A novel strong tracking finite-difference extended Kalman filter for nonlinear eye tracking

Non-intrusive methods for eye tracking are important for many applications of vision-based human computer interaction. However, due to the high nonlinearity of eye motion, how to ensure the robustness of external interference and accuracy of eye tracking poses the primary obstacle to the integration of eye movements into todays’s interfaces. In this paper, we present a strong tracking finite-difference extended Kalman filter algorithm, aiming to overcome the difficulty in modeling nonlinear eye tracking. In filtering calculation, strong tracking factor is introduced to modify a priori covariance matrix and improve the accuracy of the filter. The filter uses finite-difference method to calculate partial derivatives of nonlinear functions for eye tracking. The latest experimental results show the validity of our method for eye tracking under realistic conditions. Supported by the National Natural Science Foundation of China (Grant No. 60572027), the Outstanding Young Researchers Foundation of Sichuan Province (Grant No. 03ZQ026-033), the Program for New Century Excellent Talents in University of China (Grant No. NCET-05-0794), and the Young Teacher Foundation of Mechanical School (Grant No. MYF0806)     

A new real-time eye tracking based on nonlinear Unscented Kalman Filter for monitoring driver fatigue

A new scheme for driver fatigue detection is presented, which is based on the nonlinear unscented Kalman filter and eye tracking. Assuming a probability distribution than to approximate an arbitrary nonlinear function or transformation, eye nonlinear tracking can be achieved using an unscented transformation (UT), which adopts a set of deterministic sigma points to match the posterior probability density function of the eye movement. Driver fatigue can be detected using the percentage of eye closure (PERCLOS) framework in a realistic driving condition after the eye nonlinear tracking. This system was tested adequately in realistic driving environments with subjects of different genders, with/without glasses, in day/night driving, being commercial/noncommercial drivers, in continuous driving time, and under different road conditions. The last experimental results show that the proposed method not only improves the robustness for nonlinear eye tracking, but also can provide more accurate estimation than the traditional Kalman filter.     

Maximum correntropy unscented filter

The unscented transformation (UT) is an efficient method to solve the state estimation problem for a non-linear dynamic system, utilising a derivative-free higher-order approximation by approximating a Gaussian distribution rather than approximating a non-linear function. Applying the UT to a Kalman filter type estimator leads to the well-known unscented Kalman filter (UKF). Although the UKF works very well in Gaussian noises, its performance may deteriorate significantly when the noises are non-Gaussian, especially when the system is disturbed by some heavy-tailed impulsive noises. To improve the robustness of the UKF against impulsive noises, a new filter for non-linear systems is proposed in this work, namely the maximum correntropy unscented filter (MCUF). In MCUF, the UT is applied to obtain the prior estimates of the state and covariance matrix, and a robust statistical linearisation regression based on the maximum correntropy criterion is then used to obtain the posterior estimates of the state and covariance matrix. The satisfying performance of the new algorithm is confirmed by two illustrative examples.     

自适应UKF算法在目标跟踪中的应用

针对目标跟踪中系统噪声统计特性未知导致滤波发散或者滤波精度不高的问题, 提出了一种自适应无迹卡尔曼滤波(Unscented Kalman filter, UKF)算法.该算法在滤波过程中,利用改进的Sage-Husa估 计器在线估计未知系统噪声的统计特性,并对滤波发散的情况进行判断和抑制, 有效提高了滤波的数值稳定性,减小了状态估计误差. 仿真实验结果表明,与标准UKF算法相比,自适应UKF算法明显改善了目标跟踪的精度和稳定性.     

基于测量方差时变的改进强跟踪滤波算法

分析了测量方差预先设定对强跟踪滤波算法的不利影响,提出了一种测量方差自学习修正的强跟踪滤波算法。该滤波算法能够充分利用传感器每次测量带来的新信息,同时,可以进一步优化测量方差,提高了对状态的估计精度,最后,通过仿真计算验证了该算法的有效性。     

一种提高无迹卡尔曼滤波精确度的方法

无迹卡尔曼滤波是通过确定性采样,以无迹变换为基础,用卡尔曼线性滤波框架而建立起来的,对非线性系统有很好的滤波效果,但当噪声的影响较大时,精确度将会减低。为解决上述问题,提出了一种提高无迹卡尔曼滤波(UKF)精确度的方法,它将观测噪声和系统噪声引入到采样点中,对噪声进行对称采样处理,同时改进了算法过程,增加了无迹卡尔曼滤波的抗干扰性,与常规无迹卡尔曼滤波(UKF)相比,不仅保持了系统的稳定性,而且提高了精确度,最后通过仿真进行了验证。     

基于强跟踪滤波器预测的主动表观模型人脸特征点跟踪

利用主动表观模型(AAM)可以对视频序列中人脸进行特征点定位,当目标对象与初始位置偏离过大时,就会使拟合过程陷入局部最小,使迭代无法收敛到正确位置,造成定位失败。针对此问题,提出了一种基于强跟踪滤波器(STF)预测的AAM(STF-AAM)人脸特征点跟踪方法。首先,将视频中头部运动看成动态系统,然后利用强跟踪滤波器对其进行预测跟踪,从而找到每一帧的拟合初始位置并进行拟合运算。由于视频序列中每一帧中的拟合初始位置都能被快速找到,从而取得了比较精确、快速的跟踪结果。实验结果表明,所提方法与传统方法相比在保证拟合精度的同时,提高了算法的跟踪定位速度。     

基于Unscented变换的强跟踪滤波器

针对强跟踪滤波器(STF)存在要求非线性函数连续可微和强非线性时滤波性能不佳等理论局限性,提出一种基于Unscented变换的强跟踪滤波器(UTSTF).UTSTF基于STF的理论框架,采用Unscented变换代替STF中的雅可比矩阵计算:UTSTF兼具STF鲁棒性强、Unscented变换精度高、实现简单的优点,有效克服了STF的理论局限性.仿真实例验证了UTSTF的有效性.     

基于UKF区域交叉定位的WSNs Sink节点动态跟踪算法

为了提高无线传感器网络（ WSNs）使用寿命,对WSNs的目标跟踪方式进行研究,提出基于无迹Kalman滤波（ UKF）的WSNs Sink节点动态跟踪算法,以实现高效节能的资源管理和利用方式。首先利用UKF算法对目标节点的下一位置进行预测,然后通过四圆区域定位交叉定位算法对Sink节点的位置区域进行局部准确定位。实验结果表明：这种动态的Sink节点预测定位算法能够有效缩短数据发射传感器和Sink点之间的距离,减少跳数,从而实现负载均衡降低能耗的效果。     

基于序贯无迹卡尔曼滤波的雷达目标跟踪方法

提出一种基于序贯无迹卡尔曼滤波的雷达目标跟踪方法。雷达跟踪系统为离散非线性系统,传统的解决方法是使用扩展卡尔曼滤波。无迹卡尔曼滤波用少量采样点表示随机变量的分布,通过非线性系统传播,能以三阶精度获得非线性变换的均值和方差的估计。为了提高无迹卡尔曼滤波的精度,用序贯无迹卡尔曼滤波方法依次处理方位角、俯仰角和距离,来进行雷达目标跟踪。通过Monte Carlo仿真,验证了该滤波算法比传统的扩展卡尔曼滤波具有更高的滤波精度和更高的计算效率。     

加权观测融合非线性无迹卡尔曼滤波算法

针对非线性系统的无迹卡尔曼滤波器(UKF),应用加权最小二乘(WLS)法,提出了加权观测融合UKF滤波算法.证明了加权观测融合UKF滤波算法与集中式观测融合UKF滤波算法在数值上的完全等价性,因而具有全局最优性.一个带两传感器非线性系统的仿真例子说明了两种融合算法的有效性及等价性.     

基于UKF的闪烁噪声机动目标跟踪

闪烁噪声下的机动目标跟踪是一个非线性非高斯系统滤波问题,传统的卡尔曼理论很难保证其跟踪精度.文中提出了一种基于UKF的闪烁噪声机动目标跟踪算法,首先对目标系统的状态方程进行无味变换,然后再进行滤波估计,以减小跟踪误差.UKF不需要求导,它能比EKF更好地迫近目标运动模型的非线性特性,具有更高的估计精度,计算量却与EKF同阶.在仿真实验中采用"协同转弯模型"作为机动目标的运动模型,雷达的量测方程也是非线性的,分别应用UKF和EKF跟踪闪烁噪声下的机动目标,结果表明,UKF能够较好地解决闪烁噪声下跟踪机动目标的难题,其跟踪精度要远远高于EKF.     

基于加性无迹卡尔曼滤波的雷达目标跟踪方法

提出一种基于加性无迹卡尔曼滤波的雷达目标跟踪方法。雷达跟踪系统为离散非线性系统,传统的解决方法是使用扩展卡尔曼滤波。无迹卡尔曼滤波用少量采样点表示随机变量的分布,通过非线性系统传播,能以三阶精度获得非线性变换的均值和方差的估计。用无迹卡尔曼滤波进行雷达目标跟踪。通过Monte Carlo仿真,验证了该滤波算法比传统的扩展卡尔曼滤波具有更高的滤波精度。     

基于强跟踪滤波器的多目标跟踪方法

在诸多的多目标跟踪算法中，相互作用多模型（IMM）算法是目前公认的最为有效的算法。但到目前为止，LMM估计方法都是建立在卡尔曼滤波器（KF）和扩展卡尔曼滤波器（EKF）基础上，因而其性能不仅依赖于所采用的模型集，而且在更大程度上依赖于所采用的滤波技术。强跟踪滤波器（STF）克服了卡尔曼和扩展卡尔曼的三大缺陷，因而设计一种基于STF的IMM目标跟踪算法显然能提高其性能。仿真实验表明，基于STF的IMM算法的跟踪性能要优于基于KF和EKF的IMM算法的跟踪性能。     

基于无极卡尔曼滤波算法的雅可比矩阵估计

在基于图像的机器人视觉伺服中,采用在线估计图像雅可比的方法,不需事先知道系统的精确模型,可以避免复杂的系统标定过程。为了有效改善图像雅可比矩阵的在线估计精度,进而提高机器人的跟踪精度,针对机器人跟踪运动目标的应用背景,提出了利用无极卡尔曼滤波算法在线估计总雅可比矩阵。在二自由度的机器人视觉伺服仿真平台上,分别用卡尔曼滤波器（KF）、粒子滤波器（PF）和无极卡尔曼滤波器（UKF）三种算法进行总雅可比矩阵的在线估计。实验结果证明,使用UKF算法的跟踪精度优于其他两种算法,时间耗费仅次于KF算法。     

面向增强现实的多传感器组合位姿注册算法

持续稳定的准确注册是构建增强现实系统的关键,为提高跟踪注册的稳定性和精度,提出了一种基于互补滤波(CF)和无迹卡尔曼滤波(UKF)的多传感器融合注册方案.该算法采用互补滤波器融合陀螺仪、加速度计和地磁感应计数据估计摄像头姿态;在处理视觉图像时,结合惯性姿态数据进行图像特征匹配;利用UKF融合视觉和惯性数据进行摄像头位置估计.实验表明:该算法在跟踪稳定性、精度、效率和抗干扰能力均优于传统的基于扩展卡尔曼滤波(EKF)的融合算法.     

强跟踪卡尔曼滤波在视频目标跟踪中的应用

针对经典卡尔曼滤波器在滤波数学模型与实际过程的数学规律不匹配、滤波特性较差的情况,提出利用强跟踪卡尔曼滤波器对视频序列图像中的运动目标进行跟踪。该方法是在经典卡尔曼滤波递推公式中的一步验前误差方差阵中引入可在线计算的时变渐消矩阵,从而调节增益K,使之能够不断变化,保证对新息序列的自适应调节,使状态滤波更准确。实验结果表明,较之经典卡尔曼滤波,该方法具有对运动目标更强的跟踪能力,跟踪精度更高,均方误差更小。     

UKF与EKF在卫星姿态估计应用中的比较

针对卫星的姿态和角速度估计问题,分别给出基于Unscented卡尔曼滤波(UKF)与推广卡尔曼滤波(EKF)的估计算法,并做了相应比较.为了避免欧拉角带来的奇异问题,UKF选用Rodrigues参数而EKF选用四元数参数法来描述姿态误差.考虑卫星的非线性模型,UKF采用Unscented变换而EKF采用线性化方法对姿态误差进行估计.利用陀螺和磁强计的测量信息,KF和EKF都可得到三轴稳定卫星的姿态估计值,但UKF的收敛速度高于EKF.数值仿真结果表明,当初始姿态存在大偏差时,所给出的UKF的滤波算法性能明显优于EKF.     

基于无迹卡尔曼滤波的被动多传感器融合跟踪

针对被动传感器观测的非线性问题,将无迹变换引入卡尔曼滤波算法中.进一步,针对其弱可观测性,采用多个被动传感器集中式融合跟踪策略,提出了基于无迹卡尔曼滤波的被动多传感器融合跟踪算法.以3个被动站跟踪为例进行仿真研究,结果表明所提出的算法可达到比经典的扩展卡尔曼滤波算法更高阶的跟踪精度.     

Variants of extended Kalman filtering approaches for Bayesian tracking

We provide a tutorial for a number of variants of the extended Kalman filter (EKF). In these methods, so called, sigma points are employed to tackle the nonlinearity of problems. The sigma points exactly represent the mean and the variance of the state distribution function in a dynamic state equation. The initially developed EKF variant, that is, unscented Kalman filter (UKF) (also called sigma point Kalman filter) shows enhanced performance compared with that of conventional EKF in the literature. Another variant, which is not well known, is central difference Kalman filter (CDKF) whose way to approximate the nonlinearity is based on the Sterling's polynomial interpolation formula instead of the Taylor series. Endeavor to reduce the computational load resulted in the development of square root versions of both UKF and CDKF, that is, square root unscented Kalman filter and square root central difference Kalman filter (SR‐CDKF). These SR‐versions are supposed to be numerically more stable than their original versions because the state covariance is guaranteed to be positive definite by avoiding the step of matrix decomposition. In this paper, we provide the step‐by‐step algorithms of above‐mentioned EKF variants with their pros and cons. We apply these filtering methods to a number of problems in various disciplines for performance assessment in terms of both mean squared error (MSE) and processing speed. Furthermore, we show how to optimize the filters in terms of MSE performance depending on diverse scenarios. According to simulation results, CDKF and SR‐CDKF show the best MSE performance in most scenarios; particularly, SR‐CDKF shows faster processing speed than that of CDKF. Therefore, we justify that SR‐CDKF is the most efficient and the best approach among the Kalman variants including the EKF for various nonlinear problems. The motivation of this paper targets at the contribution to the disseminative usage of the Kalman variants approaches, particularly, SR‐CDKF taking advantage of its estimating performance and high processing speed. Copyright © 2016 John Wiley & Sons, Ltd.