒子滤波器以及选择最短路径用于传感器节点之间的信息交换节约了通讯能量, 通过一种有效的粒子方法逼近目标状态的预测方差以实现传感器节点的最优选择. 仿真结果表明, 与 IDSQ 算法相比较, 本文提出的动态分簇算法实现了对机动目标的高精度跟踪.     

多特征分层融合的相关滤波鲁棒跟踪

目的 为提高目标跟踪的鲁棒性,针对相关滤波跟踪中的多特征融合问题,提出了一种多特征分层融合的相关滤波鲁棒跟踪算法。方法 采用多通道相关滤波跟踪算法进行目标跟踪时,从目标和周围背景区域分别提取HOG（histogram of oriented gradient）、CN（color names）和颜色直方图3种特征。提出的分层融合算法首先采用自适应加权融合策略进行HOG和CN特征的特征响应图融合,通过计算特征响应图的平滑约束性和峰值旁瓣比两个指标得到融合权重。将该层融合结果与基于颜色直方图特征获得的特征响应图进行第2层融合时,采用固定系数融合策略进行特征响应图的融合。最后基于融合后的响应图估计目标的位置,并采用尺度估计算法估计得到目标更准确的包围盒。结果 采用OTB-2013（object tracking benchmark 2013）和VOT-2014（visual object tracking 2014）公开测试集验证所提跟踪算法的性能,在对多特征分层融合参数进行分析的基础上,与5种主流基于相关滤波的目标跟踪算法进行了对比分析。实验结果表明,本文算法的目标跟踪精度有所提高,其跟踪精度典型值比Staple算法提高了5.9%（0.840 vs 0.781）,同时由于有效地融合了3种特征,在多种场景下目标跟踪的鲁棒性优于其他算法。结论 提出的多特征分层融合跟踪算法在保证跟踪准确率的前提下,跟踪鲁棒性优于其他算法。当相关滤波跟踪算法采用了多个不同类型特征时,本文提出的分层融合策略具有一定的借鉴性。     

一种高跟踪质量保证的预先节点选择策略

为保证传感器网络节点高质量的目标跟踪效果,采用在目标移动的方向上提前选择一些节点进行监控的策略,保证当目标移动到新的位置时总有监测节点进行持续的监测,使这些监测节点总是离目标最近,感知质量最高;该策略依据网络能量消耗的不均衡性,在能量有剩余的区域提前唤醒更多的节点,而在能量消耗紧张的区域少唤醒节点,与其他策略相比并没有降低网络寿命。通过实验性能分析对比表明：该策略可以在不降低网络寿命的前提下大幅度提升跟踪质量。     

Key distribution scheme for peer-to-peer communication in mobile underwater wireless sensor networks

Wireless Sensor Networks (WSN) consist of small battery-limited devices called sensor nodes. The communication between sensor nodes is a type of peer-to-peer communication, since each node has the same capability and role. One of the recent application areas of these nodes is underwater sensing. Communication in Underwater Wireless Sensor Networks (UWSN) is challenging since radio frequencies cannot be used. Instead acoustic waves, which cause extra challenges, are used in UWSN. Since UWSNs are deployed in hostile environment, nodes can be captured by an adversary. In order to secure UWSNs, key distribution problem must be addressed. Moreover, UWSNs are inherently mobile since the nodes may be drifted in the sea. In this paper, we propose a key distribution model which is applied for two group mobility models, namely nomadic mobility model and meandering mobility model. In both schemes hierarchical structure is used and communication is handled via well-known Blom’s key distribution scheme. Our simulation results show that mobility causes some temporary decreases in the connectivity, but our schemes help to heal the connectivity performance in time. Moreover, our schemes show good resiliency performance such that capture of some nodes by an adversary only causes very small amount of links between uncaptured nodes to be compromised.     

基于多模型航迹质量的融合算法

如何确定最优加权因子是加权航迹融合算法中一个值得深入研究的问题。通过提出多模型航迹质量(Track Quality with Multiple Model, TQMM)的概念,并给出一种带信息反馈的加权航迹融合算法,来解决多传感器跟踪同一目标时的权值最优分配问题。系统引入反馈机制,利用多模型航迹质量确定权值,能够精确地更新权值,从而实时有效地进行目标跟踪。仿真结果表明,与已有的加权融合算法相比,该算法具有更好的跟踪性能,特别是在融合系统传感器观测精度相差较大的情况下,算法的跟踪效果更为突出;并且,随着传感器数目的增加,系统的跟踪精度逐步提高,但当传感器增加到一定数目时,系统的融合精度并没有得到明显的改善。     

An adaptive information dissemination of decentralized warship cooperative engagement with constrained bandwidth based on a geodetic coordinate system

The main objective of this paper is to analyze models, techniques, algorithms and infrastructures needed to complete cooperative engagement for warships with constrained bandwidth based on the geodetic coordinate system. To increase the performance of maneuvering target tracking, the 2D and 3D target motion models and the observation model based on the geodetic coordinate system are derived. In order to cope with the target tracking and fusion problems which arise from the intense non-linearity and decentralization in a geodetic coordinate system, two decentralized fusion algorithms denoted as SR-UKF (TR) and SR-UKF (CI) which we developed before are used. Considering the limited bandwidth of the communication network in a battle environment, an adaptive selection scheme which captures the competitive and cooperative relations among the neighbor sensor nodes is developed for decentralized information dissemination. The simulation results show the efficiency, adaptivity and robustness of the proposed algorithms with high precision.     

Range-free 3D node localization in anisotropic wireless sensor networks

In this paper, we propose two computationally efficient ‘range-free’ 3D node localization schemes using the application of hybrid-particle swarm optimization (HPSO) and biogeography based optimization (BBO). It is considered that nodes are deployed with constraints over three layer boundaries, in an anisotropic environment. The anchor nodes are randomly distributed over the top layer only and target nodes distributed over the middle and bottom layers. Radio irregularity factor, i.e., an anisotropic property of propagation media and heterogenous properties of the devices are considered. To overcome the non-linearity between received signal strength (RSS) and distance, edge weights between each target node and neighboring anchor nodes have been considered to compute the location of the target node. These edge weights are modeled using fuzzy logic system (FLS) to reduce the computational complexity. The edge weights are further optimized by HPSO and BBO separately to minimize the location error. Both the proposed applications of the two algorithms are compared with the earlier proposed range-free algorithms in literature, i.e., the simple centroid method and weighted centroid method. The results of our proposed applications of the two algorithms are better as compared to centroid and weighted centroid methods in terms of error and scalability.     

A cross-layer transmission scheduling scheme for wireless sensor networks

In a wireless sensor network, the sensor nodes are densely deployed for detecting in many cases. One design challenge for such a network is how to devise a good data fusion algorithm for information retrieval. Noting that the channel state information (CSI) between the cluster head and the sensor nodes will influence the received bit energy noise ratio of the sensor nodes, we propose an optimal data fusion algorithm taking into account the CSI for a one-hop clustered wireless sensor network. On the basis of the fusion algorithm, we consider the redundancy of the sensor deployment and propose a cross-layer transmission scheduling scheme. By selecting proper set of sensor nodes to transmit their local information back in turn, the scheme can prolong the lifetime of the sensor network. The numerical and simulation results show that it can get a good tradeoff between the energy efficiency and the performance.     

多模态视觉跟踪方法综述

目标跟踪是计算机视觉研究中的前沿和热点问题,在安全监控、无人驾驶等领域中有着重要的应用价值。然而,目前基于可见光数据的视觉跟踪方法,在光照变化、恶劣天气下因数据质量受限难以实现鲁棒跟踪。因此,一些研究者提出了多模态视觉跟踪任务,通过引入其他模态数据,包括红外模态、深度模态、事件模态以及文本模态,在一定程度上弥补了可见光模态在恶劣天气、遮挡、快速运动和外观歧义等条件下的不足。多模态视觉跟踪旨在挖掘可见光和其他模态数据的互补优势,在视频中实现鲁棒的目标定位,对全天时全天候感知有着重要的价值和意义,受到越来越多的研究和关注。由于主流的多模态视觉跟踪方法针对可见光—红外跟踪展开,因此,本文以阐述可见光—红外跟踪方法为主,从信息融合的角度将现有方法划分为结合式融合和判别式融合,分别进行了详细介绍和分析,并对不同类方法的优缺点进行了分析和比较。然后,本文对其他多模态视觉跟踪任务的研究工作进行了介绍,并对不同多模态视觉跟踪任务的优缺点进行了分析和比较。最后,本文对多模态视觉跟踪方法进行了总结并对未来发展进行展望。     

分布式动态一致性非线性目标跟踪策略研究

针对集中目标跟踪和分层目标跟踪中心节点通信瓶颈以及容错性能差的不足, 提出了一种分布式动态一致性非线性目标跟踪策略。目标状态初始化由网络节点采用加权最小二乘法完成。整个跟踪过程采用动态成簇策略, 分阶段选择并唤醒任务节点检测目标并执行分布式一致性扩展卡尔曼滤波策略完成目标的状态估计, 其余节点进入休眠状态从而能降低系统的能耗。从跟踪误差和能量两个方面, 与集中目标跟踪算法相比, 仿真结果表明所提算法与集中卡尔曼滤波相比, 跟踪精度相当, 适用于要求高可靠度的非线性跟踪。此外分布式的工作方式使得节点仅需与邻居交换数据并在局部完成状态估计, 消除集中式结构中心节点的瓶颈, 以保证部分传感器节点的损坏不会影响到全局任务的完成。     

无线传感器网络中一种新的分布式定位方案研究

Node localization in wireless sensor networks (WSN) is treated as a functional dual of target tracking from a novel perspective in the paper. Different from the traditional tracking problem in WSN, using the static location-ware node to estimate the moving target, the mobile node is used to help unknown nodes to accurately discover their positions. A new node localization scheme virtual beacons-energy ratios localization (VB-ERL) and its refinements for the WSN are presented. In the scheme, the mobile node moves in the surveillant field based on the Gauss-Markov mobility model and periodically broadcasts the information packets. Each static unknown node receives the virtual beacons and energy in its sensing range, and estimates its location by finding the intersection of a set of hyper-spheres. Simulation results show the proposed scheme is efficient.     

水下传感器网络中的多路径路由技术研究

水下声信道是一种复杂信道,由于各方面因素影响,在数据传输过程中,水下传感器网络数据链路层会有可能产生随机中断.研究了一种虚拟汇聚节点的多路径水下传感器网络路由技术,在随机布设的传感器节点中选取了缓存节点,并创建了局部的汇聚节点,通过多路径的路由技术,有效减少了网络吞吐率受链路中断的影响,并且避免了汇聚节点处的数据冲突.通过网络的冗余性,增强了网络稳定性、鲁棒性.     

基于像素级图像融合的Mean Shift目标跟踪

针对可见光、红外单模图像序列进行Mean Shift目标跟踪时存在的问题,提出了先对可见光、红外图像序列进行像素级动态图像融合,采用加权平均融合和基于区域目标检测的图像序列融合框架,再对融合结果进行Mean Shift目标核函数直方图建模,然后进行匹配跟踪。实验采用了实际图像序列。实验结果表明,针对目标进行跨背景区域的运动,该方法较采用单模图像序列进行跟踪具有更好的鲁棒性,并且满足实时性的要求。     

Neuro-adaptive cooperative tracking control of unknown higher-order affine nonlinear systems

In this paper we propose a practical design method for distributed cooperative tracking control of a class of higher-order nonlinear multi-agent systems. Dynamics of the agents (also called the nodes) are assumed to be unknown to the controller and are estimated using Neural Networks. Linearization-based robust neuro-adaptive controller driving the follower nodes to track the trajectory of the leader node is proposed. The nodes are connected through a weighted directed graph with a time-invariant topology. In addition to the fact that only few nodes have access to the leader, communication among the follower nodes is limited with some nodes having access to the information of their neighbor nodes only. Command generated by the leader node is ultimately followed by the followers with bounded synchronization error. The proposed controller is well-defined in the sense that control effort is restrained to practical limits. The closed-loop system dynamics are proved to be stable and simulation results demonstrate the effectiveness of the proposed control scheme.     

An efficient Dynamic Addressing based routing protocol for Underwater Wireless Sensor Networks

Underwater Wireless Sensor Networks (UWSNs) are different in many aspects as compared to terrestrial sensor networks. Other than long propagation delays and high error probability, continuous node movement makes it hard to manage the location information of sensor nodes. Determining the location of every node is a major issue as nodes can move continuously with the water currents. In order to handle the problem of large propagation delays and unreliable link quality, many algorithms have been proposed and some of them provide good solutions for these issues, but continuous node movements still need attention. In order to handle the problem of node mobility, we proposed a Hop-by-Hop Dynamic Addressing Based (H2-DAB) routing protocol, where every node in the network will be assigned a routable address in a quick and efficient way without requiring an explicit configuration or any dimensional location information. It helps to provide an option where nodes can communicate without any centralized infrastructure, also a mechanism is available where nodes can come and leave the network without having any serious effect on the rest of the network. Simulation results show that H2-DAB can manage easily during the quick routing changes where node movements are very frequent yet require little or no overhead in order to complete its tasks.     

一种基于无线传感器网络的分布式处理目标跟踪系统

系统使用超声波传感器和扩展卡尔曼滤波对无线传感器网络中的移动单目标进行定位跟踪.节点嵌入式应用程序采用TinyOS/nesC[1]编程实现,采用Labview进行应用层开发.为了优化网络的能耗以延长网络寿命,提出了两种在分布式传感器网络中局部节点自适应选择任务节点[2]的方法.实验结果验证了扩展卡尔曼算法的正确性,并比较了这两种任务节点选择调度方法的跟踪性能,得出了基于候选节点协方差矩阵最小迹的任务节点选择调度方式在目标丢失率和跟踪精度综合考虑的基础上性能更优.     

Learning spatially regularized similarity for robust visual tracking

Matching visual appearances of the target object over consecutive frames is a critical step in visual tracking. The accuracy performance of a practical tracking system highly depends on the similarity metric used for visual matching. Recent attempts to integrate discriminative metric learned by sequential visual data (instead of a predefined metric) in visual tracking have demonstrated more robust and accurate results. However, a global similarity metric is often suboptimal for visual matching when the target object experiences large appearance variation or occlusion. To address this issue, we propose in this paper a spatially weighted similarity fusion (SWSF) method for robust visual tracking. In our SWSF, a part-based model is employed as the object representation, and the local similarity metric and spatially regularized weights are jointly learned in a coherent process, such that the total matching accuracy between visual target and candidates can be effectively enhanced. Empirically, we evaluate our proposed tracker on various challenging sequences against several state-of-the-art methods, and the results demonstrate that our method can achieve competitive or better tracking performance in various challenging tracking scenarios.