基于模糊逻辑的多特征融合的SOAMST跟踪算法

针对复杂环境条件下颜色、光照变化和遮挡对目标跟踪算法精度和鲁棒性的影响,论文提出了基于模糊逻辑多特征融合的SOAMST跟踪算法。首先,选择颜色特征和LBP特征对目标进行建模,并根据模糊逻辑算法调整两种特征在计算目标质心位置和权重图像中的权重;其次,目标被遮挡暂时消失时,根据SOAMST算法得到上一帧目标的状态信息,调用粒子滤波算法对目标位置进行预测,可以避免丢失跟踪目标,实现目标连续跟踪。实验表明,论文算法在复杂环境条件下能很好地实现目标跟踪。     

一种复杂场景下的运动目标跟踪算法

提出了一种基于跟踪窗口自适应和抗遮挡的目标跟踪算法。采用Mean Shift算法确定当前帧的目标位置,最优选取核函数带宽,使跟踪窗口能够根据目标尺寸大小作出自适应调整。利用Bhattacharyya系数作为遮挡的判断依据,当目标遮挡时引入卡尔曼滤波器估计目标的运动信息,进行后续状态预测。实验表明,该算法能有效跟踪复杂场景下的运动目标。     

基于遮挡检测和时空上下文信息的目标跟踪算法*

基于时空上下文信息的目标跟踪算法利用目标与背景之间的时空关系,在一定程度上解决静态遮挡问题,但当目标出现较大遮挡或快速运动目标被背景中物体遮挡(动态遮挡)时,仍然会出现跟踪不准确或跟丢的情况.基于此种情况,文中提出基于遮挡检测和时空上下文信息的目标跟踪算法.首先利用首帧图像中压缩后的光照不变颜色特征构造并初始化时空上下文模型.然后利用双向轨迹误差对输入的视频帧进行遮挡情况判断.如果相邻帧间目标区域特征点的双向匹配误差小于给定阈值,说明目标未出现严重遮挡或动态遮挡,可以利用时空上下文模型进行准确跟踪.否则利用文中提出的组合分类器对后续帧进行目标检测,直至重新检测到目标,同时对上下文模型和分类器进行在线更新.在多个视频帧序列上的测试表明,文中算法可以较好地解决复杂场景下较严重的静态遮挡和动态遮挡问题.     

等级关联的粒子群迭代多目标检测跟踪

针对目标在跟踪过程中受环境变化影响(光照、遮挡等)使其跟踪发生偏移的问题,提出一种从目标粗匹配到粒子群算法精确定位的等级关联结构的多目标跟踪算法.与现有跟踪算法相比,在粗匹配阶段粒子随机产生过程中融入了上下文信息,提高了目标匹配的准确度,降低了错误跟踪的目标数;对于在粒子群精确定位阶段有显著偏差的目标位置,采用Metropolis-Hastings采样算法进行纠正,同时完成模板更新,从而保证了目标跟踪的准确性.实验结果表明,该算法在目标被遮挡的情形下能够准确地跟踪被遮挡的目标.     

基于遮挡检测和多块位置信息融合的分块目标跟踪算法

目标跟踪无法有效判断目标何时被遮挡以及同时配合模板更新.针对这一问题,文中提出基于遮挡检测和多块位置信息融合的分块目标跟踪算法.首先,将目标区域分成4个子块,结合目标整体,利用遮挡具有从局部开始和方向性的特点,计算各分块间相关值的比值,判断目标是否遮挡及遮挡部位.再根据目标是否遮挡,采用不同的更新方式.最后,根据未被遮挡的各个分块位置信息确定最终目标的位置.在数据集上的实验表明,文中算法可以有效判定目标是否存在遮挡,并提升遮挡情况下的跟踪效果.     

基于混合粒子滤波和稀疏表示的目标跟踪算法

针对图像序列中的运动目标在跟踪过程中易受到光照等复杂环境、外观变化及部分遮挡影响的问题,提出基于全局信息和局部信息的混合粒子滤波算法.将目标的局部二元模式纹理特征引入粒子滤波算法,通过稀疏编码目标子块,充分利用目标的局部空间信息,并结合全局信息以确定当前帧中目标的位置.在跟踪过程中实时更新模板,这在一定程度上提高算法的鲁棒性.实验表明在目标处于复杂环境中算法能达到较理想的跟踪效果.     

在线特征选择和遮挡处理的目标跟踪*

为了提高相似物体干扰、光照变化等复杂环境下目标跟踪的稳定性,提出利用Fisher准则的在线选择鉴别性特征,将在线特征选择嵌入到跟踪算法中。但是,在目标被严重遮挡时仍在线选择鉴别性特征,会使目标模板偏移,导致跟踪失败。为了在目标被严重遮挡的情况下仍能在线选择鉴别性目标特征,选择一个可靠的子区域来推测被遮挡目标的颜色特征,再选择鉴别性特征。实验结果表明该方法在相似物体干扰、被跟踪目标被遮挡等复杂环境下极大地改善了跟踪的稳定性。     

基于深度信息的压缩感知人脸检测跟踪

传统的压缩感知跟踪是基于彩色视频图像序列中的目标跟踪, 但在跟踪过程中可能会受到光照变化和旋转遮挡因素的影响, 从而导致复杂环境下跟踪结果的鲁棒性不足. 为了获得稳定的跟踪结果, 提出了一种基于深度信息的压缩感知人脸检测跟踪算法. 首先, 根据改进的质心分割算法确定首帧深度图中人脸的跟踪位置. 其次, 根据深度信息计算出深度图中每一点对应的平均曲率并形成平均曲率图. 然后, 基于平均曲率图随机提取压缩特征; 最后, 通过压缩降维, 目标邻域搜索, 迭代更新特征模板, 计算出平均曲率图中下一帧人脸的最优跟踪位置, 实现人脸跟踪. 实验结果表明, 将人脸的深度信息和压缩感知特征相结合在光照变化和旋转遮挡情况下具有很好的鲁棒性, 能更好的实现复杂背景下对多姿态人脸的跟踪.     

抗遮挡与尺度自适应的改进KCF跟踪算法

核相关滤波(kernel correlation filter,KCF)目标跟踪算法在目标发生尺度变化或受长时间遮挡时无法实现准确跟踪.对此,提出一种融合窗口滤波的抗遮挡尺度自适应的目标跟踪算法.首先,利用快速尺度估计对跟踪目标进行尺度变换;然后,当检测到目标受到遮挡时停止对分类器模型的更新,融合加权窗口滤波器对目标位置进行预测,并利用预测信息修正目标跟踪区域;最后,将所提出算法移植到DJI Guidance视觉平台上并为其设计跟踪实验.实验结果表明,该算法能够有效解决目标尺度变化与目标受遮挡等跟踪问题.     

基于粒子滤波和压缩感知的目标跟踪算法

为了解决目标跟踪过程中出现的目标遮挡和光照变化问题,提出一种基于粒子滤波和压缩感知的目标跟踪算法。算法融合颜色特征和纹理特征来描述目标,增强算法在光照变化和复杂环境下的鲁棒性;利用压缩感知理论对特征进行降维,提高算法实时性;最后,根据粒子滤波原理估计目标状态,得到目标位置。实验结果表明,本算法在有效减少算法运行时间的前提下,能够准确跟踪遮挡和光照变化情况下的目标。     

一种基于集中式融合的多模型图像跟踪系统

本文设计了一种多模型的图像跟踪系统，并采用集中式结构来融合各种模型的跟踪结果．由于图像中噪声的存在、遮挡现象的发生以及被跟踪对象的变形会对某些跟踪算法产生影响，因此，一个比较理想的跟踪系统应该能够融合这些跟踪算法的优点，从而稳定地跟踪目标．本系统采用了两个跟踪模式，分别是基于区域的和基于特征点的跟踪方法．两种模式分别得到量测，并由相关系数判定遮挡，从而决定哪些跟踪结果送到融合中心．仿真试验表明，这种算法能有效提高跟踪精度，并具有较强的鲁棒性．     

基于加权直方图和均值漂移的实时跟踪算法

均值漂移算法在跟踪过程中没有有效利用跟踪目标的位置、运动方向等信息,当物体快速移动、旋转时,实时跟踪的目标极易丢失;均值漂移算法利用密度梯度估计跟踪目标,直方图足用来统计图像或图像的某个区域中每个灰度级或颜色级的分布情况的,依据颜色分布进行匹配具有较好的稳定性.跟踪目标的直方图受目标形状变化的影响较小,但通常直方图不包含任何的空间位置信息,加权直方图有效利用了窄间信息.提出了一种加权直方图和均值漂移算法相结合的快速实时跟踪算法.实验证明该算法具有速度快、鲁棒性、稳定的特点,基本达到了实时跟踪处理的要求.     

Robust containment tracking of uncertain linear multi-agent systems: a non-smooth control approach

This paper addresses the distributed robust containment tracking problem of networked systems with uncertain linear dynamics and multiple controlled leaders. The uncertainty class considered in this paper satisfies some matched conditions. To achieve containment tracking in such a multi-agent system, some distributed controllers consisting of using relative state-based continuous feedback and a non-smooth manoeuvre are developed. By transforming the containment tracking problem into the global robust stabilisation problem of interconnected systems, it is shown that the states of followers will asymptotically converge to a convex hull formed by those of the leaders if the control parameters in the proposed controllers are appropriately selected. It is clearly pointed out that the involved control parameters can be successfully found for solving the containment tracking problem if each follower can be directly or indirectly influenced by at least one leader, and the nominal dynamics of followers are stabilisable. The important issue of how fast containment can be achieved is also addressed. Finally, some numerical simulations are given for illustration.     

Target tracking algorithm based on optical flow method using corner detection

The tracking speed and accuracy are two most important parameters for a target tracking system. In our study, the proposed target tracking algorithm combines the Harris method and the optical flow method. To improve the tracking speed, the Harris method is initially used to extract some target corner features, and the optical flow method is then used to more accurately match corner features for the subsequent video frames. When the tracked target is rotated or distorted, the barycenter algorithm is employed to compute the barycenter of those matched features of target. To meet the real-time-tracking requirement, a small-zone image searching method and a high speed digital signal processing system are also designed. Our experimental study shows that the method described in this paper has high accuracy of target tracking, and can be applied to the situations of rotated, distorted, and/or shielded targets, although it has a limitation that it is only suitable for smaller targets.     

Decision-aware data suppression in wireless sensor networks for target tracking applications

Target tracking applications of wireless sensor networks (WSNs) may provide a high performance only when a reliable collection of target positions from sensor nodes is ensured. The performance of target tracking in WSNs is affected by transmission delay, failure probability, and nodes energy depletion. These negative factors can be effectively mitigated by decreasing the amount of transmitted data. Thus, the minimization of data transfers from sensor nodes is an important research issue for the development of WSN-based target tracking applications. In this paper, a data suppression approach is proposed for target chasing in WSNs. The aim of the considered target chasing task is to catch a moving target by a mobile sink in the shortest time. According to the introduced approach, a sensor node sends actual target position to the mobile sink only if this information is expected to be useful for minimizing the time in which target will be caught by the sink. The presented method allows sensor nodes to evaluate the usefulness of sensor readings and select those readings that have to be reported to the sink. Experiments were performed in a simulation environment to compare effectiveness of the proposed approach against state-of-the-art methods. Results of the experiments show that the presented suppression method enables a substantial reduction in the amount of transmitted data with no significant negative effect on target chasing time.     

Tracking ability in subjects symptomatic of cumulative trauma disorder: does it relate to disability?

Symptoms of upper extremity cumulative trauma disorders (CTDs) often include weakness, discomfort, pain, numbness and stiffness, which are generally assessed clinically by using static tests or isolated movements. Little is known about the dynamic, functional ability of the upper extremity in CTD, yet, more than impairment, performance variables may relate to disability. The objectives of this study were to determine whether a manual tracking task was sensitive to the presence of symptoms associated with CTD and whether tracking performance related to disability. Forty-five volunteers who had frequently experienced one or more symptoms consistent with upper extremity CTD for at least 1 year and 22 control subjects performed the manual tracking task. Using a hand-held stylus over a digitizing tablet, subjects tracked a target that moved pseudo-randomly and was displayed on a computer screen. The root mean square error of the linear difference between target and stylus positions provided a measure of overall performance accuracy. Quadrant specific performance was also calculated to determine whether the location of the target (hence hand and wrist position) influenced performance. Additionally, the symptomatic group completed the Disability of the Arm, Shoulder and Hand (DASH) questionnaire reflecting physical disability level. Performance accuracy was poorer in symptomatic subjects than controls (p<0.001) and was influenced by target location (p<0.0001). The overall performance was associated with physical disability (r = 0.54). The findings suggest that tracking performance is sensitive to the presence of CTD symptoms and related to disability level. Further validation is required to determine whether the performance measure is sensitive to disease progression or intervention-induced changes.     

航天测量船雷达天线前馈技术应用分析

航天测量船船载雷达设备在海上使用时的跟踪精度受到船体摇晃的影响,尤其是在海况不理想的状况下。因此采用一种技术,使得既不改变跟踪稳定性又能很好的隔离船摇就显得非常重要。通过补偿前馈给天线方位和俯仰是一种非常好的的方法。介绍了航天测量船雷达船摇前馈补偿技术,根据原理推导出了补偿船摇、目标运动产生的跟踪误差的前馈方程,并根据推导结果进行了实际应用分析。     

融合YOLO检测的多目标跟踪算法

针对目前视频多目标跟踪过程中的遮挡问题,提出了一种融合YOLO v3的多目标检测和跟踪算法,选定基于检测跟踪的框架作为跟踪的整体框架,使用YOLO v3来实现对目标信息的检测工作,在选定某一检测类别的基础上,使用本文提出的跟踪算法,通过数据关联完成对此类别的多目标跟踪,并针对跟踪过程中的目标遮挡问题以及因目标遮挡而引起的轨迹跟踪异常的问题,提出了修正算法。测试视频中被遮挡的大部分目标都能准确地跟踪,但在背景移动时也会发生一部分目标身份互换的情况。所提出的算法在解决多目标跟踪中的遮挡问题时具有一定的准确性和实时性。     

基于颜色-纹理特征的目标跟踪

针对传统的基于颜色特征目标跟踪算法在一些复杂场景中存在的跟踪不稳定性,提出一种基于颜色 纹理特征的目标跟踪算法;在传统的基于颜色Mean shift的目标跟踪算法中加入纹理特征,在提取目标颜色特征的同时提取目标的纹理特征,并且采取串接原则,在搜索目标新位置时仍然沿用传统的基于颜色的均值漂移跟踪算法,但在每一次迭代过程搜寻目标最佳的位置点即特征相似最大的区域时,利用纹理特征来实现,并且采用八邻域搜索法（候选区域周围扩大八个大小相等的区域）来解决部分遮挡的问题。通过对比实验表明,该算法在复杂场景中表现出的实时性和鲁棒性较好。关键词：     

Measuring consistency of web page design and its effects on performance and satisfaction

Symptoms of upper extremity cumulative trauma disorders (CTDs) often include weakness, discomfort, pain, numbness and stiffness, which are generally assessed clinically by using static tests or isolated movements. Little is known about the dynamic, functional ability of the upper extremity in CTD, yet, more than impairment, performance variables may relate to disability. The objectives of this study were to determine whether a manual tracking task was sensitive to the presence of symptoms associated with CTD and whether tracking performance related to disability. Forty-five volunteers who had frequently experienced one or more symptoms consistent with upper extremity CTD for at least 1 year and 22 control subjects performed the manual tracking task. Using a hand-held stylus over a digitizing tablet, subjects tracked a target that moved pseudo-randomly and was displayed on a computer screen. The root mean square error of the linear difference between target and stylus positions provided a measure of overall performance accuracy. Quadrant specific performance was also calculated to determine whether the location of the target (hence hand and wrist position) influenced performance. Additionally, the symptomatic group completed the Disability of the Arm, Shoulder and Hand (DASH) questionnaire reflecting physical disability level. Performance accuracy was poorer in symptomatic subjects than controls (p<0.001) and was influenced by target location (p<0.0001). The overall performance was associated with physical disability (r = 0.54). The findings suggest that tracking performance is sensitive to the presence of CTD symptoms and related to disability level. Further validation is required to determine whether the performance measure is sensitive to disease progression or intervention-induced changes.