Mean Shift tracking with multiple reference color histograms

The Mean Shift tracker is a widely used tool for robustly and quickly tracking the location of an object in an image sequence using the object’s color histogram. The reference histogram is typically set to that in the target region in the frame where the tracking is initiated. Often, however, no single view suffices to produce a reference histogram appropriate for tracking the target. In contexts where multiple views of the target are available prior to the tracking, this paper enhances the Mean Shift tracker to use multiple reference histograms obtained from these different target views. This is done while preserving both the convergence and the speed properties of the original tracker. We first suggest a simple method to use multiple reference histograms for producing a single histogram that is more appropriate for tracking the target. Then, to enhance the tracking further, we propose an extension to the Mean Shift tracker where the convex hull of these histograms is used as the target model. Many experimental results demonstrate the successful tracking of targets whose visible colors change drastically and rapidly during the sequence, where the basic Mean Shift tracker obviously fails.     

Object tracking by mean shift and radial basis function neural networks

In this paper, a tracker based on mean shift and radial basis function neural networks called MS-RBF is addressed. As its name implies, two independent trackers have been combined and linked together. The mean shift algorithm estimates the target’s location within only two iterations. The scale and orientation of target are computed by exploiting 2-D correlation coefficient between reference and target candidate histograms instead of using Bhattacharyya coefficient. A code optimization strategy, named multiply–add–accumulate (MAC), is proposed to remove useless memory occupation and programmatic operations. MAC implementation has reduced computational load and made overall tracking process faster. The second tracker “RBFNN” has an input feature vector that contains variables such as local contrast, color histogram, gradient, intensity, and spatial frequency. The neural network learns the color and texture features from the target and background. Then, this information is used to detect and track the object in other frames. The neural network employs Epanechnikov activation functions. The features extracted in any frame are clustered by Fuzzy C-Means clustering which produces the means and variances of the clusters. The experimental results show that the proposed tracker can resist to different types of occlusions, sudden movement, and shape deformations.     

多颜色直方图自适应组合Mean Shift跟踪

经典Mean Shift跟踪算法使用单一颜色直方图跟踪目标,导致其对目标外观的变化鲁棒性较差。为了解决该问题,提出一种多颜色直方图自适应组合Mean Shift跟踪算法。该算法利用多个视图的颜色核函数直方图的加权组合作为目标模型进行Mean Shift跟踪;为了适应目标外观的变化,利用目标区域对每一颜色直方图的概率图均值和方差的比值评价每一颜色直方图的可靠性,并自适应地计算其组合权值。实验结果表明,与现有Mean Shift跟踪算法相比,提出的跟踪算法对目标的外观变化具有更强的鲁棒性。     

Accurate appearance-based Bayesian tracking for maneuvering targets

We propose a tracking algorithm that combines the Mean Shift search in a Particle Filtering framework and a target representation that uses multiple semi-overlapping color histograms. The target representation introduces spatial information that accounts for rotation and anisotropic scaling without compromising the flexibility typical of color histograms. Moreover, the proposed tracker can generate a smaller number of samples than Particle Filter as it increases the particle efficiency by moving the samples toward close local maxima of the likelihood using Mean Shift. Experimental results show that the proposed representation improves the robustness to clutter and that, especially on highly maneuvering targets, the combined tracker outperforms Particle Filter and Mean Shift in terms of accuracy in estimating the target size and position while generating only 25% of the samples used by Particle Filter.     

A parallel and robust object tracking approach synthesizing adaptive Bayesian learning and improved incremental subspace learning

This paper presents a novel tracking algorithm which integrates two complementary trackers. Firstly, an improved Bayesian tracker(B-tracker) with adaptive learning rate is presented. The classification score of B-tracker reflects tracking reliability, and a low score usually results from large appearance change. Therefore, if the score is low, we decrease the learning rate to update the classifier fast so that B-tracker can adapt to the variation and vice versa. In this way, B-tracker is more suitable than its traditional version to solve appearance change problem. Secondly, we present an improved incremental subspace learning method tracker(Stracker). We propose to calculate projected coordinates using maximum posterior probability, which results in a more accurate reconstruction error than traditional subspace learning tracker. Instead of updating at every time, we present a stopstrategy to deal with occlusion problem. Finally, we present an integrated framework(BAST), in which the pair of trackers run in parallel and return two candidate target states separately. For each candidate state, we define a tracking reliability metrics to measure whether the candidate state is reliable or not, and the reliable candidate state will be chosen as the target state at the end of each frame. Experimental results on challenging sequences show that the proposed approach is very robust and effective in comparison to the state-of-the-art trackers.     

带宽自适应MeanShift图像分割算法

MeanShift是目前为止特征空间分析的最好方法之一,但其分割结果受带宽参数的影响。图像粗糙度是与视觉感受相关的图像纹理特征,对图像纹理的描述能力很强。图像像素的平均偏移量也体现了图像像素的总体离散情况。通过对高斯核函数的创建以及图像粗糙度的描述,创新性地给出了MeanShift的窗口尺寸选择方法以及图像像素平均偏移的计算,仿真结果表明,该算法对不同类型的图像,均能得到令人满意的效果。     

Robust visual tracking using information theoretical learning

This paper presents a novel online object tracking algorithm with sparse representation for learning effective appearance models under a particle filtering framework. Compared with the state-of-the-art ? ₁ sparse tracker, which simply assumes that the image pixels are corrupted by independent Gaussian noise, our proposed method is based on information theoretical Learning and is much less sensitive to corruptions; it achieves this by assigning small weights to occluded pixels and outliers. The most appealing aspect of this approach is that it can yield robust estimations without using the trivial templates adopted by the previous sparse tracker. By using a weighted linear least squares with non-negativity constraints at each iteration, a sparse representation of the target candidate is learned; to further improve the tracking performance, target templates are dynamically updated to capture appearance changes. In our template update mechanism, the similarity between the templates and the target candidates is measured by the earth movers’ distance(EMD). Using the largest open benchmark for visual tracking, we empirically compare two ensemble methods constructed from six state-of-the-art trackers, against the individual trackers. The proposed tracking algorithm runs in real-time, and using challenging sequences performs favorably in terms of efficiency, accuracy and robustness against state-of-the-art algorithms.     

基于多目标检测与跟踪的密集客流检测

针对密集交通场景中的客流检测问题,提出了基于支持向量机(SVM)多目标检测与Mean Shift跟踪相结合的方法.首先采用自适应检测窗口提取梯度方向直方图,经过SVM分类和聚类算法,得到头部图像初始假设.然后采用Mean Shift算法,对头部假设进行跟踪,得到连续的头部图像序列.通过SVM分类器对序列图像进行整体判断,得到客流信息.实验结果表明,自适应滑动窗口的方法减少了特征提取阶段的处理时间,提高了检测速度;同时,通过对得到的跟踪序列进行整体判别,客流量的检测精度得到了提高.     

Histogram similarity measure using variable bin size distance

In order to improve the performance of bin-by-bin distances, this paper proposes variable bin size distance (VBSD) as the histogram similarity measure. It calculates the histogram distance in a fine-to-coarse way, and can be considered as a cross-bin extension for bin-by-bin distances. The VBSD can be used to measure the similarity of multi-dimensional histograms, and is insensitive to both the histogram translation and the variation of histogram bin size. Experimental results show that the variable bin size distance performs better than bin-by-bin distances in the image retrieval applications.     

足球视频球员感知跟踪算法

目的 足球比赛视频中的球员跟踪算法为足球赛事分析提供基础的数据支持。但足球比赛中球员跟踪存在极大的挑战：球员进攻、防守和争夺球权时,目标球员可能产生快速移动、严重遮挡和周围出现若干名干扰球员的情况,目前仍没有一种能够完美解决足球比赛中球员跟踪问题的算法。因此如何解决足球场景中的困难,提升球员跟踪的准确度,成为当前研究的热点问题。方法 本文在分析足球比赛视频中球员目标特点的基础上,通过融合干扰项感知的颜色模型和目标感知的深度模型,提出并设计了一种球员感知的跟踪算法。干扰项感知的颜色模型分别提取目标、背景和干扰项的颜色直方图,利用贝叶斯公式得到搜索区域中每个像素点属于目标的似然概率。目标感知的深度模型利用孪生网络计算搜索区域与目标的相似度。针对跟踪漂移问题,使用全局跟踪器和局部跟踪器分别跟踪目标整体和目标上半身,并且在两个跟踪器的跟踪结果出现较大差异的时候分析跟踪器有效性并进行定位修正。结果 在公共的足球数据集上将本文算法与10个其他跟踪算法进行对比实验,同时对于文本算法进行了局部跟踪器的消融实验。实验结果表明,球员感知跟踪算法的平均有效重叠率达到了0.560 3,在存在同队球员和异队球员干扰的情况下,本文算法比排名第2的算法的有效重叠率分别高出3.7%和6.6%,明显优于其他算法,但是由于引入了干扰项感知的颜色模型、目标感知的深度模型以及局部跟踪器等模块增加了算法的时间复杂度,导致本文算法跟踪速度较慢。结论 本文总结了跟踪算法的整体流程并分析了实验结果,认为干扰项感知、目标感知和局部跟踪这3个策略在足球场景中的球员跟踪问题中起到了重要的作用,为未来在足球球员跟踪领域研究的继续深入提供了参考依据。     

Robust tracking with interest points: A sparse representation approach

Visual tracking is an important task in various computer vision applications including visual surveillance, human computer interaction, event detection, video indexing and retrieval. Recent state of the art sparse representation (SR) based trackers show better robustness than many of the other existing trackers. One of the issues with these SR trackers is low execution speed. The particle filter framework is one of the major aspects responsible for slow execution, and is common to most of the existing SR trackers. In this paper,¹ we propose a robust interest point based tracker in l₁ minimization framework that runs at real-time with performance comparable to the state of the art trackers. In the proposed tracker, the target dictionary is obtained from the patches around target interest points. Next, the interest points from the candidate window of the current frame are obtained. The correspondence between target and candidate points is obtained via solving the proposed l₁ minimization problem.In order to prune the noisy matches, a robust matching criterion is proposed, where only the reliable candidate points that mutually match with target and candidate dictionary elements are considered for tracking. The object is localized by measuring the displacement of these interest points. The reliable candidate patches are used for updating the target dictionary. The performance and accuracy of the proposed tracker is benchmarked with several complex video sequences. The tracker is found to be considerably fast as compared to the reported state of the art trackers. The proposed tracker is further evaluated for various local patch sizes, number of interest points and regularization parameters. The performance of the tracker for various challenges including illumination change, occlusion, and background clutter has been quantified with a benchmark dataset containing 50 videos.     

Online adaptive multiple pedestrian tracking in monocular surveillance video

Automatic online multiple pedestrian tracking is a rather important and challenging task in the field of machine vision. A new multiple pedestrian tracking system is proposed in this paper, which combines pedestrian detection, motion prediction, target matching and adaptive location adjustment methods. The clip-split strategy was adopted for optimization of the detected pedestrian candidates, which resulted in great improvement of the tracking accuracies, especially when the marginal areas of the detected target candidates contained background scenes. For each frame, the proposed adaptive location adjustment method was used to adjust the location and scale of the targets to deal with drifting problems where necessary, especially after severe occlusions. Experimental results on three challenging real-world datasets demonstrated that the proposed tracker has excellent performance over other state-of-the-art trackers based on MOT metrics.

     

Robust object tracking via multi-scale patch based sparse coding histogram

There are many visual tracking algorithms that are based on sparse representation appearance model. Most of them are modeled by local patches with fixed patch scale, which make trackers less effective when objects undergone appearance changes such as illumination variation, pose change or partial occlusion. To solve the problem, a novel appearance representation model is proposed via multi-scale patch based sparse coding histogram for robust visual tracking. In this paper, the appearance of an object is modeled by different scale patches, which are represented by sparse coding histogram with different scale dictionaries. Then a similarity measure is applied to the calculation of the distance between the sparse coding histograms of target candidate and target template. Finally, the similarity score of the target candidate is passed to a particle filter to estimate the target state sequentially in the tracking process. Additionally, in order to decrease the visual drift caused by partial occlusion, an occlusion handling strategy is adopted, which takes the spatial information of multi-scale patches and occlusion into account. Based on the experimental results on some benchmarks of video sequences, our tracker outperforms state-of-the-art tracking methods.     

The analysis and applications of adaptive-binning color histograms

Histograms are commonly used in content-based image retrieval systems to represent the distributions of colors in images. It is a common understanding that histograms that adapt to images can represent their color distributions more efficiently than do histograms with fixed binnings. However, existing systems almost exclusively adopt fixed-binning histograms because, among existing well-known dissimilarity measures, only the computationally expensive Earth Mover’s Distance (EMD) can compare histograms with different binnings. This paper addresses the issue by defining a new dissimilarity measure that is more reliable than the Euclidean distance and yet computationally less expensive than EMD. Moreover, a mathematically sound definition of mean histogram can be defined for histogram clustering applications. Extensive test results show that adaptive histograms produce the best overall performance, in terms of good accuracy, small number of bins, no empty bin, and efficient computation, compared to existing methods for histogram retrieval, classification, and clustering tasks.     

基于四元数描述和EMD的人体运动捕获数据检索

针对运动捕获数据的高效匹配问题,提出了一种新的基于四元数描述和EMD（ Earth Mover＆#39;s Distance）的人体运动检索算法。该算法主要包括特征提取和运动匹配两部分。在特征提取部分,为了解决高维数据检索效率低的问题,引入了四元数描述符对关节点的数据信息特征进行描述,通过映射姿态分布的原始数据,并采取K-means聚类方法对待查询动作和运动数据库的特征数据进行降维并归类。在运动匹配部分,根据聚类结果,建立每个特征数据集的距离矩阵,将匹配问题转换为运输优化问题。然后,用EMD算法度量待查询动作和数据库动作之间的相似值。仿真实验结果证明了提出的算法是有效的。     

变分调整约束下的反向低秩稀疏学习目标跟踪

目的 低秩稀疏学习目标跟踪算法在目标快速运动和严重遮挡等情况下容易出现跟踪漂移现象,为此提出一种变分调整约束下的反向低秩稀疏学习目标跟踪算法。方法 采用核范数凸近似低秩约束描述候选粒子间的时域相关性,去除不相关粒子,适应目标外观变化。通过反向稀疏表示描述目标表观,用候选粒子稀疏表示目标模板,减少在线跟踪中L₁优化问题的数目,提高跟踪效率。在有界变差空间利用变分调整对稀疏系数差分建模,约束目标表观在相邻帧间具有较小变化,但允许连续帧间差异存在跳跃不连续性,以适应目标快速运动。结果 实验利用OTB（object tracking benchmark）数据集中的4组涵盖了严重遮挡、快速运动、光照和尺度变化等挑战因素的标准视频序列进行测试,定性和定量对比了本文算法与5种热点算法的跟踪效果。定性分析基于视频序列的主要挑战因素进行比较,定量分析通过中心点位置误差（central pixel error,CPE）比较跟踪算法的精度。与CNT（convolutional networks training）、SCM（sparse collaborative model）、IST（inverse sparse tracker）、DDL（discriminative dictionary learning）和LLR（locally low-rank representation）算法相比,平均CPE值分别提高了2.80、4.16、13.37、35.94和41.59。实验结果表明,本文算法达到了较高的跟踪精度,对上述挑战因素更具鲁棒性。结论 本文提出的跟踪算法,综合了低秩稀疏学习和变分优化调整的优势,在复杂场景下具有较高的跟踪精度,特别是对严重遮挡和快速运动情况的有效跟踪更具鲁棒性。     

Tracking by Affine Kernel Transformations Using Color and Boundary Cues

Kernel-based trackers aggregate image features within the support of a kernel (a mask) regardless of their spatial structure. These trackers spatially fit the kernel (usually in location and in scale) such that a function of the aggregate is optimized. We propose a kernel-based visual tracker that exploits the constancy of color and the presence of color edges along the target boundary. The tracker estimates the best affinity of a spatially aligned pair of kernels, one of which is color-related and the other of which is object boundary-related. In a sense, this work extends previous kernel-based trackers by incorporating the object boundary cue into the tracking process and by allowing the kernels to be affinely transformed instead of only translated and isotropically scaled. These two extensions make for more precise target localization. A more accurately localized target also facilitates safer updating of its reference color model, further enhancing the tracker's robustness. The improved tracking is demonstrated for several challenging image sequences.     

结合双模板融合与孪生网络的鲁棒视觉目标跟踪

目的 视觉目标跟踪算法主要包括基于相关滤波和基于孪生网络两大类。前者虽然精度较高但运行速度较慢,无法满足实时要求。后者在速度和精度方面取得了出色的跟踪性能,然而,绝大多数基于孪生网络的目标跟踪算法仍然使用单一固定的模板,导致算法难以有效处理目标遮挡、外观变化和相似干扰物等情形。针对当前孪生网络跟踪算法的不足,提出了一种高效、鲁棒的双模板融合目标跟踪方法(siamese tracker with double template fusion,Siam-DTF)。方法 使用第1帧的标注框作为初始模板,然后通过外观模板分支借助外观模板搜索模块在跟踪过程中为目标获取合适、高质量的外观模板,最后通过双模板融合模块,进行响应图融合和特征融合。融合模块结合了初始模板和外观模板各自的优点,提升了算法的鲁棒性。结果 实验在3个主流的目标跟踪公开数据集上与最新的9种方法进行比较,在OTB2015(object tracking benchmark 2015)数据集中,本文方法的AUC(area under curve)得分和精准度分别为0.701和0.918,相比于性能第2的SiamRPN++(siamese region proposal network++)算法分别提高了0.6%和1.3%;在VOT2016(visual object tracking 2016)数据集中,本文方法取得了最高的期望平均重叠(expected average overlap,EAO)和最少的失败次数,分别为0.477和0.172,而且EAO得分比基准算法SiamRPN++提高了1.6%,比性能第2的SiamMask_E算法提高了1.1%;在VOT2018数据集中,本文方法的期望平均重叠和精确度分别为0.403和0.608,在所有算法中分别排在第2位和第1位。本文方法的平均运行速度达到47帧/s,显著超出跟踪问题实时性标准要求。结论 本文提出的双模板融合目标跟踪方法有效克服了当前基于孪生网络的目标跟踪算法的不足,在保证算法速度的同时有效提高了跟踪的精确度和鲁棒性,适用于工程部署与应用。     

类孪生网络目标跟踪算法综述

目前,在视觉目标跟踪任务中的主流方法是基于模版匹配的跟踪器,这些方法在目标的分类和边界框的回归上具有很强的鲁棒性,主要可以分为判别相关滤波跟踪器和孪生网络跟踪器,这两种方法都有一个类孪生网络的框架。以孪生网络跟踪器为例,该方法通过模版和搜索区域之间的相关操作确定目标的位置,取得了顶尖的性能表现。近年来,Transformer在计算机视觉领域的发展十分迅速,结合了Transformer的类孪生网络跟踪器在速度和精度方面都远超传统的跟踪方法。文章简要概括了判别相关滤波跟踪器、孪生网络跟踪器的发展,以及Transformer在目标跟踪任务中的应用。