基于核函数粒子滤波和多特征自适应融合的目标跟踪

经典粒子滤波及其改进算法在观测模型与真实情况存在偏差时会导致滤波发散,针对这一问题,提出一种核函数粒子滤波算法.该算法根据目标状态与粒子状态之间的距离,利用核函数产生权值对粒子进行二次加权,根据粒子的二次加权结果进行粒子重采样;以改进的粒子滤波算法为框架,提出了一种自适应多特征融合目标跟踪方法,利用相似性度量动态地评价特征对目标与背景的区分能力,并自适应地计算特征融合权重,以适应目标跟踪过程中目标与背景的变化,提高目标跟踪的鲁棒性.实验结果表明,文中提出的目标跟踪方法比经典粒子滤波目标跟踪方法具有更强的抗干扰性能和较高的跟踪精度.     

Real-time hand tracking using a mean shift embedded particle filter

Particle filtering and mean shift (MS) are two successful approaches to visual tracking. Both have their respective strengths and weaknesses. In this paper, we propose to integrate advantages of the two approaches for improved tracking. By incorporating the MS optimization into particle filtering to move particles to local peaks in the likelihood, the proposed mean shift embedded particle filter (MSEPF) improves the sampling efficiency considerably. Our work is conducted in the context of developing a hand control interface for a robotic wheelchair. We realize real-time hand tracking in dynamic environments of the wheelchair using MSEPF. Extensive experimental results demonstrate that MSEPF outperforms the MS tracker and the conventional particle filter in hand tracking. Our approach produces reliable tracking while effectively handling rapid motion and distraction with roughly 85% fewer particles. We also present a simple method for dynamic gesture recognition. The hand control interface based on the proposed algorithms works well in dynamic environments of the wheelchair.     

多特征融合的自适应性粒子滤波跟踪算法

为提高粒子滤波视觉目标跟踪算法的实时性与鲁棒性,提出了一种基于多特征融合的自适应性粒子滤波跟踪算法。该算法利用颜色和结构特征表示目标,将两者融合于粒子滤波的框架中,利用融合后的信息计算粒子的权值,以降低算法受目标形变及复杂环境的影响。同时,根据跟踪预测的准确程度动态计算跟踪所需的粒子数目,对采样粒子集进行自适应调整,以提高粒子质量,降低粒子数量,减少算法运算时间。实验结果表明,所提算法对于每帧图像的平均计算时间相对于传统混合跟踪算法缩短了将近一半,而且算法的鲁棒性较强。     

An adaptive sample count particle filter

The particle filter technique has been used extensively over the past few years to track objects in challenging environments. Due to its nonlinear nature and the fact that it does not assume a Gaussian probability density function it tends to outperform other available tracking methods. A novel adaptive sample count particle filter (ASCPF) tracking method is presented in this paper for which the main motivation is to accurately track an object in crowded scenes using fewer particles and hence with reduced computational overhead. Instead of taking a fixed number of particles, a particle range technique is used where an upper and lower bound for the range is initially identified. Particles are made to switch between an active and inactive state within this identified range. The idea is to keep the number of active particles to a minimum and only to increase this as and when required. Active contours are also utilized to determine a precise area of support around the tracked object from which the color histograms used by the particle filter can be accurately calculated. This, together with the variable particle spread, allows a more accurate proposal distribution to be generated while using less computational resource. Experimental results show that the proposed method not only tracks the object with comparable accuracy to existing particle filter techniques but is up to five times faster.     

基于粒子滤波的小波特征跟踪方法研究

该文提出了基于粒子滤波的小波特征跟踪方法。粒子滤波基于蒙特卡罗模拟方法来实现递推贝叶斯滤波,是一种实用的后验概率求解方法。文中研究了目标的Gabor小波网络表示,用一定数量的小波构成一个集合来表示目标特征,各小波的参数由优化方法来确定。构建了基于粒子滤波的跟踪框架,每个粒子表示一种Gabor小波网络的可能形式,并计算与当前图像的相似度。粒子权值与相似度成正比,目标状态的后验概率由粒子加权表示。与传统的“峰值”跟踪方法不同,粒子滤波具有“多峰”的跟踪形式。并结合对光照、噪声不敏感的小波表示形式,具有较强的抗局部遮挡能力。     

Real-time visual tracking via multi-cue based adaptive particle filter framework

Visual tracking using particle filter has been extensively investigated due to its myriad of application in the field of computer vision. However, particle filter framework performance is heavily impaired due to its inherent problems namely, particle degeneracy and impoverishment. In addition, most of the tracking methods using single cue are greatly affected by dynamic environmental challenges. To address these issues, we propose an adaptive multi-cue particle filter based real-time visual tracking framework. Three complementary cues namely, color histogram, LBP and pyramid of histogram of gradient have been exploited for object’s appearance model. These cues are integrated using the proposed adaptive fusion model for the automatic boosting of important particles and suppression of unimportant particles. Resampling method using butterfly search optimization relocate low performing particles to high likelihood area. Proposed outlier detection mechanism not only helps in detecting low performing particles but also aids in updating of the reference dictionary. Online estimation of cue reliability along with its multi-cue fusion leads to quick adaptation of the proposed tracker. On average of the outcome, our tracker achieves average center location error of 6.89 (in pixels) and average F-measure of 0.786 when evaluated on OTB-100 and VOT dataset against 13 others state-of-the-art.

     

A moving object tracking based on color information employing a particle filter algorithm

In this article, we present a new algorithm to track a moving object based on color information employing a particle filter algorithm. Recently, a particle filter has been proven very successful for nonlinear and non-Gaussian estimation problems. It approximates a posterior probability density of the state, such as the object position, by using samples which are called particles. The probability distribution of the state of the tracked object is approximated by a set of particles, where each state is denoted as the hypothetical state of the tracked object and its weight. The particles are propagated according to a state space model. Here, the state is treated as the position of the object. The weight is considered as the likelihood of each particle. For this likelihood, we consider the similarity between the color histogram of the tracked object and the region around the position of each particle. The Bhattacharya distance is used to measure this similarity. Finally, the mean state of the particles is treated as the estimated position of the object. Experiments were performed to confirm the effectiveness of this method to track a moving object.     

基于GPU加速的粒子滤波多说话人跟踪算法及其应用

为了解决粒子滤波多说话人跟踪过程中粒子易发散导致多目标跟踪精度低的问题,提出了并行粒子滤波和基于GPU的K-均值聚类的多声源定位方法。该方法首先分析了粒子滤波在实现多目标跟踪时,进行数据关联的过程产生较大的计算量,并且出现多个目标时,粒子会逐渐发散。针对计算量大和粒子发散的问题,提出了一种并行粒子滤波和K-均值聚类的方法。实验表明,随着粒子数和目标数的增加,计算量以指数增加,并且粒子发散严重,采用基于GPU的K-均值聚类方法的粒子滤波多说话人跟踪方法,相比传统粒子滤波跟踪方法具有更收敛的粒子集并且跟踪精度较高。     

基于特征约束和均值漂移的机动目标粒子跟踪

粒子滤波是适用于非线性非高斯系统下目标跟踪的强有力工具．ＭｉｒｏＳｏｔ足球机器人系统可以作为研究机动目标跟踪问题的平台．对此,在分析ＭｉｒｏＳｏｔ系统目标特征的基础上,提出一种基于目标特征约束的均值漂移粒子滤波算法,利用约束和优化的思想提高粒子的质量并减少其数量．对比实验表明,该方法有效地克服了传统粒子滤波的计算量和粒子退化问题,保证了多机动目标跟踪的准确性和实时性．     

基于多观测模型的粒子滤波头部跟踪算法

粒子滤波在非线性和非高斯问题上具有独特的优越性,但在视频跟踪过程中,其跟踪性能却在很大程度上依赖于观测模型的选择。为了解决被跟踪目标特征状态随时间变化而与粒子观测模型不匹配的问题,提出了一种新的粒子滤波算法,即将被跟踪目标的不同特征状态与粒子观测模型相结合,形成一组具有不同观测模型的粒子,并且在跟踪过程中,对应不同观测模型的粒子根据被跟踪目标所表现的特征线索的变化而相互转换,从而动态刻画了被跟踪目标特征变化的过程。实验结果表明,本算法能够有效处理由于头部旋转而导致跟踪性能下降甚至丢失跟踪目标的问题,提高了跟踪的准确性,并且具有较好的鲁棒性。     

Intelligent video target tracking using an evolutionary particle filter based upon improved cuckoo search

The aim of this paper is to propose an evolutionary particle filter based upon improved cuckoo search algorithm which will overcome the sample impoverishment problem of generic particle filter. In our proposed method, improved cuckoo search (ICS) algorithm is embedded into particle filter (PF) framework. Improved cuckoo search algorithm uses levy flight for generating new particles in the solution and introduced randomness in samples by abandoning a fraction of these particles. The second important contribution in this article is introduction of new way for tackling scaling and rotational error in object tracking. Performance of proposed improved cuckoo particle filter is investigated and evaluated on synthetic and standard video sequences and compared with the generic particle filter and particle swarm optimization based particle filter. We show that object tracking using improved cuckoo particle filter provides more reliable and efficient tracking results than generic particle filter and PSO-particle filter. The proposed technique works for real time video objects tracking.     

An evolutionary particle filter with the immune genetic algorithm for intelligent video target tracking

Particle filter algorithm is widely used for target tracking using video sequences, which is of great importance for intelligent surveillance applications. However, there is still much room for improvement, e.g. the so-called “sample impoverishment”. It is brought by re-sampling which aims to avoid particle degradation, and thus becomes the inherent shortcoming of the particle filter. In order to solve the problem of sample impoverishment, increase the number of meaningful particles and ensure the diversity of the particle set, an evolutionary particle filter with the immune genetic algorithm (IGA) for target tracking is proposed by adding IGA in front of the re-sampling process to increase particle diversity. Particles are regarded as the antibodies of the immune system, and the state of target being tracked is regarded as the external invading antigen. With the crossover and mutation process, the immune system produces a large number of new antibodies (particles), and thus the new particles can better approximate the true state by exploiting new areas. Regulatory mechanisms of antibodies, such as promotion and suppression, ensure the diversity of the particle set. In the proposed algorithm, the particle set optimized by IGA can better express the true state of the target, and the number of meaningful particles can be increased significantly. The effectiveness and robustness of the proposed particle filter are verified by target tracking experiments. Simulation results show that the proposed particle filter is better than the standard one in particle diversity and efficiency. The proposed algorithm can easily be extended to multiple objects tracking problems with occlusions.     

Posterior representation with a multi‐modal likelihood using the gaussian sum filter for localization in a known map

A Gaussian sum filter (GSF) with component extended Kalman filters (EKF) is proposed as an approach to localizing an autonomous vehicle in an urban environment with limited GPS availability. The GSF uses vehicle‐relative vision‐based measurements of known map features coupled with inertial navigation solutions to accomplish localization in the absence of GPS. The vision‐based measurements have multimodal measurement likelihood functions that are well represented as weighted sums of Gaussian densities. The GSF is used because of its ability to represent the posterior distribution of the vehicle pose with better efficiency (fewer terms, less computational complexity) than a corresponding bootstrap particle filter with various numbers of particles because of the interaction with measurement hypothesis tests. The expectation‐maximization algorithm is used off line to determine the representational efficiency of the particle filter in terms of an effective number of Gaussian densities. In comparison, the GSF, which uses an iterative condensation procedure after each iteration of the filter to maintain real‐time capabilities, is shown through a series of in‐depth empirical studies to more accurately maintain a representation of the posterior distribution than the particle filter using 37 min of recorded data from Cornell University's autonomous vehicle driven in an urban environment, including a 32 min GPS blackout. © 2012 Wiley Periodicals, Inc.     

基于粒子滤波和点线相合的未知环境地图构建方法

针对粒子滤波处理未知环境地图构建时存在存储空间负荷高、计算量大的问题, 本文使用线段特征描述环境信息, 将点线相合的增量式地图构建方法引入粒子滤波中. 在每个粒子中保存对已构建线段特征地图的假设; 使用点线相合的位姿估计算法将观测信息引入重要性函数, 确定采样空间; 通过观测信息与已构建线段特征地图之间的相合关系更新粒子权重; 最后通过选择性重采样去除因匹配不当和误差积累产生的错误地图. 分析表明, 该算法的复杂度较低. 在真实传感器数据上的实验结果验证了该算法构建室内环境地图的有效性和鲁棒性. 算法所需存储空间和粒子数远小于现有粒子滤波地图构建方法.     

无线传感器网络环境下基于粒子滤波的移动机器人SLAM算法

定位问题是移动机器人研究领域中最基本的问题,在Bayes的框架下研究了机器人与无线传感器网络(WSN)组成系统中的同时建图与定位问题(SLAM).针对该系统中只存在距离测量信息可用的情况提出了一种基于粒子滤波的SLAM算法.该方法将机器人状态和节点位置估计设置为一组全局估计粒子,通过对粒子及其权重的更新来计算整个系统的状态.算法将WSN节点的位置估计在机器人的路径上分解为相互独立的估计,从而将全局粒子的计算转化为使用一个机器人状态滤波器和对应于每个机器人粒子的节点位置滤波器进行计算.针对观测信息低维的特点,设计了处理低维观测信息的方法,使得观测信息可以在滤波阶段得到合理利用.并且详细介绍了提出的SLAM算法原理和计算过程,并通过仿真实验证明了算法的有效性和实用性.     

区间量测下基于无迹变换的伯努利粒子滤波算法

针对区间量测下目标的实时检测与跟踪问题,提出基于无迹变换的伯努利粒子滤波算法(Bernoulli- Upf).该算法在伯努利粒子滤波算法(Bernoulli-pf)的基础上融合无迹卡尔曼滤波(UKF),融合后的算法在预测步骤产生持续存活粒子时,充分考虑到当前时刻的量测,从而引导粒子向高似然区域移动,使得粒子分布更加接近真实状态的后验分布.仿真实验表明,Bernoulli-Upf算法的估计精度优于Bernoulli-pf算法.     

State estimation using the particle filter with mode tracking

A particle filter is a data assimilation scheme that employs a fully nonlinear, non-Gaussian analysis step. Unfortunately as the size of the state grows the number of ensemble members required for the particle filter to converge to the true solution increases exponentially. To overcome this Vaswani [Vaswani N. 2008. IEEE Trans Signal Process 56:4583–97] proposed a new method known as mode tracking to improve the efficiency of the particle filter. When mode tracking, the state is split into two subspaces. One subspace is forecast using the particle filter, the other is treated so that its values are set equal to the mode of the marginal pdf. There are many ways to split the state. One hypothesis is that the best results should be obtained from the particle filter with mode tracking when we mode track the maximum number of unimodal dimensions. The aim of this paper is to test this hypothesis using the three dimensional stochastic Lorenz equations with direct observations. It is found that mode tracking the maximum number of unimodal dimensions does not always provide the best result. The best choice of states to mode track depends on the number of particles used and the accuracy and frequency of the observations.     

混沌映射采样的粒子滤波器

针对粒子滤波粒子多样性减弱引起的粒子枯竭问题,提出一种新的基于混沌映射采样的粒子滤波改进算法（CMS-PF）．在重要性采样之后,用类似载波的方法将离线生成的混沌序列映射到以较大权重粒子为中心的样本子空间,从而生成一些映射粒子,并结合当前时刻的预测粒子构建候选粒子集,最终依据各粒子自身的权重实现优选．仿真结果表明,该算法能有效提高对非线性系统状态的估计精度．     

基于用户行为分析的手势跟踪方法

人手结构的高维性而导致粒子滤波跟踪方法中采样数目非常庞大,是实现运动人手的实时性跟踪研究的主要障碍之一.以降低粒子数目为目标,以行为分析和建模为切入点,提出一种手势跟踪方法.首先分析操作者在手势操作过程中的行为特征,建立人手运动的动态模型;其次,研究动态模型的基本特征,并给出一种描述方法;然后,建立人手运动的时段模型,分析了手势状态的时间-空间关系.在此基础上,提出了状态变量微观结构的概念,重点给出了基于状态变量微观结构的手势跟踪算法;最后,设计和完成了实验,并与相关参考文献方法的实验结果进行对比.结果表明,采用该算法,用少量粒子就可以得到比较精确的跟踪结果.提出的核心算法已经用于一个基于自然手势交互的三维虚拟装配原型系统.     

利用多特征混沌粒子滤波的视觉目标跟踪方法

随着摄像终端的增多以及自动视频分析需求量的增大,针对视频序列中存在突然运动、遮挡、运动模糊等干扰因素时传统视觉目标跟踪方法很难获得鲁棒性高、精确稳定的目标跟踪的问题,提出了利用多特征混沌粒子滤波的视觉目标跟踪方法。首先,基于非线性动力学预测进行混沌建模,利用混沌映射的梯度优化函数来搜索状态空间以找到参考轨迹;然后设计了一种用于视觉跟踪的混沌粒子滤波器,并改进运动表观模型,引入颜色、纹理和深度的特征完善滤波器的性能;最后,将多特征混沌粒子滤波器与其他视觉目标跟踪方法应用于VOT17和TB 数据集进行对比分析,以论证该方法的准确性。结果表明,提出的多特征混沌粒子滤波方法显著减少了粒子数量、搜索空间和滤波器发散,其精度高出其他方法约10%,在突然运动、遮挡和运动模糊等情况下整体性能优于其他几种对比方法。