Robust particle tracker via Markov Chain Monte Carlo posterior sampling

Particle Filter has grown to be a standard framework for visual tracking. This paper proposes a robust particle tracker based on Markov Chain Monte Carlo method, aiming at solving the thorny problems in visual tracking induced by object appearance changes, occlusions, background clutter, and abrupt motions. In this algorithm, we derive the posterior probability density function based on second order Markov assumption. The posterior probability density is the joint density of the previous two states. Additionally, a Markov Chain with certain length is used to approximate the posterior density to avoid the drawbacks of traditional importance sampling based algorithm, which consequently improves the searching ability of the proposed tracker. We compare our approach with several alternative tracking algorithms, and the experimental results demonstrate that our tracker is superior to others in dealing with various types of challenging scenarios.     

改进后的TLD视频目标跟踪方法

TLD(tracking-learning-detection)是近期受到广泛关注的一种有效的视频目标跟踪算法.在原始TLD的基础上,对其进行改进,改进包括:在TLD的跟踪器中对其局部跟踪器的布置和局部跟踪器的跟踪成败预测方法进行改进,提高跟踪器的跟踪精度和鲁棒性;在TLD的检测器中引入基于Kalman滤波器的当前帧目标所在区域预估,缩小了检测器的检测范围,提高了检测器处理速度;在TLD的检测器中加入基于马尔可夫模型的方向预测器,增强了检测器对相似目标的辨识能力.通过实验对原始TLD和改进后的TLD进行了比较,实验结果显示改进后的TLD算法较原始TLD算法具备更高的跟踪精度和更快的处理速度,而且增强了对场景中相似目标的辨识能力.     

基于多任务最小软阈值回归方法的目标跟踪*

在视频跟踪中,模型表示是直接影响跟踪效率的核心问题之一.在随时间和空间变化的复杂数据中学习目标外观模型表示所需的有效模板,从而适应内在或外在因素所引起的目标状态变化是非常重要的.文中详细描述较为鲁棒的目标外观模型表示策略,并提出一种新的多任务最小软阈值回归跟踪算法(MLST).该算法框架将候选目标的观测模型假设为多任务线性回归问题,利用目标模板和独立同分布的高斯-拉普拉斯重构误差线性表示候选目标不同状态下的外观模型,从而跟踪器能够很好地适应各种复杂场景并准确预测每一时刻的真实目标状态.大量实验证明,文中在线学习策略能够充分挖掘目标在不同时刻的特殊状态信息以提高模型表示精度,使得跟踪器保持最佳的状态,从而在一定程度上提高跟踪性能.实验结果显示,本文算法体现较好的鲁棒性并优于一些目前较先进的跟踪算法.     

Online adaptive radial basis function networks for robust object tracking

Visual tracking has been a challenging problem in computer vision over the decades. The applications of visual tracking are far-reaching, ranging from surveillance and monitoring to smart rooms. In this paper, we present a novel online adaptive object tracker based on fast learning radial basis function (RBF) networks. Pixel based color features are used for developing the target/object model. Here, two separate RBF networks are used, one of which is trained to maximize the classification accuracy of object pixels, while the other is trained for non-object pixels. The target is modeled using the posterior probability of object and non-object classes. Object localization is achieved by iteratively seeking the mode of the posterior probability of the pixels in each of the subsequent frames. An adaptive learning procedure is presented to update the object model in order to tackle object appearance and illumination changes. The superior performance of the proposed tracker is illustrated with many complex video sequences, as compared against the popular color-based mean-shift tracker. The proposed tracker is suitable for real-time object tracking due to its low computational complexity.     

基于贝叶斯模型与最佳伙伴相似度量的目标跟踪

提出了一种基于产生式与判别式联合模型的视觉目标跟踪算法。首先介绍了一种基于全局颜色特征直方图特征的贝叶斯分类器,检测出若干最有可能属于目标的候选区域,然后利用最佳伙伴相似性度量（Best-Buddies Similarity）得到候选区域与目标模板的相似度,结合概率值与相似度值估计出最优的目标状态。通过划分目标-背景区域模型、目标-干扰区域模型,对可能产生干扰的区域提前进行抑制,降低了长期跟踪可能产生的漂移问题的风险,同时引入了自适应尺度估计机制和在线模型更新策略,以获得更为精准的跟踪结果。在37组具有挑战性的图像序列上与7种优秀的算法对比实验表明,所提出的算法能够有效应对光照变化、遮挡、旋转与尺度变化等多种问题。     

Efficient multi-feature PSO for fast gray level object-tracking

Robust and real-time moving object tracking is a tricky job in computer vision systems. The development of an efficient yet robust object tracker faces several obstacles, namely: dynamic appearance of deformable or articulated targets, dynamic backgrounds, variation in image intensity, and camera (ego) motion. In this paper, a novel tracking algorithm based on particle swarm optimization (PSO) method is proposed. PSO is a population-based stochastic optimization algorithm modeled after the simulation of the social behavior of bird flocks and animal hordes. In this algorithm, a multi-feature model is proposed for object detection to enhance the tracking accuracy and efficiency. The object's model is based on the gray level intensity. This model combines the effects of different object cases including zooming, scaling, rotating, etc. into a single cost function. The proposed algorithm is independent of object type and shape and can be used for many object tracking applications. Over 30 video sequences and having over 20,000 frames are used to test the developed PSO-based object tracking algorithm and compare it to classical object tracking algorithms as well as previously published PSO-based tracking algorithms. Our results demonstrate the efficiency and robustness of our developed algorithm relative to all other tested algorithms.     

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.

     

在线复合模板模型表示的视觉目标跟踪

目的 视觉目标跟踪中,目标往往受到自身或场景中各种复杂干扰因素的影响,这对正确捕捉所感兴趣的目标信息带来极大的挑战。特别是,跟踪器所用的模板数据主要是在线学习获得,数据的可靠性直接影响到候选样本外观模型表示的精度。针对视觉目标跟踪中目标模板学习和候选样本外观模型表示等问题,采用一种较为有效的模板组织策略以及更为精确的模型表示技术,提出一种新颖的视觉目标跟踪算法。方法 跟踪框架中,将候选样本外观模型表示假设为由一组复合模板和最小重构误差组成的线性回归问题,首先利用经典的增量主成分分析法从在线高维数据中学习出一组低维子空间基向量(模板正样本),并根据前一时刻跟踪结果在线实时采样一些特殊的负样本加以扩充目标模板数据,再利用新组织的模板基向量和独立同分布的高斯—拉普拉斯混合噪声来线性拟合候选目标外观模型,最后估计出候选样本和真实目标之间的最大似然度,从而使跟踪器能够准确捕捉每一时刻的真实目标状态信息。结果 在一些公认测试视频序列上的实验结果表明,本文算法在目标模板学习和候选样本外观模型表示等方面比同类方法更能准确有效地反映出视频场景中目标状态的各种复杂变化,能够较好地解决各种不确定干扰因素下的模型退化和跟踪漂移问题,和一些优秀的同类算法相比,可以达到相同甚至更高的跟踪精度。结论 本文算法能够在线学习较为精准的目标模板并定期更新,使得跟踪器良好地适应内在或外在因素(姿态、光照、遮挡、尺度、背景扰乱及运动模糊等)所引起的视觉信息变化,始终保持其最佳的状态,使得候选样本外观模型的表示更加可靠准确,从而展现出更为鲁棒的性能。     

一种自适应模板更新的判别式KCF跟踪方法

为了解决单目标跟踪算法中存在的目标旋转、遮挡和快速运动等挑战,提出了一种基于自适应更新策略的判别式核相关滤波器（kernelized correlation filter,KCF）目标跟踪新框架。构建了外观判别式模型,实现跟踪质量有效性的评估。构造了新的自适应模板更新策略,能够有效区分目标跟踪异常时当前目标是否发生了旋转。提出了一种结合目标检测的跟踪新构架,能够进一步有效判别快速运动和遮挡状态。同时,针对上述3种挑战,分别采用模板更新、目标运动位移最小化以及目标检测算法实现目标跟踪框的恢复,保证了跟踪的有效性和长期性。实验分别采用2种传统手动特征HOG和CN（color names）验证提出的框架鲁棒性,结果证明了提出的目标跟踪新方法在速度和精度方面的优越性能。     

Fragments based tracking with adaptive cue integration

In this paper, we address the issue of part-based tracking by proposing a new fragments-based tracker. The proposed tracker enhances the recently suggested FragTrack algorithm to employ an adaptive cue integration scheme. This is done by embedding the original tracker into a particle filter framework, associating a reliability value to each fragment that describes a different part of the target object and dynamically adjusting these reliabilities at each frame with respect to the current context. Particularly, the vote of each fragment contributes to the joint tracking result according to its reliability, and this allows us to achieve a better accuracy in handling partial occlusions and pose changes while preserving and even improving the efficiency of the original tracker. In order to demonstrate the performance and the effectiveness of the proposed algorithm we present qualitative and quantitative results on a number of challenging video sequences.     

Tracking using Numerous Anchor Points

In this paper, an online adaptive model-free tracker is proposed to track single objects in video sequences to deal with real-world tracking challenges like low-resolution, object deformation, occlusion and motion blur. The novelty lies in the construction of a strong appearance model that captures features from the initialized bounding box and then are assembled into anchor point features. These features memorize the global pattern of the object and have an internal star graph-like structure. These features are unique and flexible and help tracking generic and deformable objects with no limitation on specific objects. In addition, the relevance of each feature is evaluated online using short-term consistency and long-term consistency. These parameters are adapted to retain consistent features that vote for the object location and that deal with outliers for long-term tracking scenarios. Additionally, voting in a Gaussian manner helps in tackling inherent noise of the tracking system and in accurate object localization. Furthermore, the proposed tracker uses pairwise distance measure to cope with scale variations and combines pixel-level binary features and global weighted color features for model update. Finally, experimental results on a visual tracking benchmark dataset are presented to demonstrate the effectiveness and competitiveness of the proposed tracker.     

基于自适应状态转移的混合跟踪算法

为提高粒子滤波视觉目标跟踪算法的准确性和实时性,提出一种基于自适应状态转移的混合跟踪算法。首先采用零阶自适应变化模型来获取目标的可能状态,然后利用均值漂移算法的局部优化特性找到后验概率的最大值。在多峰值情况下由粒子滤波随机产生粒子,用新的粒子集来确定目标的最终位置。实验结果表明,这种改进的算法在保证准确性的同时,降低了系统的计算时间。     

Learning spatially regularized similarity for robust visual tracking

Matching visual appearances of the target object over consecutive frames is a critical step in visual tracking. The accuracy performance of a practical tracking system highly depends on the similarity metric used for visual matching. Recent attempts to integrate discriminative metric learned by sequential visual data (instead of a predefined metric) in visual tracking have demonstrated more robust and accurate results. However, a global similarity metric is often suboptimal for visual matching when the target object experiences large appearance variation or occlusion. To address this issue, we propose in this paper a spatially weighted similarity fusion (SWSF) method for robust visual tracking. In our SWSF, a part-based model is employed as the object representation, and the local similarity metric and spatially regularized weights are jointly learned in a coherent process, such that the total matching accuracy between visual target and candidates can be effectively enhanced. Empirically, we evaluate our proposed tracker on various challenging sequences against several state-of-the-art methods, and the results demonstrate that our method can achieve competitive or better tracking performance in various challenging tracking scenarios.     

增强二阶网络调制的目标跟踪

目的 表观模型对视觉目标跟踪的性能起着决定性的作用。基于网络调制的跟踪算法通过构建高效的子网络学习参考帧目标的表观信息,以用于测试帧目标的鲁棒匹配,在多个目标跟踪数据集上表现优异。但是,这类跟踪算法忽视了高阶信息对鲁棒建模物体表观的重要作用,致使在物体表观发生大尺度变化时易产生跟踪漂移。为此本文提出全局上下文信息增强的二阶池化调制子网络,以学习高阶特征提升跟踪器的性能。方法 首先,利用卷积神经网络（convolutional neural networks,CNN）提取参考帧和测试帧的特征;然后,对提取的特征采用不同方向的长短时记忆网络（long shot-term memory networks,LSTM）捕获每个像素的全局上下文信息,再经过二阶池化网络提取高阶信息;最后,通过调制机制引导测试帧学习最优交并比预测。同时,为提升跟踪器的稳定性,在线跟踪通过指数加权平均自适应更新物体表观特征。结果 实验结果表明,在OTB100（object tracking benchmark）数据集上,本文方法的成功率为67.9%,超越跟踪器ATOM （accurate tracking by overlap maximization）1.5%;在VOT （visual object tracking）2018数据集上平均期望重叠率（expected average overlap,EAO）为0.44,超越ATOM 4%。结论 本文通过构建全局上下文信息增强的二阶池化调制子网络来学习高效的表观模型,使跟踪器达到目前领先的性能。     

基于动态函数连接神经网络的自适应逆控制系统辨识研究

自适应逆控制将系统扰动消除和动态响应性能独立分开控制,其性能的优劣取决于系统对象、逆对象及逆控制器模型辨识精度的高低。文中提出用动态函数连接神经网络来实现自适应逆控制系统对象、逆对象的同时在线建模和逆控制器的离线建模,并将模型参数的辨识转化为空间参数寻优。针对混沌初始化对已收敛种群结构的破坏性,提出用变参数混沌粒子群优化算法对神经网络权值进行全局寻优,通过仿真实验可以看出基于动态函数连接神经网络的建模误差小,辨识精度高;与当前的参考模型自适应控制方法进行对比分析,所提方法能取得较好的扰动消除效果,并能使系统的跟踪响应性能得到提高,从而验证了方法的有效性、可行性。     

Robust decentralized multi-model adaptive template tracking

In this paper, a robust and efficient visual tracking method through the fusion of several distributed adaptive templates is proposed. It is assumed that the target object is initially localized either manually or by an object detector at the first frame. The object region is then partitioned into several non-overlapping subregions. The new location of each subregion is found by an EM¹-like gradient-based optimization algorithm. The proposed localization algorithm is capable of simultaneously optimizing several possible solutions in a probabilistic framework. Each possible solution is an initializing point for the optimization algorithm which improves the accuracy and reliability of the proposed gradient-based localization method to the local extrema. Moreover, each subregion is defined by two adaptive templates named immediate and delayed templates to solve the “drift” problem.² The immediate template is updated by short-term appearance changes whereas the delayed template models the long-term appearance variations. Therefore, the combination of short-term and long-term appearance modeling can solve the template tracking drift problem. At each tracking step, the new location of an object is estimated by fusing the tracking result of each subregion. This fusion method is based on the local and global properties of the object motion to increase the robustness of the proposed tracking method against outliers, shape variations, and scale changes. The accuracy and robustness of the proposed tracking method is verified by several experimental results. The results also show the superior efficiency of the proposed method by comparing it to several state-of-the-art trackers as well as the manually labeled “ground truth” data.     

Mean shift tracker combined with online learning-based detector and Kalman filtering for real-time tracking

Color-based visual object tracking is one of the most commonly used tracking methods. Among many tracking methods, the mean shift tracker is used most often because it is simple to implement and consumes less computational time. However, mean shift trackers exhibit several limitations when used for long-term tracking. In challenging conditions that include occlusions, pose variations, scale changes, and illumination changes, the mean shift tracker does not work well. In this paper, an improved tracking algorithm based on a mean shift tracker is proposed to overcome the weaknesses of existing methods based on mean shift tracker. The main contributions of this paper are to integrate mean shift tracker with an online learning-based detector and to newly define the Kalman filter-based validation region for reducing computational burden of the detector. We combine the mean shift tracker with the online learning-based detector, and integrate the Kalman filter to develop a novel tracking algorithm. The proposed algorithm can reinitialize the target when it converges to a local minima and it can cope with scale changes, occlusions and appearance changes by using the online learning-based detector. It updates the target model for the tracker in order to ensure long-term tracking. Moreover, the validation region obtained by using the Kalman filter and the Mahalanobis distance is used in order to operate detector in real-time. Through a comparison against various mean shift tracker-based methods and other state-of-the-art methods on eight challenging video sequences, we demonstrate that the proposed algorithm is efficient and superior in terms of accuracy and speed. Hence, it is expected that the proposed method can be applied to various applications which need to detect and track an object in real-time.     

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.     

Event-driven video adaptation: A powerful tool for industrial video supervision

Efficient video content adaptation requires techniques for content analysis and understanding as well as the development of appropriate mechanisms for content scaling in terms of the network properties, terminal devices characteristics and users’ preferences. This is particularly evident in industrial surveillance applications, due to the huge amount of data needed to be stored, delivered and handled. In this paper, we address both issues by incorporating (a) computer vision tools that allows efficient tracking of salient visual objects for long time regardless of the dynamics of the visual environment –via a self initialized tracking algorithm—and (b) an adaptive optimal rate distortion scheme able to allocate different priorities for each detected video object with respect to users’ needs, network platforms capabilities and terminal characteristics. The self initialized tracker firstly appropriately describes visual content, secondly incorporates adaptive mechanisms for automatically update the tracker to adjust to the current conditions and thirdly includes an efficient decision mechanism that estimates the time instances in which adaptation should be activated. For the rate distortion algorithm, an optimal adaptive framework is adopted which is capable of allocating the desired quality to objects of users’ interest without violating the target bit rate of the sequence. The Wavelet Packet Transform (WPT) is adopted towards this purpose. The advantage of the WPT is that it localizes the frequency components of each video object and therefore it offers additionally content adaptability according to video object texture coding. The WPT tree is transmitted only at the first frame of each shot and thus dew bits are required for its encoding. Experimental results and comparisons with other approaches are presented to illustrate the good performance of the proposed architecture. The results cover real-world and complex industrial environments.