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。     

Visual tracking via weakly supervised learning from multiple imperfect oracles

Notwithstanding many years of progress, visual tracking is still a difficult but important problem. Since most top-performing tracking methods have their strengths and weaknesses and are suited for handling only a certain type of variation, one of the next challenges is to integrate all these methods and address the problem of long-term persistent tracking in ever-changing environments. Towards this goal, we consider visual tracking in a novel weakly supervised learning scenario where (possibly noisy) labels but no ground truth are provided by multiple imperfect oracles (i.e., different trackers). These trackers naturally have intrinsic diversity due to their different design strategies, and we propose a probabilistic method to simultaneously infer the most likely object position by considering the outputs of all trackers, and estimate the accuracy of each tracker. An online evaluation strategy of trackers and a heuristic training data selection scheme are adopted to make the inference more effective and efficient. Consequently, the proposed method can avoid the pitfalls of purely single tracking methods and get reliably labeled samples to incrementally update each tracker (if it is an appearance-adaptive tracker) to capture the appearance changes. Extensive experiments on challenging video sequences demonstrate the robustness and effectiveness of the proposed method.     

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.     

Object tracking via collaborative multi-task learning and appearance model updating

In this paper, we propose a novel visual tracking algorithm using the collaboration of generative and discriminative trackers under the particle filter framework. Each particle denotes a single task, and we encode all the tasks simultaneously in a structured multi-task learning manner. Then, we implement generative and discriminative trackers, respectively. The discriminative tracker considers the overall information of object to represent the object appearance; while the generative tracker takes the local information of object into account for handling partial occlusions. Therefore, two models are complementary during the tracking. Furthermore, we design an effective dictionary updating mechanism. The dictionary is composed of fixed and variational parts. The variational parts are progressively updated using Metropolis–Hastings strategy. Experiments on different challenging video sequences demonstrate that the proposed tracker performs favorably against several state-of-the-art trackers.     

Online learning neural tracker

Object tracking is a fundamental computer vision problem and is required for many high-level tasks such as activity recognition, behavior analysis and surveillance. The main challenge in the object tracking problem is the dynamic change in object/background appearance, illumination, shape and occlusion. We present an online learning neural tracker (OLNT) to differentiate the object from the background and also adapt to changes in object/background dynamics. For target modeling and object tracking, a neural algorithm based on risk sensitive loss function is proposed to handle issues related to sample imbalance and dynamics of object. Region-based features like region-based color moments for larger mobile objects and color/texture features at pixel level for smaller mobile objects are used to discriminate the object from background. The proposed neural classifier automatically determines the number of neurons required to estimate the posterior probability map. In the online learning neural classifier, only one neuron parameter is updated per tracker to reduce the computational burden during online adaptation. The tracked object is represented using an estimated posterior probability map. The posterior probability map is used to adapt the bounding box to handle the scale change and improper initialization.For illustrating the advantage of the proposed OLNT under rapid illumination variation, change in appearance, scale/size change, and occlusion, we present results from benchmark video sequences. Finally, we also present the comparison with well-known trackers in the literature and highlight the advantage of the proposed tracker.     

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。     

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.     

快速深度学习的鲁棒视觉跟踪

目的 基于深度学习的视觉跟踪算法具有跟踪精度高、适应性强的特点,但是,由于其模型参数多、调参复杂,使得算法的时间复杂度过高。为了提升算法的效率,通过构建新的网络结构、降低模型冗余,提出一种快速深度学习的算法。方法 鲁棒特征的提取是视觉跟踪成功的关键。基于深度学习理论,利用海量数据离线训练深度神经网络,分层提取描述图像的特征;针对网络训练时间复杂度高的问题,通过缩小网络规模得以大幅缓解,实现了在GPU驱动下的快速深度学习;在粒子滤波框架下,结合基于支持向量机的打分器的设计,完成对目标的在线跟踪。结果 该方法精简了特征提取网络的结构,降低了模型复杂度,与其他基于深度学习的算法相比,具有较高的时效性。系统的跟踪帧率总体保持在22帧/s左右。结论 实验结果表明,在目标发生平移、旋转和尺度变化,或存在光照、遮挡和复杂背景干扰时,本文算法能够实现比较稳定和相对快速的目标跟踪。但是,对目标的快速移动和运动模糊的鲁棒性不够高,容易受到相似物体的干扰。     

基于子空间自适应学习的粒子滤波跟踪算法

为了提高目标外观迅速变化时视觉跟踪算法的鲁棒性,提出了一种基于自适应子空间学习的粒子滤波跟踪算法。在粒子滤波构架下,建立状态判决机制,根据判决结果并结合主成分分析(PCA)子空间与正交子空间的特点,选择合适的学习方法。这样既能准确、稳定地学习到目标的低维子空间,又能迅速地学习到目标外观变化的趋势。同时,加入鲁棒估计技术处理遮挡问题,避免了对目标状态估计的影响。实验结果表明,该算法在光照变化、姿态变化、遮挡的情况下,均具有较强的鲁棒性。     

Robust feature learning for online discriminative tracking without large-scale pre-training

Owing to the inherent lack of training data in visual tracking, recent work in deep learning-based trackers has focused on learning a generic representation offline from large-scale training data and transferring the pre-trained feature representation to a tracking task. Offline pre-training is time-consuming, and the learned generic representation may be either less discriminative for tracking specific objects or overfitted to typical tracking datasets. In this paper, we propose an online discriminative tracking method based on robust feature learning without large-scale pre-training. Specifically, we first design a PCA filter bank-based convolutional neural network (CNN) architecture to learn robust features online with a few positive and negative samples in the high-dimensional feature space. Then, we use a simple soft-thresholding method to produce sparse features that are more robust to target appearance variations. Moreover, we increase the reliability of our tracker using edge information generated from edge box proposals during the process of visual tracking. Finally, effective visual tracking results are achieved by systematically combining the tracking information and edge box-based scores in a particle filtering framework. Extensive results on the widely used online tracking benchmark (OTB-50) with 50 videos validate the robustness and effectiveness of the proposed tracker without large-scale pre-training.     

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.     

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。     

I-VITAL: Information aided visual tracking with adversarial learning

With the advent of convolutional neural networks (CNN), MDNet and the Siamese trackers posed tracking as supervised learning. They model an object’s presence using classification (foreground and background) and location using regression. For the first time, we have brought probability distribution into the CNN framework for tracking. We have selected “Information maximization Generative Adversarial Network (InfoGAN)” to couple the target and background classes with two unique Gaussian distributions. This paper highlights the use of InfoGAN in information extraction & feedback to improve the tracking framework. Specifically, the novel features proposed in this tracking framework are (i) Coupling of unique probability distributions to target and background classes and (ii) Unsupervised tracker status (success/ failure) identification and correction through information feedback. We demonstrated the efficacy of the proposed I-VITAL tracker in visual tracking with experimental comparisons on well-known data sets such as GOT10K, VOT2020, and OTB-2015. Compared with base works, the proposed tracker has improved performance in locating the object of interest.     

基于多任务混合噪声分布模型表示的视频跟踪

视觉跟踪中,目标信息是不确定的非线性变化过程。随时间和空间而变化的复杂动态数据中学习出较为精确的目标模板并用它来线性表示候选样本外观模型,从而使跟踪器较好地适应跟踪作业中内在或外在因素所引起的目标外观变化是视觉目标跟踪研究的重点。提出一种新颖的多任务混合噪声分布模型表示的视频跟踪算法,将候选样本外观模型假设为由一组目标模板和最小重构误差组成的多任务线性回归问题。利用经典的增量主成分分析法从高维数据中学习出一组低维子空间基向量（模板正样本）,并在线实时采样一些特殊的负样本加以扩充目标模板,再利用扩充后的新模板和独立同分布的高斯-拉普拉斯混合噪声来线性拟合当前时刻的候选目标外观模型,最后计算候选样本和真实目标之间的最大似然度,从而准确捕捉当前时刻的真实目标。在一些公认测试视频上的实验结果表明,该算法将能够在线学习较为精准的目标模板并定期更新目标在不同状态时的特殊信息,使得跟踪器始终保持最佳的状态,从而良好地适应不断发生变化的视觉信息（姿态、光照、遮挡、尺度、背景扰乱及运动模糊等）,表现出更好的鲁棒性能。     

Visual Tracking via Subspace Learning: A Discriminative Approach

Good tracking performance is in general attributed to accurate representation over previously obtained targets and/or reliable discrimination between the target and the surrounding background. In this work, a robust tracker is proposed by integrating the advantages of both approaches. A subspace is constructed to represent the target and the neighboring background, and their class labels are propagated simultaneously via the learned subspace. In addition, a novel criterion is proposed, by taking account of both the reliability of discrimination and the accuracy of representation, to identify the target from numerous target candidates in each frame. Thus, the ambiguity in the class labels of neighboring background samples, which influences the reliability of the discriminative tracking model, is effectively alleviated, while the training set still remains small. Extensive experiments demonstrate that the proposed approach outperforms most state-of-the-art trackers.     

Robust Visual Tracking Based on Convolutional Features with Illumination and Occlusion Handing

视觉追踪是在计算机视觉的一个重要区域。怎么处理照明和吸藏问题是一个挑战性的问题。这份报纸论述一篇小说和有效追踪算法处理如此的问题。一方面,一起始的外观总是有的目标清除轮廓,它对照明变化光不变、柔韧。在另一方面,特征在追踪起一个重要作用,在哪个之中 convolutional 特征显示出有利性能。因此,我们采用卷的轮廓特征代表目标外观。一般来说,一阶的衍生物边坡度操作员在由卷检测轮廓是有效的他们与图象。特别, Prewitt 操作员对水平、垂直的边更敏感,当 Sobel 操作员对斜边更敏感时。内在地, Prewitt 和 Sobel 与对方一起是补足的。技术上说,这份报纸设计二组 Prewitt 和 Sobel 边察觉者提取一套完全的 convolutional 特征,它包括水平、垂直、斜的边特征。在第一个框架,轮廓特征从目标被提取构造起始的外观模型。在有这些轮廓特征的试验性的图象的分析以后,明亮的部分经常提供更有用的信息描述目标特征,这能被发现。因此,我们建议一个方法比较候选人样品和我们仅仅使用明亮的象素的训练模型的类似,它使我们的追踪者有能力处理部分吸藏问题。在得到新目标以后,变化以便改编外观,我们建议相应联机策略逐渐地更新我们的模型。convolutional 特征由井综合的 Prewitt 和 Sobel 边察觉者提取了的实验表演能是足够有效的学习柔韧的外观模型。九个挑战性的序列上的众多的试验性的结果证明我们的建议途径与最先进的追踪者比较很有效、柔韧。     

Real-time object tracking via compressive feature selection

Recently, compressive tracking (CT) has been widely proposed for its efficiency, accuracy and robustness on many challenging sequences. Its appearance model employs non-adaptive random projections that preserve the structure of the image feature space. A very sparse measurement matrix is used to extract features by multiplying it with the feature vector of the image patch. An adaptive Bayes classifier is trained using both positive samples and negative samples to separate the target from background. On the CT framework, however, some features used for classification have weak discriminative abilities, which reduces the accuracy of the strong classifier. In this paper, we present an online compressive feature selection algorithm(CFS) based on the CT framework. It selects the features which have the largest margin when using them to classify positive samples and negative samples. For features that are not selected, we define a random learning rate to update them slowly. It makes those weak classifiers preserve more target information, which relieves the drift when the appearance of the target changes heavily. Therefore, the classifier trained with those discriminative features couples its score in many challenging sequences, which leads to a more robust tracker. Numerous experiments show that our tracker could achieve superior result beyond many state-of-the-art trackers.     

协同结构稀疏重构的判别性视觉跟踪

基于稀疏表示的表观似然模型在目标跟踪领域具有广泛的应用,但是这种单一产生式目标表观模型并未考虑完整的判别性结构信息,容易受复杂背景的干扰。为了缓解由该问题造成的目标跟踪漂移,提出了一种目标表观字典和背景字典协同结构稀疏重构优化的视觉跟踪方法。通过构建一个有判别力的基于稀疏表示的表观似然模型,实现了对目标表观模型更为准确的描述。通过合理选择约束候选目标区域和候选背景区域的稀疏系数,在表观似然模型中引入判别式信息,以进一步揭示候选目标区域的潜在相关性和候选背景区域的结构关系,从而更加准确地学习候选目标区域的表观模型。大量有挑战性的视频序列上的实验结果验证了算法在复杂背景下跟踪的鲁棒性,与其他相关算法的对比实验也体现了该算法的优越性。     

Robust object tracking via integration of particle filtering with deep detection

We propose a video object tracker (IDPF-RP) which is built upon the variable-rate color particle filtering with two innovations: (i) A deep region proposal network guided candidate BB selection scheme based on the dynamic prediction model of particle filtering is proposed to accurately generate the qualified object BBs. The introduced region proposal alignment scheme significantly improves the localization accuracy of tracking. (ii) A decision level fusion scheme that integrates the particle filter tracker and a deep detector resulting in an improved object tracking accuracy is formulated. This enables us to adaptively update the target model that improves robustness to appearance changes arising from high motion and occlusion. Performance evaluation reported on challenging VOT2018/2017/2016 and OTB-50 data sets demonstrates that IDPF-RP outperforms state-of-the-art trackers especially under size, appearance and illumination changes. Our tracker achieves comparable mean accuracy on VOT2018 while it respectively provides about 8%, 15%, and 30% higher success rates on VOT2016, VOT2017 and OTB-50 when IoU threshold is 0.5.     

高置信度互补学习的实时目标跟踪

目的 判别式目标跟踪算法在解决模型漂移问题时通常都是在预测结果的基础上构建更可靠的样本或采用更健壮的分类器,从而忽略了高效简洁的置信度判别环节。为此,提出高置信度互补学习的实时目标跟踪算法（HCCL-Staple）。方法 将置信度评估问题转化为子模型下独立进行的置信度计算与互补判别,对相关滤波模型计算输出的平均峰值相关能量（APCE）,结合最大响应值进行可靠性判定,当二者均以一定比例大于历史均值时,判定为可靠并进行更新,将颜色概率模型的输出通过阈值处理转化为二值图像,并基于二值图像形态学提取像素级连通分量属性（PCCP）,综合考虑连通分量数量、最大连通分量面积及矩形度进行可靠性判别,当置信度参数多数呈高置信度形态时,判定为可靠,进行更新;否则,判定为不可靠,降低该模型的融合权重并停止更新。结果 在数据集OTB-2015上的实验结果表明,HCCL-Staple算法与原算法相比,距离精度提高了3.2%,成功率提高了2.7%,跟踪速度为32.849帧/s,在颜色特征适应性较弱的场景和目标被遮挡的复杂场景中均能有效防止模型漂移,与当前各类主流的跟踪算法相比具有较好的跟踪效果。结论 两种子模型的置信度判别方法均能针对可能产生低置信度结果的敏感场景进行有效估计,且对输出形式相同的其他模型在置信度判别上具有一定的适用性。互补使用上述判别策略的HCCL-Staple算法能够有效防止模型漂移,保持高速的同时显著提升跟踪精度。