判别稀疏表示与在线字典学习的运动目标跟踪

针对传统稀疏表示不能有效区分目标和背景的缺点,提出一种判别稀疏表示算法,这种算法在传统稀疏表示目标函数中加入一个判别函数,大大降低干扰因素对目标跟踪的影响。基于判别稀疏表示和[?1]约束,提出一种在线字典学习算法升级目标模板,有效降低背景信息对目标模板的影响。提取目标梯度方向的直方图（HOG）特征,利用其对光照和形变等复杂环境具有较强鲁棒性的优点,实现对目标更稳定的跟踪。实验结果表明,与现有跟踪方法相比,该算法的跟踪效果更好。     

在线判别分析的稀疏视觉跟踪

通过分析经典稀疏视觉跟踪算法在粒子滤波框架下的采样粒子分布与运动目标真实状态的差异,提出了一个基于在线判别分析的改进稀疏视觉跟踪算法。该跟踪算法通过在线逻辑斯蒂判别分析模型及其更新过程,自主获取运动目标的实时状态与变化,增强运动目标与背景信息之间的可判别性。同时,实现对采样粒子的预先筛选,尽量排除与运动目标差异大的粒子,以提高跟踪算法的鲁棒性,同时减少L1优化求解的次数从而提高算法的执行效率。与5个高水平跟踪算法在4段公开视频上的实验结果表明,提出的算法能够长时间鲁棒地对运动目标进行跟踪,同时相对典型稀疏跟踪算法而言,明显地降低了计算复杂度。     

软判决稀疏字典的目标跟踪算法

为提高视频目标跟踪算法的鲁棒性,提出一种基于在线更新稀疏模板的自适应参数特征判别跟踪算法.该算法采用离线方式训练出基于方向梯度直方图特征的字典,用于目标表示和线性分类器训练,从而构建出非固定参数的观测模型;观测模型中动态调整的权重系数由采用正负模板构建形成的稀疏字典进行实时动态更新;将观测模型与粒子滤波相结合对当前帧的各候选采样进行观测,得出跟踪结果.实验结果表明,文中算法具有相对较好的鲁棒性.     

加权的超像素级时空上下文目标跟踪

目标跟踪是计算机视觉中的热点问题,而目标运动的复杂背景、光照变换和尺度变化等因素大大的影响着目标跟踪的准确性。总结当前比较热门的几种跟踪算法的优缺点,针对时空上下文算法的不足提出了改进方法：加权的超像素级时空上下文目标跟踪算法（weighted super pixel level spatio-temporal context,WSSTC）。该算法利用像素的特征信息对目标上下文区域进行聚类,形成超像素级区域,并通过时间上下文中超像素块特征的相似性,对空间上下文进行加权处理,建立了超像素级的目标外观模型。实验结果表明,加权的超像素级时空上下文目标跟踪算法在目标跟踪中具有更好的准确性和鲁棒性。     

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。     

融合显著度时空上下文的超像素跟踪算法*

为了更有效地利用目标的特征信息,提高目标的跟踪精度和鲁棒性,提出融合显著度时空上下文的超像素跟踪算法.首先对目标上下文区域进行超像素分割,根据运动信息计算目标上下文的运动相关性及特征协方差信息,得到相关性显著度.然后基于贝叶斯框架,在频域构建融合显著度信息的时空上下文模型.再利用联合颜色和纹理的直方图信息计算巴氏系数,更新时空上下文模型.此外,引入尺度金字塔模型,准确估计目标尺度.最后加入低通滤波自适应运动预测模块,在线更新动态模型样本集,使用岭回归方法实现低通滤波的参数在线更新.在公共数据上的实验表明,文中算法在光照变化、背景复杂、目标旋转、机动性高、分辨率低等情况下具有较好的跟踪效果.     

基于稀疏表示和特征选择的LK目标跟踪

为了实现复杂场景中的视觉跟踪, 提出了一种以LK（Lucas-Kanade）图像配准算法为框架, 基于稀疏表示的在线特征选择机制。在视频序列的每一帧, 筛选出一些能够很好区分目标及其相邻背景的特征, 从而降低干扰对跟踪的影响。该算法分别构造前景字典和背景字典, 前景字典来自于第一帧的手动标定, 并随着跟踪结果不断更新, 而背景字典则在每一帧重新构造。同时, 一种新的字典更新策略不仅能有效应对目标的外观变化, 而且通过特征选择机制, 能避免在更新过程中引入干扰, 从而克服了漂移现象。 大量的实验结果表明, 该算法能有效应对视角变化、光照变化以及大面积的局部遮挡等挑战。     

样本分块稀疏表示判决式目标跟踪

为了提高目标跟踪算法的鲁棒性和准确性,提出了一种粒子滤波框架下的样本分块稀疏表示判决式跟踪算法。算法在首帧提取目标模板和背景模板,并将这些模板进行分块,构建模板字典。然后,将候选目标进行分块处理,并使用模板字典稀疏重构候选目标分块,从而获得候选目标的稀疏系数和残差。进而,构建一款贝叶斯分类器,分类器的输入为候选目标稀疏系数和残差中提取的相似度信息,输出为候选目标与真实目标的相似度。分类器通过跟踪过程中获得的正负样本进行训练,使之能够适应目标和背景的变化。最后,将文中算法在8组具有挑战性的视频中进行测试,平均跟踪误差为5.9个像素,跟踪成功率为89%。与选取的3种先进的算法比较,本文算法具有更高的鲁棒性和准确性。     

标签一致K-SVD稀疏编码视频跟踪算法

稀疏编码视频目标跟踪算法对目标遮挡问题有一定的适应性,但当目标受背景杂波、光照变化等干扰时,跟踪结果将会出现漂移现象.为此,提出一种基于字典学习和模板更新的视频目标跟踪算法.该算法在构造字典时加入背景模板集,利用标签一致K-SVD方法进行字典学习,同时训练出低维字典和目标背景分类器;在稀疏编码过程中,借助粒子滤波技术,采用分类器分类结果和候选目标直方图构建整体似然模型;最后通过字典学习更新字典、分类器及目标直方图.采用标准数据库中具有挑战性的视频数据进行算法测试实验,结果表明,对于存在遮挡、背景杂波、光照变化、目标旋转和尺度变化等复杂跟踪环境下的目标跟踪,文中算法都能有效地降低跟踪结果存在的漂移现象,且具有较好的稳定性.     

基于分段加权的反向稀疏跟踪算法研究

为提高稀疏表示跟踪模型性能，提出一种分段加权的反向稀疏跟踪算法，将跟踪问题转化为在贝叶斯框架下寻找概率最高的候选对象问题，构造不同的分段权重函数来分别度量候选目标与正负模板的判别特征系数。通过池化来降低跟踪结果的不确定性干扰，选择正负模板加权系数差值最大的候选表示作为跟踪结果。实验表明，在光照变化、遮挡、快速运动、运动模糊情况下，所提出的算法可以确保跟踪结果的准确性和鲁棒性。     

Discriminative multi-task objects tracking with active feature selection and drift correction

In this paper, we propose a discriminative multi-task objects tracking method with active feature selection and drift correction. The developed method formulates object tracking in a particle filter framework as multi-Task discriminative tracking. As opposed to generative methods that handle particles separately, the proposed method learns the representation of all the particles jointly and the corresponding coefficients are similar. The tracking algorithm starts from the active feature selection scheme, which adaptively chooses suitable number of discriminative features from the tracked target and background in the dynamic environment. Based on the selected feature space, the discriminative dictionary is constructed and updated dynamically. Only a few of them are used to represent all the particles at each frame. In other words, all the particles share the same dictionary templates and their representations are obtained jointly by discriminative multi-task learning. The particle that has the highest similarity with the dictionary templates is selected as the next tracked target state. This jointly sparsity and discriminative learning can exploit the relationship between particles and improve tracking performance. To alleviate the visual drift problem encountered in object tracking, a two-stage particle filtering algorithm is proposed to complete drift correction and exploit both the ground truth information of the first frame and observations obtained online from the current frame. Experimental evaluations on challenging sequences demonstrate the effectiveness, accuracy and robustness of the proposed tracker in comparison with state-of-the-art algorithms.     

Robust visual tracking via discriminative appearance model based on sparse coding

In this paper, we formulate visual tracking as a binary classification problem using a discriminative appearance model. To enhance the discriminative strength of the classifier in separating the object from the background, an over-complete dictionary containing structure information of both object and background is constructed which is used to encode the local patches inside the object region with sparsity constraint. These local sparse codes are then aggregated for object representation, and a classifier is learned to discriminate the target from the background. The candidate sample with largest classification score is considered as the tracking result. Different from recent sparsity-based tracking approaches that update the dictionary using a holistic template, we introduce a selective update strategy based on local image patches which alleviates the visual drift problem, especially when severe occlusion occurs. Experiments on challenging video sequences demonstrate that the proposed tracking algorithm performs favorably against several state-of-the-art methods.     

多模型协作的分块目标跟踪

为解决复杂场景下,基于整体表观模型的目标跟踪算法容易丢失目标的问题,提出一种多模型协作的分块目标跟踪算法.融合基于局部敏感直方图的产生式模型和基于超像素分割的判别式模型构建目标表观模型,提取局部敏感直方图的亮度不变特征来抵制光照变化的影响;引入目标模型的自适应分块划分策略以解决局部敏感直方图算法缺少有效遮挡处理机制的问题,提高目标的抗遮挡性;通过相对熵和均值聚类度量子块的局部差异置信度和目标背景置信度,建立双权值约束机制和子块异步更新策略,在粒子滤波框架下,选择置信度高的子块定位目标.实验结果表明,本文方法在复杂场景下具有良好的跟踪精度和稳定性.     

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.     

一种结合空间信息和稀疏字典优化的目标跟踪算法

针对复杂场景中目标表观变化引起的跟踪漂移问题, 提出一种新的基于稀疏表示的目标跟踪算法. 该算法通过稀疏性和空间相关性正则约束得到一种优化的目标代价函数, 利用拉格朗日对偶理论和加速近端梯度方法完成字典优化, 并利用最大池化理论和空间金字塔方法得到降维的且包含更多空间信息的目标模板系数和候选样本系数. 实验结果表明, 所提出的算法在背景干扰、光照变化、形变、运动模糊、严重遮挡等多种复杂场景中都能取得较为鲁棒的跟踪效果.     

基于稀疏表达的遮挡目标跟踪算法

针对视觉跟踪中的目标遮挡问题,提出一种基于稀疏表达的视觉跟踪算法。采用稀疏表达方法描述跟踪目标,构造基于Gabor特征的目标词典和遮挡词典,通过l1范数最优化求解稀疏表达系数。在粒子滤波框架下跟踪目标,根据稀疏表达系数判断遮挡,并利用重构残差更新遮挡情况下的粒子权重。在目标模板更新时,通过引入可靠性评价来抑制模板漂移。实验结果表明,该算法能够有效地跟踪处于遮挡状态下的运动目标,并对目标姿态变化以及光照变化具有较好的鲁棒性。     

Synthesis K-SVD based analysis dictionary learning for pattern classification

In the fields of computer vision and pattern recognition, dictionary learning techniques have been widely applied. In classification tasks, synthesis dictionary learning is usually time-consuming during the classification stage because of the sparse reconstruction procedure. Analysis dictionary learning, which is another research line, is more favorable due to its flexible representative ability and low classification complexity. In this paper, we propose a novel discriminative analysis dictionary learning method to enhance classification performance. Particularly, we incorporate a linear classifier and the supervised information into the traditional analysis dictionary learning framework by adding a discrimination error term. A synthesis K-SVD based algorithm which can effectively constrain the sparsity is presented to solve the proposed model. Extensive comparison experiments on benchmark databases validate the satisfactory performance of our method.

     

Online visual tracking based on subspace representation with continuous occlusion modeling

As an important issue in image processing and computer vision, online visual tracking acts a critical role in numerous lines of research and has many potential applications. This paper presents a novel tracking algorithm based on subspace representation with continuous occlusion handling, the contributions of which are threefolds. First, this paper develops an effective objective function to represent the tracked object, in which the object reconstruction, the sparsity of the error term and the spatial consistency of the error term are simultaneously considered. Then, we derive an iterative algorithm to solve the proposed objective function based on the accelerated proximal gradient framework, and therefore obtain the optimal representation coefficients and the possible occlusion conditions. Finally, based on the proposed representation model, we design an effective likelihood function and a simple model update scheme for building a robust tracker within the particle filter framework. We conduct many experiments to evaluate the proposed tracking algorithm in comparisons with other state-of-the-art trackers. Both qualitative and quantitative evaluations demonstrate the proposed tracker achieves good performance.     

稀疏性正则化非负矩阵分解的在线学习方法

针对非负矩阵分解效率低的不足,提出一种基于在线学习的稀疏性非负矩阵分解的快速方法.通过对目标函数添加正则化项来控制分解后系数矩阵的稀疏性,将问题转化成稀疏表示的字典学习问题,利用在线字典学习算法求解目标函数,并对迭代过程的矩阵更新进行转换,采取块坐标下降法进行矩阵更新,提高算法收敛速度.实验结果表明,该方法在有效保持图像特征信息的同时,运行效率得到提高.