基于Meanshift与卡尔曼滤波的多目标跟踪

多目标跟踪相比较于单目标跟踪而言,视频中的目标数量增加,且在目标运动时,多个目标之间可能会产生遮挡,更增加了目标跟踪的难度,针对以上问题提出了Meanshift算法与卡尔曼滤波相结合的方法进行多目标的跟踪,首先采用Meanshift算法将目标与背景进行分割,然后分别建立Kalman数学模型,结果表明,该方法能够实现较为稳定的多目标的跟踪。     

基于卡曼滤波与均值偏移算法的目标跟踪

针对变化场景下的目标鲁棒跟踪,提出了一种结合均值漂移与Kalman滤波的跟踪算法.利用YCbCr特征空间进行目标描述,使用Kalman滤波对目标运动速度和空间位置进行预测.根据干扰的不同情况,使用不同的比例因子将两算法的跟踪结果线性加权得到目标的最终位置,并利用一种比较科学的模型更新策略,减轻了模型漂移的影响,视频序列跟踪结果表明,提出的方法能够稳定地进行跟踪.     

新的基于Kalman滤波的跟踪方法

模板更新策略是匹配跟踪算法成败的关键,为了提高基于模板匹配跟踪算法的性能,在分析多种模板更新算法的基础上,给出使用Kalman滤波器更新模板的方法。该方法不再将模板图像视为一个整体,而是使用Kalman滤波器对模板图像逐像素点进行更新,以得到自适应和最佳的目标模板图像,使匹配跟踪算法的性能得到很大提高,特别对于目标被遮挡、目标姿态变化以及环境照度变化有很强的适应性。对匹配算法的改进和遮挡的处理使该算法的性能得到进一步提高。实验结果表明该方法行之有效。     

基于Kalman滤波的无线传感器网络多目标跟踪

研究了无线传感器网络(WSN)多目标跟踪系统,探讨制约其性能的条件,阐明了基于Kalman滤波的系统,同时还应用了若干事件辅助机制。通过相应的仿真实验发现,提出的新方法与调度策略可以实时跟踪多目标,同时还有诸多方面的优势,例如,降低测量时间,缩减计算开销,节约能耗,以及改善精度等。     

红外序列图像目标跟踪的自适应Kalman滤波方法

提出了一种用于动态序列图像目标跟踪的自适应Kalman滤波方法。该方法用函数估计的思想估计目标的当前运动模型,同时实时修改滤波器的统计模型,并将最小二乘支持向量机应用于对当前目标运动模型的估计。实验表明,此种改进的Kalman滤波器的算法在跟踪机动目标时具有良好的性能。     

基于卡尔曼滤波器的运动目标跟踪算法

为了有效解决运动目标遮挡时目标信息容易丢失从而导致跟踪失败的问题,提出一种基于卡尔曼滤波器的运动目标跟踪算法。该算法首先利用高斯混合模型的背景差分法,结合空间邻域的相关性信息得到运动目标图像,然后通过建立帧间关系矩阵将跟踪情况分为5种状态分别进行处理,这5种状态是新目标出现、目标匹配、目标遮挡、目标分离和目标消失。采用卡尔曼滤波器预测目标参数,建立目标在下一帧中的预测信息。当运动目标相互遮挡时,在卡尔曼滤波器预测区域内采用交叉搜索法实现多个运动目标的精确匹配。通过多个视频序列测试,该算法能够获得良好的跟踪结果。     

基于强跟踪五阶容积卡尔曼滤波的眼睛跟踪算法

非侵入式眼睛跟踪在许多基于视觉的人机交互应用中扮演十分重要的角色,但由于眼睛运动的强非线性,如何确保眼睛跟踪过程中对外界干扰的鲁棒性以及跟踪精确度是其应用的关键问题。为提高眼睛跟踪的鲁棒性和精确度,提出强跟踪五阶容积卡尔曼滤波算法(ST-5thCKF),将强跟踪滤波(STF)次优渐消因子引入具有接近最少容积采样点且保持五阶滤波精确度的五阶容积卡尔曼滤波(5thCKF),获取5thCKF对强非线性良好滤波精确度同时具备STF对外界干扰的鲁棒性。真实条件下的实验结果验证了所提算法在眼睛跟踪中的有效性。     

基于序列批处理Kalman滤波的跟踪算法

提高跟踪准确度是雷达发展的重要方向之一,本文通过建立的雷达跟踪模型,从批处理的角度,将多个状态矢量联合进行处理,并改进了量测方程,给出了一种使用序列批处理Kalman滤波（SBKF）以提高雷达跟踪准确度的新手段。通过仿真实验看出,相比传统扩展卡尔曼滤波（EKF）算法,序列批处理Kalman滤波的结果更接近真实值,有更好的收敛性,能得到更加稳定的滤波结果,有效地抑制了量测方程非线性化和野值带来的影响。     

基于多尺度特征提取的Kalman滤波跟踪

针对波动性较大目标跟踪,传统Kalman滤波算法鲁棒性和实时性不足,提出一种基于多尺度特征提取的Kalman跟踪算法.前帧目标区域特征点匹配出后续帧目标区域特征点,并以后者特征点为中心,建立搜索区域,避免了遍历整幅后续帧图像,快速地为Kalman滤波方程状态后验值提供了稳定的观测信号和观测残差.实验证明,这种作为约束条...     

基于双重扩展卡尔曼滤波器的共轴跟踪技术研究

为了解决光电经纬仪由于机动目标运动模型不准确而引起的跟踪精度下降的问题,采用了单隐层前向神经网络(SLFNs)进行建模,提出了基于状态参数双重扩展卡尔曼滤波估计的共轴跟踪控制技术。仿真与实验结果显示,对83.33sin0.6t的等效正弦目标的速度估计最大误差为0.070 9()/s,跟踪精度为2.42';对旋转周期为4.5 s的光学动态靶标的跟踪精度达到2.96'以内。由此可见,所建立的模型与机动目标实际模型匹配,双重扩展卡尔曼滤波器(DEKF)能快速跟踪和估计状态参数。与传统控制方法相比,提出的方法具有更高的跟踪能力,能有效提高系统的跟踪精度。     

Real-time mobility tracking algorithms for cellular networks based on Kalman filtering

We propose two algorithms for real-time tracking of the location and dynamic motion of a mobile station in a cellular network using the pilot signal strengths from neighboring base stations. The underlying mobility model is based on a dynamic linear system driven by a discrete command process that determines the mobile station's acceleration. The command process is modeled as a semi-Markov process over a finite set of acceleration levels. The first algorithm consists of an averaging filter for processing pilot signal, strength measurements and two Kalman filters, one to estimate the discrete command process and the other to estimate the mobility state. The second algorithm employs a single Kalman filter without prefiltering and is able to track a mobile station even when a limited set of pilot signal measurements is available. Both of the proposed tracking algorithms can be used to predict future mobility behavior, which can be, useful in resource allocation applications. Our numerical results show that the proposed tracking algorithms perform accurately over a wide range of mobility parameter values.     

基于Kalman滤波器运动目标跟踪的火灾监测方法

针对目前通常采用的火焰信息特征检测方法无法有效排除环境变化产生的干扰,特别是光线变化易引发实时火灾监控出现误检的问题,提出了一种基于Kalman滤波器运动跟踪算法的火焰检测方法,同时利用颜色、圆形度等特征和信息进一步确认火灾。不同干扰条件下的测试结果表明,利用文中提出的算法进行火灾识别判断,具有响应时间短,抗干扰性强等优点,可满足实际使用需求。     

基于神经网络的机动目标跟踪模糊Kalman滤波算法

以实现坦克对机动目标的有效跟踪为背景,针对传统Kalman滤波算法存在的计算量较大、需要先验信息较多的缺点,提出了一种基于神经网络的机动目标跟踪模糊Kalman滤波算法.在"当前"统计模型的基础上,将未知的目标机动加速度作为附加的过程噪声,使用模糊系统估计全部过程噪声的时变方差,利用神经网络对模糊系统中的参数进行优化.仿真结果表明了所提方法的有效性.     

基于YOLOv5网络模型的人员口罩佩戴实时检测

近年来,随着硬件算力的提升和人工智能算法的创新发展,使得深度学习算法在目标检测方面有着广泛的应用.针对现有人工方式查看人员口罩佩戴情况的不足,提出了一种基于深度学习YOLOv5算法实现对口罩佩戴情况的实时检测.算法首先将数据集进行归一化处理,再将数据接入YOLOv5网络进行迭代训练,并将最优权重数据保存用作测试集测试,...     

A hand tracking algorithm with particle filter and improved GVF snake model

To solve the problem that the accurate information of hand cannot be obtained by particle filter, a hand tracking algorithm based on particle filter combined with skin-color adaptive gradient vector flow (GVF) snake model is proposed. Adaptive GVF and skin color adaptive external guidance force are introduced to the traditional GVF snake model, guiding the curve to quickly converge to the deep concave region of hand contour and obtaining the complex hand contour accurately. This algorithm realizes a real-time correction of the particle filter parameters, avoiding the particle drift phenomenon. Experimental results show that the proposed algorithm can reduce the root mean square error of the hand tracking by 53%, and improve the accuracy of hand tracking in the case of complex and moving background, even with a large range of occlusion. This work has been supported by the National Natural Sciencal Foundation of China (No.61403274), and the Tianjin Technology Project of Intelligent Manufacturing (No.15ZXZNGX00160). E-mail:agwu@tju.edu.cn      

基于改进卡尔曼滤波的激光补给无人机跟瞄方法研究

激光供能为无人机长时间工作提供了保障,但是激光供能对捕获、跟踪和对准(APT)系统具有较高的要求.本文针对无人机距离地面补给站远、激光跟踪延迟、无人机供给能量不足等问题,提出一种基于自适应卡尔曼滤波算法,采用当前统计模型构建,通过残差检测对无人机模型进行实时的修正,加快位置更新速度,实现激光对无人机的最优跟踪.经过仿真...     

一种基于预测值量测转换的卡尔曼滤波跟踪算法

在雷达目标跟踪中,系统量测信息通常在球坐标系下获得。为了采用经典卡尔曼滤波算法实现有效目标跟踪,通常采用量测转换方法将非线性量测信息转换到直角坐标系中。针对传统量测转换方法基于量测值计算转换误差统计特性而导致的估计结果有偏问题,提出了一种基于预测值的量测转换方法,并将其与卡尔曼滤波算法相结合,获得了一种基于预测值量测转换的卡尔曼滤波跟踪算法。仿真结果表明,与现有的基于量测转换的卡尔曼滤波算法相比,该算法能在不提高运算量的情况下有效改善目标跟踪效果,跟踪精度提升约20%。     

Probabilistic Kalman filter for moving object tracking

Kalman filter has been successfully applied to tracking moving objects in real-time situations. However, the filter cannot take into account the existing prior knowledge to improve its predictions. In the moving object tracking, the trajectories of multiple targets in the same environment could be available, which can be viewed as the prior knowledge for the tracking procedure. This paper presents the probabilistic Kalman filter (PKF) that is able to take into account the stored trajectories to improve tracking estimation. The PKF has an extra stage after two steps of the Kalman filter to refine the estimated position of the targets. The refinement is obtained by applying the Viterbi algorithm to a probabilistic graph, that is constructed based on the observed trajectories. The graph is built in the offline situation and could be adapted in the online tracking. The proposed tracker has higher accuracy compared to the standard Kalman filter and could handle widespread problems such as occlusion. Another significant achievement of the proposed tracker is to track an object with anomalous behaviors by drawing an inference based on the constructed probabilistic graph. The PKF was applied to several manually-built videos and several other video-bases containing severe occlusions, which demonstrates a significant performance in comparison with other state-of-the-art trackers.     

Influence of stochastic noise statistics on Kalman filter performance based on video target tracking

The system stochastic noises involved in Kalman filtering are preconditioned on being ideally white and Gaussian distributed. In this research, efforts are exerted on exploring the influence of the noise statistics on Kalman filtering from the perspective of video target tracking quality. The correlation of tracking precision to both the process and measurement noise covariance is investigated; the signal-to-noise power density ratio is defined; the contribution of predicted states and measured outputs to Kalman filter behavior is discussed; the tracking precision relative sensitivity is derived and applied in this study case. The findings are expected to pave the way for future study on how the actual noise statistics deviating from the assumed ones impacts on the Kalman filter optimality and degradation in the application of video tracking.     

Video object tracking using adaptive Kalman filter

In this paper, a new video moving object tracking method is proposed. In initialization, a moving object selected by the user is segmented and the dominant color is extracted from the segmented target. In tracking step, a motion model is constructed to set the system model of adaptive Kalman filter firstly. Then, the dominant color of the moving object in HSI color space will be used as feature to detect the moving object in the consecutive video frames. The detected result is fed back as the measurement of adaptive Kalman filter and the estimate parameters of adaptive Kalman filter are adjusted by occlusion ratio adaptively. The proposed method has the robust ability to track the moving object in the consecutive frames under some kinds of real-world complex situations such as the moving object disappearing totally or partially due to occlusion by other ones, fast moving object, changing lighting, changing the direction and orientation of the moving object, and changing the velocity of moving object suddenly. The proposed method is an efficient video object tracking algorithm.