Siamese visual tracking with multilayer feature fusion and corner distance IoU loss

The tracker based on the Siamese network regards tracking tasks as solving a similarity problem between the target template and search area. Using shallow networks and offline training, these trackers perform well in simple scenarios. However, due to the lack of semantic information, they have difficulty meeting the accuracy requirements of the task when faced with complex backgrounds and other challenging scenarios. In response to this problem, we propose a new model, which uses the improved ResNet-22 network to extract deep features with more semantic information. Multilayer feature fusion is used to obtain a high-quality score map to reduce the influence of interference factors in the complex background on the tracker. In addition, we propose a more powerful Corner Distance IoU (intersection over union) loss function so that the algorithm can better regression to the bounding box. In the experiments, the tracker was extensively evaluated on the object tracking benchmark data sets, OTB2013 and OTB2015, and the visual object tracking data sets, VOT2016 and VOT2017, and achieved competitive performance, proving the effectiveness of this method.     

结合GLCM与三阶张量建模的在线目标跟踪

为提高目标跟踪算法对多种目标表观变化场景的自适应能力和跟踪精度,论文提出一种结合灰度共生(GLCM)与三阶张量建模的目标优化跟踪算法。该算法首先提取目标区域的灰度信息,通过GLCM的高区分度特征对目标进行二元超分描述,并结合三阶张量理论融合目标区域的多视图信息,建立起目标的三阶张量表观模型。然后利用线性空间理论对表观模型进行双线性展开,通过在线模型特征值描述与双线性空间的增量特征更新,明显降低模型更新时的运算量。跟踪环节,建立二级联合跟踪机制,结合当前时刻信息通过在线权重估计构建动态观测模型,以真实目标视图为基准建立静态观测模型对跟踪估计动态调整,以避免误差累积出现跟踪漂移,最终实现对目标的稳定跟踪。通过与典型算法进行多场景试验对比,表明该算法能够有效应对多种复杂场景下的运动目标跟踪,平均跟踪误差均小于9像素。     

自适应时空正则的无人机目标跟踪算法

针对无人机跟踪场景中目标分辨率较低且易受无人机(unmanned aerial vehicle,UAV)飞行姿态、速度变化等因素的影 响而难以对目标进行鲁棒跟踪的问题,提出了一种自适应时空正则的无人机目标跟踪算法以 有效解决上述问题。在时空正则相关滤波器(spatial temporal regularized correlation filter,STRCF)算法基础上引入AutoTrack中的空间正则性代价并利用峰值 旁瓣比和局部响应变化量,在线动态更新时空正则化参数以提升跟踪器的准确性,通过在跟踪 器中嵌入遮挡处理模块解决目标遭遮挡后跟踪漂移的问题。在多个无人机基准数据集上进行 了测试,实验结果表明,与基准算法AutoTrack相比,本文算法具有更高的精确度和更快的 处理速度。其中在DTB70数据集上跟踪精度和速度分别提升了1.5% 和74.4%;在UAVDT 数据集上9个属性的分类对比中,本文算法在尺度变化(scale variation,SV)、目标模糊(object blur,OB)等7个属 性上取得较高的性能,均排在第一位。由此可见本文算法可以更好地满足无人机应用需求。     

基于多示例学习和随机蕨丛检测的在线目标跟踪

基于检测的目标跟踪方法目前在计算机视觉领域受到了广泛的关注,这类方法通过训练判别分类器将目标对象从背景中分离出来;分类器的训练是根据当前的跟踪状态从当前帧中提取正负样本来进行,但训练样本的不准确将导致分类器退化产生漂移。该文提出一种能够有效克服目标漂移的跟踪算法,采用检测器和跟踪器相结合的框架,利用中值流算法作为跟踪器,提高跟踪点的可靠性;级联若干个随机蕨弱分类器构成强分类器作为检测器;用在线多示例学习方法更新检测器,提高检测精度;最后将检测器、跟踪器的结果相融合得到最终的目标位置。实验结果表明,与其它方法相比,该方法对目标漂移有更强的鲁棒性。     

融合运动信息与表观信息的多目标跟踪算法

多目标跟踪是计算机视觉领域的重要研究方向,其在智能视频监控、人机交互、机器人导航、公共安全等领域有着重要的作用。目前目标跟踪算法仍面临诸多的挑战,例如遮挡、背景复杂、运动模糊等因素所造成的影响难以完全规避。文中基于一种简单的在线跟踪方法,提出一种融合多类信息的算法,有效地提升了跟踪器的性能。模型关注于帧与帧之间的目标检测与数据关联问题,依赖于不同帧之间目标运动与表观的相似性,当目标丢失及存在遮挡时,融合多源信息减少相关的不确定性。同时,该算法在真实环境中可实现实时跟踪的性能。实验评估结果表明,提出的跟踪器在公开数据集上具有良好的性能,可以显著减少目标丢失率以及身份交换率。     

Robust Struck tracker via color Haar-like feature and selective updating

Recently, Struck—a tracker based on structured support vector machine, received great attention as a consequence of its superior performance on many challenging scenes. In this work, we present an improved Struck tracker by using color Haar-like features and effective selective updating. First, we integrate color information into Haar-like features in a simple way, which models the spatial and color information simultaneously without increasing the computational complexity. Second, we make selective model updates according to the tracking status of the object. This prevents inferior patterns resulted by occlusions, abrupt appearance or illumination changes from being added to object model, which decreases the risk of model drift problem. The experimental results indicate that the proposed tracking algorithm outperforms the original Struck by a remarkable margin in precision and accuracy, and it is competitive with other state-of-the-art trackers on a tracking benchmark of 50 challenging sequences.     

Real-time and robust visual tracking with scene-perceptual memory

Unmanned aerial vehicle (UAV) based aerial visual tracking is one of the research hotspots in computer vision. However, the mainstream trackers for UAV still have two shortcomings: (1) the accuracy of correlation filter tracker is greatly improved with more complex model, it impedes accuracy-speed trade-off. (2) object occlusion and camera motion in the aerial tracking scene also seriously restrict the application of aerial tracking. To address these problems, and inspired by AutoTrack tracker, we propose an aerial correlation filtering tracker based on scene-perceptual memory, Fast-AutoTrack. Firstly, to perceive and judge tracking anomalies, such as object occlusion and camera motion, inspired by the peak sidelobe ratio and AutoTrack, a confidence score is designed by perceiving and remembering the changing trend of the confidence and the local historical confidence. Secondly, after tracking anomaly occurring, several search regions are predicted based on the local object motion trend and the Spatio-temporal context information for object re-detection. Finally, to accelerate the model updating, the perceptual hashing algorithm (PHA) is used to obtain the similarity of the search regions between two adjacent frames. On typical aerial tracking datasets UAVDT, UAV123@10fps, and DTB70, Fast-AutoTrack run 71.4% faster than AutoTrack with almost equal accuracy and show favorable accuracy-speed trade-off.     

基于关键特征信息感知和在线自适应掩模的孪生网络目标跟踪

近年来,孪生网络在视觉目标跟踪的应用给跟踪器性能带来了极大的提升,可以同时兼顾准确率和实时性。然而,孪生网络跟踪器的准确率在很大程度上受到限制。为了解决上述问题,该文基于通道注意力机制,创新地提出了关键特征信息感知模块来增强网络模型的判别能力,使网络聚焦于目标的卷积特征变化;在此基础上,该文还提出了一种在线自适应掩模策略,根据在线学习到的互相关层输出状态,自适应掩模后续帧,以此来突出前景目标。在OTB100, GOT-10k数据集上进行实验验证,所提跟踪器在不影响实时性的前提下,准确率相较于基准有了显著提升,并且在遮挡、尺度变化以及背景杂乱等复杂场景下具有鲁棒的跟踪效果。     

Robust shape tracking with multiple models in ultrasound images

This paper addresses object tracking in ultrasound images using a robust multiple model tracker. The proposed tracker has the following features: 1) it uses multiple dynamic models to track the evolution of the object boundary, and 2) it models invalid observations (outliers), reducing their influence on the shape estimates. The problem considered in this paper is the tracking of the left ventricle which is known to be a challenging problem. The heart motion presents two phases (diastole and systole) with different dynamics, the multiple models used in this tracker try to solve this difficulty. In addition, ultrasound images are corrupted by strong multiplicative noise which prevents the use of standard deformable models. Robust estimation techniques are used to address this difficulty. The multiple model data association (MMDA) tracker proposed in this paper is based on a bank of nonlinear filters, organized in a tree structure. The algorithm determines which model is active at each instant of time and updates its state by propagating the probability distribution, using robust estimation techniques.     

基于多层字典的自重构目标跟踪算法

针对视觉跟踪系统中常用的模板处理方法很难 适应目标外观和视频背景不断变化的不足,提出一种基于多层字典的自重构 目标跟踪算法。通过构建多层字典,分别从时间和 空间上增强目标描述能力,既可以刻画目标局部细节,又蕴含了目标整体信息;在跟踪过程 中,模板可以利 用多层字典根据前景和背景的复杂性自适应地分裂与分并,分裂出多个跟踪器从不同角度进 行跟踪,有效地 提高定位精度,也可以合并子模板以达到降低系统的计算负荷。定性和定量分析的实验结果 表明,本文算法具 有良好的跟踪精度和运行效率,可以较好地应对变化与遮挡。     

基于强化学习的公共空间行人轨迹跟踪

对公共空间中的多目标行人轨迹跟踪问题,提出一种基于强化学习的多目标行人轨迹跟踪算法.首先采用高精确度的目标检测器检测公共空间视频中的行人目标,并为每个目标分配一个独立的单目标跟踪器进行轨迹跟踪;将每个目标作为独立智能体,通过深度强化学习方式进行训练;接下来结合跟踪轨迹与检测目标之间的表观和位置特征构建相似度代价矩阵;最...     

基于自适应模型更新的实时跟踪算法

为提高分层卷积特征目标跟踪算法的速度和精度,文中提出了一种基于自适应模型更新的单层卷积特征目标跟踪算法。首先提取Pool4层的多通道的卷积特征对训练样本的类标函数进行调整,在确保跟踪精确度的同时提高了算法的速度。该算法引入了平均峰值能量比,通过比值变化情况反馈目标跟踪的结果,与稀疏模型更新策略相结合,对跟踪器进行自适应更新,提高了算法对遮挡和相似物干扰的鲁棒性。对于目标快速尺度变化问题,文中采用尺度金字塔对尺度进行评估,提高了跟踪器的泛化能力。在OTB2013和OTB2015上测试新算法,实验结果表明,该算法的平均距离精度分别为91.0%和86.8%,平均速度约43 帧/s,局域良好的鲁棒性和实时性。     

Automatic bootstrapping and tracking of object contours

A new fully automatic object tracking and segmentation framework is proposed. The framework consists of a motion-based bootstrapping algorithm concurrent to a shape-based active contour. The shape-based active contour uses finite shape memory that is automatically and continuously built from both the bootstrap process and the active-contour object tracker. A scheme is proposed to ensure that the finite shape memory is continuously updated but forgets unnecessary information. Two new ways of automatically extracting shape information from image data given a region of interest are also proposed. Results demonstrate that the bootstrapping stage provides important motion and shape information to the object tracker. This information is found to be essential for good (fully automatic) initialization of the active contour. Further results also demonstrate convergence properties of the content of the finite shape memory and similar object tracking performance in comparison with an object tracker with unlimited shape memory. Tests with an active contour using a fixed-shape prior also demonstrate superior performance for the proposed bootstrapped finite-shape-memory framework and similar performance when compared with a recently proposed active contour that uses an alternative online learning model.     

采用高维数据聚类的目标跟踪

根据刚体各部位具有变换一致性这一特性,提出一种采用高维数据聚类的目标跟踪方法。从数学理论方面证明提出的度量方法可以应用于目标跟踪, 称其为高维数据聚类跟踪器(HDDC tracker)。该算法框架如下,首先, 采用Harris检测器对模板与跟踪区域进行特征提取;然后利用这些特征的空间信息对所提取的特征进行编组;接着计算模板特征组与跟踪区域特征组间的仿射变换阵;最后,采用高维数据聚类对这些仿射变换阵进行度量, 将那些相似仿射阵对应的跟踪区域作为跟踪目标。实验表明: HDDC tracker能够有效地跟踪具有仿射形变的目标,并且性能优于先进跟踪算法。     

基于时空信息融合的无人艇水面目标检测跟踪

在无人艇(USV)的导航、避障等多种任务中,目标检测与跟踪都十分重要,但水面环境复杂,存在目标尺度变化、遮挡、光照变化以及摄像头抖动等诸多问题。该文提出基于时空信息融合的无人艇水面视觉目标检测跟踪,在空间上利用深度学习检测,提取单帧深度语义特征,在时间上利用相关滤波跟踪,计算帧间方向梯度特征相关性,通过特征对比将时空信息进行融合,实现了持续稳定地对水面目标进行检测与跟踪,兼顾了实时性和鲁棒性。实验结果表明,该算法平均检测速度和精度相对较高,在检测跟踪速度为15 fps情况下,检测跟踪精确度为0.83。     

基于信赖域的序贯拟蒙特卡洛滤波算法

针对系统状态估计、目标跟踪等是包含多源不确定性信息的非线性非高斯随机过程,提出了一种基于信赖域的序贯拟蒙特卡洛(Sequential Quasi-Monte Carlo,SQMC)滤波算法.该算法利用拟蒙特卡洛积分技术优化采样粒子在状态空间的分布特性,降低了滤波过程中的积分误差,提高了状态估计精度;同时,利用信赖域(T...     

基于KL散度与通道选择的热红外目标跟踪算法

为了解决单一跟踪器无法有效应对复杂背景及目标外观的显著变化,对于热红外目标跟踪准确度不高的问题,基于全卷积孪生网络提出了一种多响应图集成的跟踪算法用于热红外跟踪。首先,使用预训练的卷积神经网络来提取热红外目标的多个卷积层的特征并进行通道选择,在此基础上分别构建3个对应的跟踪器,每个跟踪器独立执行跟踪并返回一个响应图。然后,利用Kullback–Leibler（KL）散度对多个响应图进行优化集成,得到一个更强的响应图。最后利用集成后的响应图来确定目标位置。为了评估所提算法的性能,在当前最全面的热红外跟踪基准LSOTB-TIR（Large-Scale Thermal Infrared Object Tracking Benchmark）上进行了实验。实验结果表明,所提算法能够适应复杂多样的红外跟踪场景,综合性能超过了现有的红外跟踪算法。     

基于边缘多通道梯度模型的多运动目标检测

针对视频序列运动目标检测易受环境噪声干扰、提取目标轮廓困难的问题,提出了一种基于边缘多通道梯度改进模型的多运动目标检测算法。首先,利用Canny算子获取视频序列中目标的边缘信息,并根据人类视觉色彩的恒常特性,对目标边缘建立时间、空间、颜色多通道梯度模型;然后,利用该模型获取目标边缘像素点的运动状态描述信息,实现背景边缘和运动物体边缘的分离;最后,将间断边缘像素点与其邻域点的运动状态相关联,以连接目标间断边缘,实现运动目标轮廓的提取,并将连接后的轮廓进行形态学处理以分割出目标。实验结果表明,与同类型算法相比,本算法在运动目标检测中具有的实时性、准确性和鲁棒性更好。     

Visual tracking with genetic algorithm augmented logistic regression

In this paper, a genetic algorithm (GA) augmented logistic regression tracker is proposed. We enhance our tracker in three aspects. Firstly, a novel concept of intelligent motion model based on GA and particle filter is proposed to handle the partial occlusion, object drift and fast object motion changes during tracking. Secondly, the powerful and efficient features including FHOG and Lab are integrated to further boost the tracking performance. Thirdly, mechanism of dynamic update and choice mechanism of positive and negative templates are introduced to better adapt to the appearance changes. Extensive experimental results on the Object Tracking Benchmark dataset show that the proposed tracker performs favorably against state-of-the-art methods in terms of accuracy and robustness.     

基于相关滤波扩展记忆系统模型的智能目标跟踪

将目标跟踪过程看作一个多重记忆系统模型,提 出了基于相关滤波的扩展记忆系统模型,实现了基 于记忆系统模型的智能目标跟踪。首先,通过提取跟踪目标特征学习目标信息,生成短时相 关滤波器,产 生短时记忆;然后利用每一帧短期记忆的不断重复与更新,产生长时记忆,生成长时相关滤 波器。短时与 长时记忆构成相关滤波记忆系统模型,完成目标跟踪。在此模型基础上,分析与挖掘模型中 的相关滤波数 据,加入四种智能化控制信息,构建扩展记忆系统模型,实现智能化的目标跟踪。基于相关 滤波的扩展记 忆系统模型利用生物记忆的原理使目标跟踪更加自动化、智能化,增强目标跟踪的准确性。 实验结果表明, 与当前流行的相关滤波跟踪算法相比,本文算法提高了目标跟踪的抗干扰性、抗遮挡性与抗 形变能力,同时保证了在尺度跟踪的有效性。