基于大数据分析的移动对象轨迹预测方法

对移动对象的轨迹预测将在移动目标跟踪识别中具有较好的应用价值。移动对象轨迹预测的基础是移动目标运动参量的采集和估计,移动目标的运动参量信息特征规模较大,传统的单分量时间序列分析方法难以实现准确的参量估计和轨迹预测。提出一种基于大数据多传感信息融合跟踪的移动对象轨迹预测算法。首先进行移动目标对象进行轨迹跟踪的控制对象描述和约束参量分析,对轨迹预测的大规模运动参量信息进行信息融合和自正整定性控制,通过大数据分析方法实现对移动对象运动参量的准确估计和检测,由此指导移动对象轨迹的准确预测,提高预测精度。仿真结果表明,采用该算法进行移动对象的运动参量估计和轨迹预测的精度较高,自适应性能较强,稳健性较好,相关的指标性能优于传统方法。     

基于改进高斯混合模型的实时运动目标检测与跟踪*

为提高运动目标检测与跟踪的可靠性,提出了一种基于改进高斯混合模型的实时运动目标检测与跟踪算法。该算法建立可自动调节分布数目的高斯混合背景模型,通过背景减除获取前景图像;利用目标相邻帧的连续性分割运动目标;在此基础上将传统的颜色直方图模型进行改进,提高目标颜色分布的可信度,进而根据目标的位置、大小和颜色构造运动目标全局匹配相似度函数,实时完成运动目标检测与跟踪。利用大量的监控视频数据进行验证,结果表明,与传统的检测跟踪算法相比,该算法减少了计算量,提高了复杂背景情况下运动目标检测与跟踪的可靠性。     

基于约束策略的WSN低能耗粒子滤波跟踪算法

目标跟踪是无线传感器网络研究的关键技术之一,如何在保证较低能量消耗的前提下,实现监测场景中运动目标准确跟踪是需要解决的问题。在深入研究分析传感器网络目标跟踪算法的基础上,提出了基于约束策略的WSN低能耗粒子滤波跟踪算法。该算法采用动态分簇,既减少网络的能量消耗,又保证监测目标节点的数量;在跟踪过程中,采用约束策略得出目标估计区域,对粒子采样结果进行优化,同时对状态空间模型进行改进,增强粒子对目标的跟踪能力。仿真结果表明,提出的跟踪算法有效的实现目标的跟踪,在保证低能耗的同时提高了跟踪精度。     

A Nonparametric Adaptive Tracking Algorithm Based on Multiple Feature Distributions

This paper presents an object tracking framework based on the mean-shift algorithm, which is a nonparametric technique that uses statistical color distribution of objects. Tracking objects through highly similar-colored background is one of the problems that need to be addressed. In various cases where object and background color distributions are very similar, the color distribution obtained from single frame alone is not sufficient to track objects reliably. To deal with this problem, the proposed algorithm utilizes an adaptive statistical background and foreground modeling to detect the change due to motion using kernel density estimation techniques based on multiple recent frames. The use of multiple frames supplies more information than single frame and thus it provides more accurate modeling of both background and foreground. In addition to color distribution, this statistical multiple frame-based motion representation is integrated into a modified mean-shift algorithm to create more robust object tracking framework. The use of motion distribution provides additional discriminative power to the framework. The superior performance with quantitative results of the framework has been validated using experiments on synthetic and real sequence of images     

一种基于高斯概率模型的多人跟踪算法

针对视频监控中的多人跟踪问题,提出了一种基于高斯概率模型的算法.基于目标颜色的统计特征,采用改进的K均值方法,将目标区域按颜色信息聚类,并根据聚类结果对目标区域分块,然后用高斯模型对各分块分别进行建模.同时,对目标的位置信息也进行高斯建模.通过计算待检测目标与模型之间颜色和位置的最大联合概率值来实现跟踪.利用前后帧中目标的位置信息及颜色信息,能克服目标遮挡后因信息的丢失而跟踪失败的情况.实验结果表明,该算法具有较强的鲁棒性,能有效实现多人的跟踪.     

自适应紧致特征的超像素目标跟踪

目的 针对现有的超像素目标跟踪算法（RST）对同一类中分别属于目标和相似干扰物体的超像素块赋予相同特征置信度,导致难以区分目标和相似干扰物的问题,为此提出自适应紧致特征的超像素目标跟踪算法（ACFST）。方法 该方法在每帧的目标搜索区域内构建适合目标大小的自适应紧致搜索区域,并将该区域内外的特征置信度分别保持不变和降低。处于背景中的相似干扰物体会被该方法划分到紧致搜索区域外,其特征置信度被降低。当依据贝叶斯推理框架求出对应最大后验概率的目标时,紧致搜索区域外的特征置信度低,干扰物体归属目标的程度也低,不会被误判为目标。结果 在具有与目标相似干扰物体的两个视频集进行测试,本文ACFST跟踪算法与RST跟踪算法相比,平均中心误差分别缩减到5.4像素和7.5像素,成功率均提高了11%,精确率分别提高了10.6%和21.6%,使得跟踪结果更精确。结论 本文提出构建自适应紧致搜索区域,并通过设置自适应的参数控制紧致搜索区域变化,减少因干扰物体与目标之间相似而带来的误判。在具有相似物体干扰物的视频集上验证了本文算法的有效性,实验结果表明,本文算法在相似干扰物体靠近或与目标部分重叠时,能够保证算法精确地跟踪到目标,提高算法的跟踪精度,具有较强的鲁棒性,使得算法更能适应背景杂乱、目标遮挡、形变等复杂环境。     

Object tracking by exploiting adaptive region-wise linear subspace representations and adaptive templates in an iterative particle filter

Aiming at tracking visual objects under harsh conditions, such as partial occlusions, illumination changes, and appearance variations, this paper proposes an iterative particle filter incorporated with an adaptive region-wise linear subspace (RWLS) representation of objects. The iterative particle filter employs a coarse-to-fine scheme to decisively generate particles that convey better hypothetic estimates of tracking parameters. As a result, a higher tracking accuracy can be achieved by aggregating the good hypothetic estimates from particles. Accompanying with the iterative particle filter, the RWLS representation is a special design to tackle the partial occlusion problem which often causes tracking failure. Moreover, the RWLS representation is made adaptive by exploiting an efficient incremental updating mechanism. This incremental updating mechanism can adapt the RWLS to gradual changes in object appearances and illumination conditions. Additionally, we also propose the adaptive mechanism to continuously adjust the object templates so that the varying appearances of tracked objects can be well handled. Experimental results demonstrate that the proposed approach achieves better performance than other related prior arts.     

具有尺度和旋转适应性的长时间目标跟踪

目标发生尺度和旋转变化会给长时间目标跟踪带来很大的挑战,针对该问题,本文提出了具有尺度和旋转适应性的鲁棒目标跟踪算法.首先针对跟踪过程中目标存在的尺度变化和旋转运动,提出一种基于傅里叶-梅林变换和核相关滤波的目标尺度和旋转参数估计方法.该方法能够实现连续空间的目标尺度和旋转参数估计,采用核相关滤波提高了估计的鲁棒性和准确性.然后针对长时间目标跟踪过程中,有时不可避免地会出现跟踪失败的情况（例如由于长时间半遮挡或全遮挡等）,提出一种基于直方图和方差加权的目标搜索方法.当目标丢失时,通过提出的搜索方法能够快速从图像中确定目标可能存在的区域,使得跟踪算法具有从失败中恢复的能力.本文还训练了两个核相关滤波器用于估计跟踪结果的置信度和目标平移,通过专门的核相关滤波器能够使得估计的跟踪结果置信度更加准确和鲁棒,置信度的估计结果可用于激活基于直方图和方差加权的目标搜索模块,并判断搜索窗口中是否包含目标.本文在目标跟踪标准数据集（Online object tracking benchmark,OTB）上对提出的算法和目前主流的目标跟踪算法进行对比实验,验证了本文提出算法的有效性和优越性.     

Research on adaptive target tracking in vehicle sensor networks

For resource-constrained vehicle sensor networks (VSNs), consisting of vehicle nodes and monitor nodes, the crucial task is to track the movement of vehicles in the monitor area. In this paper, we study the problem of how to achieve the precise vehicle tracking with minimized energy consumption. We first demonstrate that the precise vehicle tracking cannot be realized when only one type sensor is equipped on monitor node. Then we employ Gaussian mixture model (GMM) to describe the distribution of the different sensory data collected by various sensors, while the mean-shift algorithm is adopted to predict the location. To obtain better performance, we further use maximum likelihood estimation to improve the monitor precision. Finally, we propose an adaptive vehicle tracking algorithm (AVT), which uses sector awakened area and sigmoid function to reduce the number of participated monitor nodes for the sake of reducing the energy. Extensive experiments are carried out to evaluate AVT with several performance criteria. Our experiment results show that the proposed AVT algorithm can effectively track mobile vehicle and perform high efficiency in conserving energy.     

基于自适应SR-CKF的序贯式WSNs目标跟踪算法

针对无线传感器网络(WSNs)动态目标跟踪问题,即通过对传感器获取的动态系统状态进行估计,预测目标的位置.提出一种基于自适应平方根容积卡尔曼(SR-CKF)的序贯式WSNs动态目标跟踪算法.该算法在运算过程中直接传递目标状态均值和协方差矩阵的平方根因子,降低了计算的复杂度.将目标跟踪过程序贯式地分配到动态簇集的每一个节点上,减小了无线通信过程中碰撞和干扰现象的发生,降低了节点通信和计算负担.针对不良观测信息,基于新息协方差匹配原理,建立了自适应SR-CKF,提高了整个系统的鲁棒性.实验仿真结果表明,本文提出的基于自适应SR-CKF的序贯式WSNs目标跟踪算法有效的提高了跟踪的精度和稳定性并且减小了传感器节点间通信的能量损耗.     

一种鲁棒高效的视频运动目标检测与跟踪算法

提出了一种视频运动目标的快速检测和稳定跟踪算法. 目标检测使用减背景法, 用均值法构造背景图像, 提出一种基于熵能和广义高斯分布的局部自适应阈值选取算法, 可有效克服噪声的影响. 采用基于特征匹配的目标跟踪方法, 提出一种LICS (Logarithm illuminance contrast statistic)特征, 该特征能够更加充分有效地表征目标, 可在光照和目标姿态变化的情况下实现刚体目标的稳定跟踪. 使用Kalman滤波限制搜索匹配范围以减小计算量. 用目标子区域匹配的方法解决目标相互遮挡时的跟踪问题. 实验结果表明, 该算法在运动目标检测效果、跟踪稳定性和运行时间方面都有良好的性能.     

Hybrid tracking based on color histogram for intelligent space

The vision sensor network is expected to achieve a contact-free wide-area location system without any additional burden on users in intelligent environments. In this article, a tracking algorithm for a location system in an intelligent environment is described. A modified color tracker based on a Kalman filter and a mean shift procedure is proposed in order to improve the robustness for occlusion and rapid movement. To handle the sudden change in object movement, we propose a hybrid tracking algorithm, including an adaptive feedback loop, based on the statistics of color histogram models after the mean-shift process. Experimental results showed that the proposed method achieves more robust tracking of multiple objects than the conventional method.     

Generalized adaptive notch filters with frequency debiasing for tracking of polynomial phase systems

Generalized adaptive notch filters are used for identification/tracking of quasi-periodically varying dynamic systems and can be considered an extension, to the system case, of classical adaptive notch filters. For general patterns of frequency variation the generalized adaptive notch filtering algorithms yield biased frequency estimates. We show that when system frequencies change slowly in a smooth way, the estimation bias can be substantially reduced by means of post-filtering of the frequency estimates. The modified (debiased) algorithm has better tracking capabilities than the original algorithm.     

基于Meanshift和粒子滤波的行人目标跟踪方法

针对粒子滤波跟踪算法计算代价大以及Meanshift跟踪算法容易陷入局部极值等问题,提出一种嵌入均值优化的粒子滤波跟踪算法。该算法根据粒子滤波的运动模型估计目标区域位置,利用Bhattacharyya距离度量粒子区域和目标模型的相似性,并根据相似性来更新粒子权值,使用Meanshift优化算法改善粒子的估计位置,使得这些粒子的候选区域能更加接近目标模板,极大提高了粒子的使用效率。实验结果表明,该算法能够有效进行人的跟踪,处理人的短暂遮挡问题,性能优于粒子滤波算法,有较好的实用性。     

Energy-efficient real-time object tracking in multi-level sensor networks by mining and predicting movement patterns

A number of studies have been written on sensor networks in the past few years due to their wide range of potential applications. Object tracking is an important topic in sensor networks; and the limited power of sensor nodes presents numerous challenges to researchers. Previous studies of energy conservation in sensor networks have considered object movement behavior to be random. However, in some applications, the movement behavior of an object is often based on certain underlying events instead of randomness completely. Moreover, few studies have considered the real-time issue in addition to the energy saving problem for object tracking in sensor networks. In this paper, we propose a novel strategy named multi-level object tracking strategy (MLOT) for energy-efficient and real-time tracking of the moving objects in sensor networks by mining the movement log. In MLOT, we first conduct hierarchical clustering to form a hierarchical model of the sensor nodes. Second, the movement logs of the moving objects are analyzed by a data mining algorithm to obtain the movement patterns, which are then used to predict the next position of a moving object. We use the multi-level structure to represent the hierarchical relations among sensor nodes so as to achieve the goal of keeping track of moving objects in a real-time manner. Through experimental evaluation of various simulated conditions, the proposed method is shown to deliver excellent performance in terms of both energy efficiency and timeliness.     

粒子滤波的视频目标跟踪算法研究

目标跟踪是计算机视觉和图像处理的一个重点课题,在视频监控、机器人视觉导航以及智能交通控制中具有广泛的应用前景.通过粒子滤波技术,研究了如何整合颜色特征、前景信息和积分图运算等技术实现视频目标跟踪的粒子滤波算法.在对目标进行分割中采用了混合高斯背景建模方法;同时结合积分直方图的计算方法对颜色特征进行分段统计及相互遮挡的判断,实现基于粒子滤波的目标跟踪算法的优化,解决跟踪中诸如遮挡、光照变化、背景干扰、尺寸变化等难以解决的问题.实验结果表明提出的方法达到了预期目标.     

A Competitive Neural Network for Multiple Object Tracking in Video Sequence Analysis

Tracking of moving objects in real situation is a challenging research issue, due to dynamic changes in objects or background appearance, illumination, shape and occlusions. In this paper, we deal with these difficulties by incorporating an adaptive feature weighting mechanism to the proposed growing competitive neural network for multiple objects tracking. The neural network takes advantage of the most relevant object features (information provided by the proposed adaptive feature weighting mechanism) in order to estimate the trajectories of the moving objects. The feature selection mechanism is based on a genetic algorithm, and the tracking algorithm is based on a growing competitive neural network where each unit is associated to each object in the scene. The proposed methods (object tracking and feature selection mechanism) are applied to detect the trajectories of moving vehicles in roads. Experimental results show the performance of the proposed system compared to the standard Kalman filter.     

一种基于背景模型的运动目标检测与跟踪算法

本文提出了一种静止摄像机条件下的运动目标检测与跟踪算法．它以一种改进的自适应混合 高斯模型为背景更新方法，用连通区检测算法分割出前景目标，以Kalman滤波为运动模型实 现对运动目标的连续跟踪．在目标跟踪时，该算法针对目标遮挡引起的各种可能情况进行了 分析，引入了对运动目标的可靠性度量，增强了目标跟踪的稳定性和可靠性．在对多个室外 视频序列的实验中，该算法显示了良好的性能，说明它对于各种外部因素的影响，如光照变 化、阴影、目标遮挡等，具有很强的适应能力．     

A shape-based voting algorithm for pedestrian detection and tracking

This paper presents the MOUGH (mixture of uniform and Gaussian Hough) Transform for shape-based object detection and tracking. We show that the edgels of a rigid object at a given orientation are approximately distributed according to a Gaussian mixture model (GMMs). A variant of the generalized Hough transform is proposed, voting using GMMs and optimized via Expectation-Maximization, that is capable of searching images for a mildly-deformable shape, based on a training dataset of (possibly noisy) images with only crude estimates of scale and centroid of the object in each image. Further modifications are proposed to optimize the algorithm for tracking. The method is able to locate and track objects reliably even against complex backgrounds such as dense moving foliage, and with a moving camera. Experimental results indicate that the algorithm is superior to previously published variants of the Hough transform and to active shape models in tracking pedestrians from a side view.     

一种二元探测传感器网络目标跟踪算法

针对二元探测传感器网络目标定位与跟踪问题,提出一种递推的质心定位方法,推导出了质心定位算法的递推公式。采用序贯最小二乘估计方法,提出了基于递推计算的质心定位结果进行目标跟踪的算法。算法以简单的观测噪声模型体现系统的测量和计算误差,利用序贯最小二乘算法的可变增益,提高了跟踪精度;算法不需要先验统计信息以及序贯式的处理方式等因素,降低了算法的计算复杂度。仿真结果验证了递推公式的正确性和跟踪算法的有效性。