基于分块EnKF的非线性目标跟踪算法

针对滤波航迹的相关性以及初始状态的选择会对跟踪性能产生影响的问题,将集合卡尔曼滤波算法引入到非线性目标跟踪领域,验证了其可行性和有效性,提出了基于分块集合卡尔曼滤波的非线性目标跟踪算法.采用分块思想生成初始集合,使用协方差矩阵加权方法解决分块间的航迹相关问题.仿真结果表明基于分块集合卡尔曼滤波的目标跟踪算法计算复杂度和以往的集合卡尔曼滤波算法同阶的情况下可以提供更高的运动参数估计精度,解决了粒子滤波算法计算量大难以进行实时跟踪的问题.      

Probabilistic Tracking of Objects with Adaptive Cue Fusion Mechanism

A tracking method based on adaptive multiple cue fusion mechanism was presented,where particle filter is used to integrate color and edge cues.The fusion mechanism assigns different weights to two cues according to their importance,thus improving the robustness and reliability of the tracking algorithm.Moreover,a multi-part color model is also invoked to deal with the confliction among similar objects.The experimental results on two real image sequences show the tracking algorithm with adaptive fusion mechanism performs well in the presence of complex scenarios such as head rotation,scale change and multiple person occlusions.     

基于均值平移和自适应预测的运动目标跟踪

针对运动目标跟踪算法不足之处,提出结合改进的均值平移与自适应预测的目标跟踪算法,基于Bhattacharyya系数值进行Kalman滤波器与粒子滤波器之间的切换.引入Kalman滤波器为Mean Shift算法估计初始点,在跟踪稳定的情况下进行模板更新,根据Kalman残差大小判定是否发生遮挡：部分遮挡情况下即结合Kalman滤波器实现对快速运动目标的实时跟踪;完全遮挡情况下结合均值平移和粒子滤波进行鲁棒跟踪.实验证明,改进的算法可以有效地提高跟踪算法的效率,并且能很好地解决遮挡问题.     

基于双重采样粒子滤波的目标轨迹跟踪研究

为保证对目标轨迹跟踪的实时性,提高其精度,提出双重采样粒子滤波模型。首先,利用粒子聚合技术对状态空间的粒子权值进行加权平均处理,形成聚合粒子,使得粒子在状态空间内分布更为合理。然后,利用线性优化方法重新产生新的粒子,优化粒子在状态空间的分布特性,增加粒子的多样性,提高算法的精确性。经仿真验证,本文提出的算法较准确,鲁棒性也较高。     

基于水域精细划分的VTS雷达站选址配置优化

为了提高水上安全监管效率和保障水上运输安全生产, 以船舶交通管理系统(VTS)雷达站为研究对象, 研究了基于水域精细划分的VTS雷达站选址优化问题; 考虑实际环境中遮挡因素和水域风险因素对雷达监测效果的影响, 基于软件ArcGIS 10.4.1提出了水域精细划分方法; 以雷达站建站位置和雷达配置类型为决策变量, 以水域覆盖率最大和总成本最小为目标函数, 构建了混合整数规划模型; 基于模型特点设计了多目标粒子群算法, 给出了生成初始粒子群的启发式规则, 并在算法中引入有效的变异操作; 为了验证方法的有效性, 以ZDT系列测试函数对算法搜寻最优解的性能以及算法的收敛性进行了研究。研究结果表明: 水域精细划分方法能够在考虑遮挡因素和风险因素的情况下实现对水域的空间划分, 实例中在存在62个雷达站候选点的情况下将雷达站所需监测水域划分为2 812个水域单元; 改进的粒子群算法在ZDT测试函数中能够有效地寻找全局最优解, 并且在最优解的分布上具有良好的收敛性和分布性; 针对实例中的VTS雷达站选址项目模型达到了95.92%的覆盖率, 成本为33 800元。可见, 考虑环境遮挡和水域风险因素的VTS雷达站选址模型是有效的, 改进的多目标粒子群算法可以提高VTS雷达站选址的科学性和合理性, 是解决VTS雷达站选址优化问题的一种有效方法。      

铁路轨道异物完整性检测与跟踪算法研究

针对野外复杂环境下轨道异物检测不完整问题,提出基于小波变换的像素过滤思想改进GMM,构建背景模型;为解决异物目标实施机动(转弯、加速或突然出现)时跟踪实时性差和准确率低的问题,分析Kalman滤波线性化误差,搭建BP神经网络修正 IMM的跟踪模型,实现轨道异物跟踪预测,并推导出非线性Kalman滤波关系.实验表明,改进GMM在正常天气下平均前景误检率降低了24.94个百分点,针对复杂恶劣天气平均前景误检率降低了33.76个百分点;建立BP神经网络-IMM-Kalman滤波模型不仅可以快速准确地对场景中的机动目标进行跟踪,而且比Kalman滤波和IMM更加平稳,误差更小.     

Data Fusion Algorithm for Multi-Sensor Dynamic System Based on Interacting Multiple Model

This paper presents a data fusion algorithm for dynamic system with multi-sensor and uncertain system models. The algorithm is mainly based on Kalman filter and interacting multiple model(IMM). It processes crosscorrelated sensor noises by using augmented fusion before model interacting. And eigenvalue decomposition is utilized to reduce calculation complexity and implement parallel computing. In simulation part, the feasibility of the algorithm was tested and verified, and the relationship between sensor number and the estimation precision was studied. Results show that simply increasing the number of sensor cannot always improve the performance of the estimation. Type and number of sensors should be optimized in practical applications.     

低可见度环境下基于同步定位与构图的无人驾驶汽车定位算法

为在大范围低可见度环境下实现无人驾驶汽车的高精度定位，基于VINS-Mono算法的系统框架，在系统的前端与后端分别增添了RFAST弱光图像增强模块与VG融合定位模块，提出了一种融合定位算法LVG_SLAM; RFAST弱光图像增强模块采用小波变换将原始输入图像的细节信息与亮度信息分离，对于包含原始图像噪声的细节信息通过统一阈值和均值滤波2种方式实现噪声抑制，并利用双边纹理滤波算法进行细节增强，在此基础上，根据多尺度Retinex算法增强图像的对比度，提高低可见度环境下角点提取的成功率，从而保证图像跟踪的稳定性，改善定位算法的鲁棒性; 基于无迹卡尔曼滤波算法，VG融合定位模块将GNSS定位信息与惯性导航测量信息进行松耦合，融合定位结果作为约束引入VI-SLAM后端，通过联合非线性优化的方式减少累积误差对算法定位精度的影响。计算结果表明:相较于VINS-Mono算法，改进的LVG_SLAM融合定位算法在EuRoC与Kitti公开数据集上表现更加出色，均方根误差分别降低了38.76%与58.39%，运动轨迹更贴近真实轨迹; 在实际夜晚道路场景下，LVG_SLAM算法将定位误差控制在一定范围内，顺利检测到闭环使得定位表现得到大幅改善，均方根误差、平均误差、最大误差、中位数误差分别降低了79.61%、82.50%、71.31%、83.77%，与VINS-Mono算法相比，在定位精度与鲁棒性方面具有明显的优势。      

一种机动目标的自适应跟踪算法

通过分析"当前"统计模型采取固定机动加速度最大值在目标跟踪中的不足,引入模糊逻辑技术,提出了一种基于"当前"统计模型的自适应跟踪算法.该算法实现了目标机动加速度最大值随机动特性的自适应调整,从而实现了系统状态噪声方差的自适应调整,提高了系统的跟踪性能.对两种典型的目标机动形式进行了Monte Carlo仿真研究,结果表明了新算法对于解决机动目标跟踪问题的有效性.     

基于多模型和辅助粒子滤波的机动目标跟踪算法研究

机动目标跟踪的本质是随机动态混合系统中的状态估计问题,其难点在于每一时刻运动模式的高度不确定性.在实际问题中,系统状态往往还呈现非线性、非高斯、不完全观测的特点.文中将多模型理论和辅助粒子滤波算法相结合,提出了一种新的机动目标跟踪算法——MM APF.仿真结果表明,该算法与传统的交互多模型——扩展卡尔曼滤波算法、辅助粒子滤波算法相比,在计算量相当的情况下,具有更高的滤波精度和较好的稳定性.     

Target tracking in standoff jammer using unscented Kalman filter and particle fiter with negative information

To handle the problem of target tracking in the presence of standoff jamming （SO J）, a Gaussian sum unscented Kalman filter （GSUKF） and a Gaussian sum particle filter （GSPF） using negative information （scans or dwells with no measurements） are implemented separately in this paper. The Gaussian sum likelihood which is derived from a sensor model accounting for both the positive and the negative information is used. GSUKF is implemented by fusing the state estimate of two or three UKF filters with proper weights which are explicitly derived in this paper. Other than GSUKF, the Gaussian sum likelihood is directly used in the weight update of the GSPF. Their performances are evaluated by comparison with the Gaussian sum extended Kalman filter （GSEKF） implementation. Simulation results show that GSPF outperforms the other filters in terms of track loss and track accuracy at the cost of large computation complexity. GSUKF and GSEKF have comparable performance; the superiority of one over another is scenario dependent.     

改进的无迹粒子滤波在组合导航中的应用研究

粒子滤波算法是一种适用于非线性非正态约束的统计滤波算法.针对粒子滤波存在退化现象,从围绕增加粒子的多样性和重要性分布函数的选择出发,提出了一种改进的无迹粒子滤波算法.该算法是利用无迹卡尔曼滤波产生的近似高斯分布作为重要性密度函数,在每次迭代中,结合马尔科夫链蒙特卡洛使粒子能够移动到不同地方,从而可以避免贫化现象.将这种算法应用到GPS/DR组合导航系统中,仿真结果证明了采用改进的无迹粒子滤波方法能达到很好的跟踪效果.     

Efficient Recognition of Human Faces from Video in Particle Filter

Introduction As an active research in computer vision andimage understanding, face recognition from videohas got wide applications, such as human-comput-er interface, video surveillance, ATM and videocommunications[1]. So far, there are many litera-tures on face recognition from video. Many archi-tectures about dynamic face recognition were pro-posed in those literatures. Tracking and recogni-tion were performed separately in Ref.[2]. Thelimitation in this method is that tracking andrecognit…     

机载雷达伺服系统设计

介绍了机载雷达伺服系统中采用双电机驱动的控制方法和优点,并对使用速率陀螺构成的速度闭环实现天线的稳定方案进行了阐述.根据本系统的特点对该机载雷达伺服系统的电流、速度、位置闭环进行了仿真,利用仿真结果进行伺服系统电流、速度和位置环路的合理设计,使系统具有较好的动态和静态性能.     

Mobile Robot Hierarchical Simultaneous Localization and Mapping Using Monocular Vision

A hierarchical mobile robot simultaneous localization and mapping (SLAM) method that allows us to obtain accurate maps was presented. The local map level is composed of a set of local metric feature maps that are guaranteed to be statistically independent. The global level is a topological graph whose arcs are labeled with the relative location between local maps. An estimation of these relative locations is maintained with local map alignment algorithm, and more accurate estimation is calculated through a global minimization procedure using the loop closure constraint. The local map is built with Rao-Blackwellised particle filter (RBPF), where the particle filter is used to extending the path posterior by sampling new poses. The landmark position estimation and update is implemented through extended Kalman filter (EKF). Monocular vision mounted on the robot tracks the 3D natural point landmarks, which are structured with matching scale invariant feature transform (SIFT) feature pairs. The matching for multi-dimension SIFT features is implemented with a KD-tree in the time cost of O(lbN). Experiment results on Pioneer mobile robot in a real indoor environment show the superior performance of our proposed method.     

基于粒子滤波的约束目标被动跟踪研究

为提高约束条件下的二维机动目标被动跟踪性能,提出了一种约束下的粒子滤波方法(CPF).使用转弯率概念建立了被动跟踪模型,阐述了非线性粒子滤波的基本过程;通过设定地域和机动性能约束条件,抛弃约束外粒子,并对粒子分布和权重进行调整;利用CPF进行了目标跟踪仿真实验,与无约束的粒子滤波跟踪进行了对比,分析了轨迹跟踪性能,比较了跟踪误差.仿真结果表明,CPF能够稳定跟踪,并且具有更高的跟踪精度.     

基于PSO优化RBF-NN的磁浮车间隙传感器温度补偿

针对高速磁浮列车悬浮间隙传感器的温度漂移现象,建立了基于RBF（radial basis function）神经网络的间隙传感器温度补偿模型.通过对全局最优粒子执行梯度下降寻优,将粒子群优化算法与梯度下降算法结合得到一种寻优能力更强的混合算法,并将该方法用于RBF温度补偿模型参数优化,提高了间隙传感器的补偿精度,最后,使用现场可编程门阵列FPGA（field-programmable gate array）实现了该补偿模型并进行了实验.实验结果表明:该方法能够较好地对间隙传感器进行温度补偿,补偿后的传感器输出不受环境温度影响,全量程范围内最大误差为0.45 mm,8~12 mm工作间隙范围内误差为0.16 mm.      

船舶航向非线性系统的动态面控制

针对船舶航向控制非线性系统模型中存在的不确定性和外界干扰的影响,采用动态面控制算法设计了一种航向控制器。由于在反步法设计过程中加入了一阶低通滤波器使得该方法无需对模型非线性多次微分,因而设计方法简单,所设计的控制器能够保证闭环系统的半全局渐近稳定,使得输出渐进跟踪期望轨迹。数字仿真结果表明,控制系统对给定航向的跟踪具有良好的动态特性,对系统的不确定性,具有较强的鲁棒性。     

Real-time follow-up head tracking in dynamic complex environments

In the modes of both object motion and camera motion, an enhanced Camshift algorithm, which is based on suppressing similar color features of background and on joint color probability density distribution image, is proposed to real-time track head in dynamic complex environment. The system consists of face detection module, head tracking module and camera control module. When tracking fails, a self-recovery mechanism is introduced. At first the Adaboost face detector based on Haar-like features is implemented to find frontal faces, the false positive is filtered according to the skin color criterion, and the true face is used to initialize the tracking module. In hue saturation value (HSV) colorspace, the hue-saturation (H-S) histogram of face skin and the saturation-value (S-V) histogram of hair are built to produce the joint color probability density distribution image, and this is intended to realize the head tracking with arbitrary pose. During tracking, region of interest (ROI) is introduced, and the color probability density distribution of a specified background area outside the ROI is learned, similar color features in the head are suppressed according to the learning result. The background suppression step is intended to resolve the problem that the tracker maybe fails when the head is distracted by backgrounds having similar colors with the head. A closed loop control model based on speed regulation is applied to drive an active camera to center the head. Once tracking drift or failure is detected, the system stops tracking and returns to the face detection module. Our experimental results show that the presented system is well suitable for tracking head with arbitrary pose in dynamic complex environments, also the active camera can track moving head smoothly and stably. The system is computationally efficient and can run in real-time completely.