Data fusion for visual tracking with particles

The effectiveness of probabilistic tracking of objects in image sequences has been revolutionized by the development of particle filtering. Whereas Kalman filters are restricted to Gaussian distributions, particle filters can propagate more general distributions, albeit only approximately. This is of particular benefit in visual tracking because of the inherent ambiguity of the visual world that stems from its richness and complexity. One important advantage of the particle filtering framework is that it allows the information from different measurement sources to be fused in a principled manner. Although this fact has been acknowledged before, it has not been fully exploited within a visual tracking context. Here we introduce generic importance sampling mechanisms for data fusion and discuss them for fusing color with either stereo sound, for teleconferencing, or with motion, for surveillance with a still camera. We show how each of the three cues can be modeled by an appropriate data likelihood function, and how the intermittent cues (sound or motion) are best handled by generating proposal distributions from their likelihood functions. Finally, the effective fusion of the cues by particle filtering is demonstrated on real teleconference and surveillance data.     

Algorithmic and architectural optimizations for computationally efficient particle filtering.

In this paper, we analyze the computational challenges in implementing particle filtering, especially to video sequences. Particle filtering is a technique used for filtering nonlinear dynamical systems driven by non-Gaussian noise processes. It has found widespread applications in detection, navigation, and tracking problems. Although, in general, particle filtering methods yield improved results, it is difficult to achieve real time performance. In this paper, we analyze the computational drawbacks of traditional particle filtering algorithms, and present a method for implementing the particle filter using the Independent Metropolis Hastings sampler, that is highly amenable to pipelined implementations and parallelization. We analyze the implementations of the proposed algorithm, and, in particular, concentrate on implementations that have minimum processing times. It is shown that the design parameters for the fastest implementation can be chosen by solving a set of convex programs. The proposed computational methodology was verified using a cluster of PCs for the application of visual tracking. We demonstrate a linear speed-up of the algorithm using the methodology proposed in the paper.     

基于深度特征表达与学习的视觉跟踪算法研究

该文针对视觉跟踪中运动目标的鲁棒性跟踪问题,将深度学习引入视觉跟踪领域,提出一种基于多层卷积滤波特征的目标跟踪算法。该算法利用分层学习得到的主成分分析(PCA)特征向量,对原始图像进行多层卷积滤波,从而提取出图像更深层次的抽象表达,然后利用巴氏距离进行特征相似度匹配估计,进而结合粒子滤波算法实现目标跟踪。结果表明,这种多层卷积滤波提取到的特征能够更好地表达目标,所提跟踪算法对光照变化、遮挡、异面旋转、摄像机抖动都具有很好的不变性,对平面内旋转也具有一定的不变性,在具有此类特点的视频序列上表现出非常好的鲁棒性。     

Enhanced Particles With Pseudolikelihoods for Three-Dimensional Tracking

In this paper, we propose a new method to fuse sensing data of the most current observation into a 3-D visual tracker using pseudolikelihood functions with particle filtering techniques. With the proposed approach, the importance density function in particle filter can be modified to represent posterior states by particle crowds in a better way. Thus, it makes the tracking system more robust to noise and outliers. On the other hand, because the particle interpretation is performed in a much more efficient fashion, the number of particles used in tracking is greatly reduced, which improves the real-time performances of the system. Simulation and experimental results verified the effectiveness of the proposed method.      

单站被动目标的多假设距离粒子滤波跟踪

针对单站被动目标跟踪的无距离信息,多假设距离粒子滤波方法利用多个粒子滤波的并行运算,对不同初始距离的粒子滤波器进行计算,利用各子滤波的残差概率对并行处理的粒子滤波运算进行自适应采样实现单站纯方位目标跟踪,并与粒子滤波、多假设距离滤波方法进行比较,仿真结果表明该算法收敛速度快,跟踪精度高。     

Abrupt motion tracking via intensively adaptive Markov-chain Monte Carlo sampling

The robust tracking of abrupt motion is a challenging task in computer vision due to its large motion uncertainty. While various particle filters and conventional Markov-chain Monte Carlo (MCMC) methods have been proposed for visual tracking, these methods often suffer from the well-known local-trap problem or from poor convergence rate. In this paper, we propose a novel sampling-based tracking scheme for the abrupt motion problem in the Bayesian filtering framework. To effectively handle the local-trap problem, we first introduce the stochastic approximation Monte Carlo (SAMC) sampling method into the Bayesian filter tracking framework, in which the filtering distribution is adaptively estimated as the sampling proceeds, and thus, a good approximation to the target distribution is achieved. In addition, we propose a new MCMC sampler with intensive adaptation to further improve the sampling efficiency, which combines a density-grid-based predictive model with the SAMC sampling, to give a proposal adaptation scheme. The proposed method is effective and computationally efficient in addressing the abrupt motion problem. We compare our approach with several alternative tracking algorithms, and extensive experimental results are presented to demonstrate the effectiveness and the efficiency of the proposed method in dealing with various types of abrupt motions.     

基于粒子滤波的系数编码车辆跟踪方法

传统基于生成式的车辆跟踪方法仅考虑了目标信息,忽略了车辆背景信息,降低了目标与背景的表征能力.针对复杂背景条件下视觉导航对车辆跟踪精度的需求,提出了一种基于粒子滤波的系数编码车辆跟踪方法.该方法首先对获取的帧图像进行仿射变换归一化处理,并采用深度去噪自编码器对变换后的图像进行完备特征字典的生成;接着,采用稀疏编码对完备特征字典进行降维处理,消除网络高层目标特征的冗余信息,保留网络底层的高效关联特征;最后,将提取的深度稀疏编码特征应用到粒子滤波的框架内实现车辆的有效跟踪,有效克服了判别式跟踪方法无法处理遮挡问题的缺陷.实验结果表明,在尺度变化、光照变化以及遮挡等复杂环境下,本文方法将跟踪精度提升了17％,每秒处理的帧图像速度提升了64％.     

Target Tracking by Particle Filtering in Binary Sensor Networks

We present particle filtering algorithms for tracking a single target using data from binary sensors. The sensors transmit signals that identify them to a central unit if the target is in their neighborhood; otherwise they do not transmit anything. The central unit uses a model for the target movement in the sensor field and estimates the target's trajectory, velocity, and power using the received data. We propose and implement the tracking by employing auxiliary particle filtering and cost-reference particle filtering. Unlike auxiliary particle filtering, cost-reference particle filtering does not rely on any probabilistic assumptions about the dynamic system. In the paper, we also extend the method to include estimation of constant parameters, and we derive the posterior Cramer-Rao bounds (PCRBs) for the states. We show the performances of the proposed methods by extensive computer simulations and compare them to the derived bounds.     

Combination of Multiple Measurement Cues for Visual Face Tracking

Visual face tracking is an important building block for all intelligent living and working spaces, as it is able to locate persons without any human intervention or the need for the users to carry sensors on themselves. In this paper we present a novel face tracking system built on a particle filtering framework that facilitates the use of non-linear visual measurements on the facial area. We concentrate on three different such non-linear visual measurement cues, namely object detection, foreground segmentation and colour matching. We derive robust measurement likelihoods under a unified representation scheme and fuse them into our face tracking algorithm. This algorithm is complemented with optimum selection of the particle filter’s object model and a target handling scheme. The resulting face tracking system is extensively evaluated and compared to baseline ones.     

岛岸背景下的红外运动多目标跟踪

提出了一种基于粒子滤波和FCM的岛岸背景条件下红外运动多目标跟踪方法.通过对红外序列图像进行中值滤波、边缘提取、海天线检测和形态滤波等预处理,提取出若干个候选目标.然后利用基于粒子滤波和FCM的算法实现对候选目标的数据关联和连续跟踪.实验结果表明,该方法具有良好的可行性和效果.     

Distributed multi-sensor particle filter for bearings-only tracking

In this article, the classical bearings-only tracking (BOT) problem for a single target is addressed, which belongs to the general class of non-linear filtering problems. Due to the fact that the radial distance observability of the target is poor, the algorithm-based sequential Monte-Carlo (particle filtering, PF) methods generally show instability and filter divergence. A new stable distributed multi-sensor PF method is proposed for BOT. The sensors process their measurements at their sites using a hierarchical PF approach, which transforms the BOT problem from Cartesian coordinate to the logarithmic polar coordinate and separates the observable components from the unobservable components of the target. In the fusion centre, the target state can be estimated by utilising the multi-sensor optimal information fusion rule. Furthermore, the computation of a theoretical Cramer–Rao lower bound is given for the multi-sensor BOT problem. Simulation results illustrate that the proposed tracking method can provide better performances than the traditional PF method.     

Object tracking with particle filtering in fluorescence microscopy images: application to the motion of neurofilaments in axons

Neurofilaments are long flexible cytoplasmic protein polymers that are transported rapidly but intermittently along the axonal processes of nerve cells. Current methods for studying this movement involve manual tracking of fluorescently tagged neurofilament polymers in videos acquired by time-lapse fluorescence microscopy. Here, we describe an automated tracking method that uses particle filtering to implement a recursive Bayesian estimation of the filament location in successive frames of video sequences. To increase the efficiency of this approach, we take advantage of the fact that neurofilament movement is confined within the boundaries of the axon. We use piecewise cubic spline interpolation to model the path of the axon and then we use this model to limit both the orientation and location of the neurofilament in the particle tracking algorithm. Based on these two spatial constraints, we develop a prior dynamic state model that generates significantly fewer particles than generic particle filtering, and we select an adequate observation model to produce a robust tracking method. We demonstrate the efficacy and efficiency of our method by performing tracking experiments on real time-lapse image sequences of neurofilament movement, and we show that the method performs well compared to manual tracking by an experienced user. This spatially constrained particle filtering approach should also be applicable to the movement of other axonally transported cargoes.     

基于权重一致性优化的实时Marginalized粒子滤波算法

针对Marginalized粒子滤波中随机量测噪声对于非线性状态估计精度的不利影响以及线性状态估计中计算量较大问题,提出了一种基于权重一致性优化的实时Marginalized粒子滤波算法.首先,结合量测系统建模中先验信息的提取和利用,通过粒子权重间一致性距离和一致性矩阵的构建,提出了量测提升策略下权重的一致性优化方法,以改善粒子滤波在非线性状态估计中的滤波精度.其次,通过对Marginalized粒子滤波实现中时间更新和量测更新环节的结构优化,给出了实时Marginalized粒子滤波,以降低蒙特卡罗仿真实现下卡尔曼滤波在状态线性估计中的计算复杂度.最后,在两者的动态结合基础上给出了新算法具体实现步骤.利用基于单站雷达目标跟踪仿真场景,分析了算法性能.理论分析和仿真实验结果验证了算法的可行性和有效性.     

粒子滤波和均值漂移相结合目标跟踪算法

采用粒子滤波算法解决运动目标跟踪中非线性非高斯问题。将均值漂移算法嵌入到粒子滤波的采样阶段中,通过将每个粒子聚集到所在区域的局部极值,提高了采样粒子的使用效率。当发生目标遮挡时采用改进的粒子滤波算法,当无遮挡时采用均值漂移算法以提高速度。实验结果表明,该方法较传统单一算法具有较强的实时性和鲁棒性,能够有效实现在遮挡场景下的目标跟踪。     

基于距离像长度特征辅助的雷达目标跟踪

传统雷达目标跟踪仅利用角度和距离数据,由于获取的测量信息较少,跟踪精度受限。本文利用现代雷达所具有的距离高分辨能力,提出了一种基于距离像长度特征辅助的跟踪模型,并结合先进的非线性滤波算法得到了一种高性能目标跟踪算法—FAT UKF。该算法将目标的运动状态与距离像长度信息联系起来,通过增加观测量的维数来提高雷达的跟踪能力。对典型实例的计算机仿真结果表明,基于特征辅助的跟踪算法不仅收敛速度快,且能有效突破传统跟踪算法的理论误差下限,大大提高了雷达跟踪系统的整体性能。      

A generic framework for tracking using particle filter with dynamic shape prior.

Tracking deforming objects involves estimating the global motion of the object and its local deformations as functions of time. Tracking algorithms using Kalman filters or particle filters (PFs) have been proposed for tracking such objects, but these have limitations due to the lack of dynamic shape information. In this paper, we propose a novel method based on employing a locally linear embedding in order to incorporate dynamic shape information into the particle filtering framework for tracking highly deformable objects in the presence of noise and clutter. The PF also models image statistics such as mean and variance of the given data which can be useful in obtaining proper separation of object and background.     

基于粒子滤波的运动物体检测跟踪

提出了一种状态空间模型粒子滤波算法,并应用于运动目标的跟踪。该方法基于贝叶斯估计,利用粒子集来表示概率,通过递推的贝叶斯滤波来近似逼近最优化结果,在预设搜索区域用粒子群找到和目标模板最相似的中心位置,并以该位置作为观测值,进行跟踪。仿真实验结果和两种实际条件下效果比较表明该算法在跟踪低常速运动中精准性高,是一种有效的目标跟踪方法。     

Efficient object tracking by incremental self-tuning particle filtering on the affine group

We propose an incremental self-tuning particle filtering (ISPF) framework for visual tracking on the affine group, which can find the optimal state in a chainlike way with a very small number of particles. Unlike traditional particle filtering, which only relies on random sampling for state optimization, ISPF incrementally draws particles and utilizes an online-learned pose estimator (PE) to iteratively tune them to their neighboring best states according to some feedback appearance-similarity scores. Sampling is terminated if the maximum similarity of all tuned particles satisfies a target-patch similarity distribution modeled online or if the permitted maximum number of particles is reached. With the help of the learned PE and some appearance-similarity feedback scores, particles in ISPF become "smart" and can automatically move toward the correct directions; thus, sparse sampling is possible. The optimal state can be efficiently found in a step-by-step way in which some particles serve as bridge nodes to help others to reach the optimal state. In addition to the single-target scenario, the "smart" particle idea is also extended into a multitarget tracking problem. Experimental results demonstrate that our ISPF can achieve great robustness and very high accuracy with only a very small number of particles.     

Robust model adaption for colour-based particle filter tracking with contextual information

Color-based particle filters have emerged as an appealing method for targets tracking. As the target may undergo rapid and significant appearance changes, the template (i.e. scale of the target, color distribution histogram) also needs to be updated. Traditional updates without learning contextual information may imply a high risk of distorting the model and losing the target. In this paper, a new algorithm utilizing the environmental information to update both the scale of the tracker and the reference appearance model for the purpose of object tracking in video sequences has been put forward. The proposal makes use of the well-established color-based particle filter tracking while differentiating the foreground and background particles according to their matching score. A roaming phenomenon that yields the estimation to shrink and diverge is investigated. The proposed solution is tested using both simulated and publicly available benchmark datasets where a comparison with six state-of-the-art trackers has been carried out. The results demonstrate the feasibility of the proposal and lie down foundations for further research on tackling complex visual tracking problems.     

基于粒子滤波的RFID室内节点定位跟踪研究

为了解决复杂室内环境下的RFID动态节点定位跟踪问题,文中建立了动态节点的运动模型和信号测量模型。仿真采用基于信号RSSI定位方法,结合运用等边三角形定位算法。由于室内射频信号具有较高的噪声污染,因此首先对采集的信号运用粒子滤波技术进行滤波处理,然后运用高斯粒子滤波算法对室内移动的RFID进行了定位跟踪预测。仿真结果表明该算法可以有效地对室内动态节点进行定位跟踪,精度较高,稳定性好,结果进一步说明高斯粒子滤波能有效地抑制室内射频噪声。