While recent years have witnessed astonishing improvements in visual tracking robustness, the advancements in tracking accuracy have been limited. As the focus has been directed towards the development of powerful classifiers, the problem of accurate target state estimation has been largely overlooked. In fact, most trackers resort to a simple multi-scale search in order to estimate the target bounding box. We argue that this approach is fundamentally limited since target estimation is a complex task, requiring highlevel knowledge about the object.We address this problem by proposing a novel tracking architecture, consisting of dedicated target estimation and classification components. High level knowledge is incorporated into the target estimation through extensive offline learning. Our target estimation component is trained to predict the overlap between the target object and an estimated bounding box. By carefully integrating target-specific information, our approach achieves previously unseen bounding box accuracy. We further introduce a classification component that is trained online to guarantee high discriminative power in the presence of distractors. Our final tracking framework sets a new state-of-the-art on five challenging benchmarks. On the new large-scale Track-ingNet dataset, our tracker ATOM achieves a relative gain of 15% over the previous best approach, while running at over 30 FPS. Code and models are available at https: //github.com/visionml/pytracking.
translated by 谷歌翻译
The current strive towards end-to-end trainable computer vision systems imposes major challenges for the task of visual tracking. In contrast to most other vision problems, tracking requires the learning of a robust target-specific appearance model online, during the inference stage. To be end-to-end trainable, the online learning of the target model thus needs to be embedded in the tracking architecture itself. Due to the imposed challenges, the popular Siamese paradigm simply predicts a target feature template, while ignoring the background appearance information during inference. Consequently, the predicted model possesses limited target-background discriminability.We develop an end-to-end tracking architecture, capable of fully exploiting both target and background appearance information for target model prediction. Our architecture is derived from a discriminative learning loss by designing a dedicated optimization process that is capable of predicting a powerful model in only a few iterations. Furthermore, our approach is able to learn key aspects of the discriminative loss itself. The proposed tracker sets a new state-of-the-art on 6 tracking benchmarks, achieving an EAO score of 0.440 on VOT2018, while running at over 40 FPS. The code and models are available at https: //github.com/visionml/pytracking.
translated by 谷歌翻译
准确且强大的视觉对象跟踪是最具挑战性和最基本的计算机视觉问题之一。它需要在图像序列中估计目标的轨迹,仅给出其初始位置和分段,或者在边界框的形式中粗略近似。判别相关滤波器(DCF)和深度暹罗网络(SNS)被出现为主导跟踪范式,这导致了重大进展。在过去十年的视觉对象跟踪快速演变之后,该调查介绍了90多个DCFS和暹罗跟踪器的系统和彻底审查,基于九个跟踪基准。首先,我们介绍了DCF和暹罗跟踪核心配方的背景理论。然后,我们在这些跟踪范式中区分和全面地审查共享以及具体的开放研究挑战。此外,我们彻底分析了DCF和暹罗跟踪器对九个基准的性能,涵盖了视觉跟踪的不同实验方面:数据集,评估度量,性能和速度比较。通过提出根据我们的分析提出尊重开放挑战的建议和建议来完成调查。
translated by 谷歌翻译
在本文中,我们介绍了Siammask,这是一个实时使用相同简单方法实时执行视觉对象跟踪和视频对象分割的框架。我们通过通过二进制细分任务来增强其损失,从而改善了流行的全面暹罗方法的离线培训程序。离线训练完成后,SiamMask只需要一个单个边界框来初始化,并且可以同时在高框架速率下进行视觉对象跟踪和分割。此外,我们表明可以通过简单地以级联的方式重新使用多任务模型来扩展框架以处理多个对象跟踪和细分。实验结果表明,我们的方法具有较高的处理效率,每秒约55帧。它可以在视觉对象跟踪基准测试中产生实时最新结果,同时以高速进行视频对象分割基准测试以高速显示竞争性能。
translated by 谷歌翻译
估计目标范围在视觉对象跟踪中构成了基本挑战。通常,跟踪器以箱子为中心,并且完全依靠边界框来定义场景中的目标。实际上,对象通常具有复杂的形状,并且与图像轴不符。在这些情况下,边界框不能提供对目标的准确描述,并且通常包含大多数背景像素。我们提出了一个以细分为中心的跟踪管道,该管道不仅会产生高度准确的分割掩码,而且还可以使用分割掩码而不是边界框来使用内部。因此,我们的跟踪器能够更好地学习目标表示形式,该目标表示明确将场景中的目标与背景内容区分开来。为了实现具有挑战性的跟踪方案的必要鲁棒性,我们提出了一个单独的实例本地化组件,该组件用于在产生输出掩码时用于调节分割解码器。我们从分段掩码中推断出一个边界框,验证我们的跟踪器在挑战跟踪数据集方面,并在LASOT上实现新的最新状态,并以69.7%的速度获得了AUC得分。由于大多数跟踪数据集不包含掩码注释,因此我们无法使用它们来评估预测的分割掩码。相反,我们在两个流行的视频对象细分数据集上验证了分割质量。
translated by 谷歌翻译
基于模板的鉴别性跟踪器是目前主导的跟踪范例由于其稳健性,但不限于边界框跟踪和有限的转换模型,这降低了它们的本地化准确性。我们提出了一个判别的单次分割跟踪器 - D3S2,其缩小了视觉对象跟踪和视频对象分段之间的差距。单次网络应用两个具有互补的几何属性的目标模型,一个不变的变换,包括非刚性变形,另一个假设刚性对象同时实现强大的在线目标分段。通过解耦对象和特征比例估计,进一步提高了整体跟踪可靠性。没有每数据集FineTuning,并且仅用于分段作为主要输出,D3S2胜过最近的短期跟踪基准Vot2020上的所有已发布的跟踪器,并非常接近GOT-10K上的最先进的跟踪器, TrackingNet,OTB100和Lasot。 D3S2优于视频对象分段基准上的前导分割跟踪器SIAMMASK,并与顶部视频对象分段算法进行操作。
translated by 谷歌翻译
基于暹罗的跟踪器在Visual Object跟踪任务上实现了有希望的性能。大多数现有的基于暹罗的跟踪器包含两个单独的跟踪分支,包括分类分支和边界框回归分支。此外,图像分割提供了obetain更准确的目标区域的替代方法。在本文中,我们提出了一种具有两个阶段的新型跟踪器:检测和分割。检测阶段能够通过暹罗网络定位目标。然后,通过在第一阶段中的粗状态估计,通过分割模块获得更准确的跟踪结果。我们对四个基准进行实验。我们的方法可以实现最先进的结果,在VOT2016,VOT2018上的51.3美元\%$ 52.6 $ \%$分别在VOT2018和VOT2019数据集上的39.0 $ \%$。
translated by 谷歌翻译
In recent years, Discriminative Correlation Filter (DCF) based methods have significantly advanced the state-of-theart in tracking. However, in the pursuit of ever increasing tracking performance, their characteristic speed and realtime capability have gradually faded. Further, the increasingly complex models, with massive number of trainable parameters, have introduced the risk of severe over-fitting. In this work, we tackle the key causes behind the problems of computational complexity and over-fitting, with the aim of simultaneously improving both speed and performance.We revisit the core DCF formulation and introduce: (i) a factorized convolution operator, which drastically reduces the number of parameters in the model; (ii) a compact generative model of the training sample distribution, that significantly reduces memory and time complexity, while providing better diversity of samples; (iii) a conservative model update strategy with improved robustness and reduced complexity. We perform comprehensive experiments on four benchmarks: VOT2016, UAV123, OTB-2015, and Temple-Color. When using expensive deep features, our tracker provides a 20-fold speedup and achieves a 13.0% relative gain in Expected Average Overlap compared to the top ranked method [12] in the VOT2016 challenge. Moreover, our fast variant, using hand-crafted features, operates at 60 Hz on a single CPU, while obtaining 65.0% AUC on OTB-2015.
translated by 谷歌翻译
从测试阶段的单个初始示例跟踪视觉对象已被广泛地作为一个/几次射击问题,即初始适应的一次性学习和在线适应的少量学习。近期几次拍摄的在线适应方法通过在离线阶段的复杂元学习优化中,从大量注释的训练数据中纳入了现有知识。这有助于在线深度跟踪器实现快速适应并降低跟踪的过度风险。在本文中,我们提出了一个简单但有效的递归最小二乘估计估计者辅助在线学习方法,但在不需要离线培训的情况下进行了几次拍摄的在线适应。它允许内置的内存保留机制进行模型,以记住关于之前看到的对象的知识,因此可以安全地从训练中安全地移除所看到的数据。这也与在防止灾难性遗忘的新出现的连续学习领域带有某些相似之处。这种机制使我们能够揭示现代在线深度跟踪器的力量,而不会产生过多的计算成本。我们根据在线学习家庭中的两个网络评估我们的方法,即在RT-MDNET中的多层的rceptrons和DIMP中的卷积神经网络。对若干具有挑战性的跟踪基准的一致性改进展示了其有效性和效率。
translated by 谷歌翻译
传统上通过在线学习物体的外观模型来解决任意对象跟踪问题,作为视频本身的唯一培训数据。尽管这些方法的成功,但他们的在线方法本身限制了他们可以学习的模型的丰富性。最近,已经进行了几次尝试利用深度卷积网络的表现力。然而,当预先知道对象轨道时,有必要在线执行随机梯度下降以调整网络的权重,严重影响系统的速度。本文在ILSVRC15数据集上装备了一种基本的跟踪算法,该历程在ILSVRC15数据集上训练了训练的端到端,用于视频中的对象检测。我们的跟踪器以超出实时的帧速率运行,尽管其极端简单,但在多个基准中实现了最先进的性能。
translated by 谷歌翻译
基于无人机(UAV)基于无人机的视觉对象跟踪已实现了广泛的应用,并且由于其多功能性和有效性而引起了智能运输系统领域的越来越多的关注。作为深度学习革命性趋势的新兴力量,暹罗网络在基于无人机的对象跟踪中闪耀,其准确性,稳健性和速度有希望的平衡。由于开发了嵌入式处理器和深度神经网络的逐步优化,暹罗跟踪器获得了广泛的研究并实现了与无人机的初步组合。但是,由于无人机在板载计算资源和复杂的现实情况下,暹罗网络的空中跟踪仍然在许多方面都面临严重的障碍。为了进一步探索基于无人机的跟踪中暹罗网络的部署,这项工作对前沿暹罗跟踪器进行了全面的审查,以及使用典型的无人机板载处理器进行评估的详尽无人用分析。然后,进行板载测试以验证代表性暹罗跟踪器在现实世界无人机部署中的可行性和功效。此外,为了更好地促进跟踪社区的发展,这项工作分析了现有的暹罗跟踪器的局限性,并进行了以低弹片评估表示的其他实验。最后,深入讨论了基于无人机的智能运输系统的暹罗跟踪的前景。领先的暹罗跟踪器的统一框架,即代码库及其实验评估的结果,请访问https://github.com/vision4robotics/siamesetracking4uav。
translated by 谷歌翻译
Siamese network based trackers formulate tracking as convolutional feature cross-correlation between a target template and a search region. However, Siamese trackers still have an accuracy gap compared with state-of-theart algorithms and they cannot take advantage of features from deep networks, such as ResNet-50 or deeper. In this work we prove the core reason comes from the lack of strict translation invariance. By comprehensive theoretical analysis and experimental validations, we break this restriction through a simple yet effective spatial aware sampling strategy and successfully train a ResNet-driven Siamese tracker with significant performance gain. Moreover, we propose a new model architecture to perform layer-wise and depthwise aggregations, which not only further improves the accuracy but also reduces the model size. We conduct extensive ablation studies to demonstrate the effectiveness of the proposed tracker, which obtains currently the best results on five large tracking benchmarks, including OTB2015, VOT2018, UAV123, LaSOT, and TrackingNet. Our model will be released to facilitate further researches.
translated by 谷歌翻译
In this paper we illustrate how to perform both visual object tracking and semi-supervised video object segmentation, in real-time, with a single simple approach. Our method, dubbed SiamMask, improves the offline training procedure of popular fully-convolutional Siamese approaches for object tracking by augmenting their loss with a binary segmentation task. Once trained, SiamMask solely relies on a single bounding box initialisation and operates online, producing class-agnostic object segmentation masks and rotated bounding boxes at 55 frames per second. Despite its simplicity, versatility and fast speed, our strategy allows us to establish a new state of the art among real-time trackers on VOT-2018, while at the same time demonstrating competitive performance and the best speed for the semisupervised video object segmentation task on DAVIS-2016 and DAVIS-2017. The project website is http://www. robots.ox.ac.uk/ ˜qwang/SiamMask.
translated by 谷歌翻译
对人类对象相互作用的理解在第一人称愿景(FPV)中至关重要。遵循相机佩戴者操纵的对象的视觉跟踪算法可以提供有效的信息,以有效地建模此类相互作用。在过去的几年中,计算机视觉社区已大大提高了各种目标对象和场景的跟踪算法的性能。尽管以前有几次尝试在FPV域中利用跟踪器,但仍缺少对最先进跟踪器的性能的有条理分析。这项研究差距提出了一个问题,即应使用当前的解决方案``现成''还是应进行更多特定领域的研究。本文旨在为此类问题提供答案。我们介绍了FPV中单个对象跟踪的首次系统研究。我们的研究广泛分析了42个算法的性能,包括通用对象跟踪器和基线FPV特定跟踪器。分析是通过关注FPV设置的不同方面,引入新的绩效指标以及与FPV特定任务有关的。这项研究是通过引入Trek-150(由150个密集注释的视频序列组成的新型基准数据集)来实现的。我们的结果表明,FPV中的对象跟踪对当前的视觉跟踪器构成了新的挑战。我们强调了导致这种行为的因素,并指出了可能的研究方向。尽管遇到了困难,但我们证明了跟踪器为需要短期对象跟踪的FPV下游任务带来好处。我们预计,随着新的和FPV特定的方法学会得到研究,通用对象跟踪将在FPV中受欢迎。
translated by 谷歌翻译
我们呈现恐惧,新颖,快速,高效,准确,强大的暹罗视觉跟踪器。我们介绍了对象模型适配的架构块,称为双模板表示,以及像素 - 明智的融合块,以实现模型的额外灵活性和效率。双模板模块仅包含单个学习参数的时间信息,而像素-Wise融合块与标准相关模块相比,像素-Wise融合块对具有较少参数的判别特征进行了更多的辨别特征。通过用新型模块插入复杂的骨干,恐惧-M和恐惧-L跟踪器在既准确性和效率的几个学术基准上超过大多数暹粒例子。使用轻质骨干,优化的版本恐惧-XS提供了超过10倍的跟踪跟踪,而不是当前暹罗跟踪器,同时保持最先进的结果。 GEAF-XS跟踪器比LightTrack [62]更小2.4倍,比LightTrack [62]更高。此外,我们通过在能量消耗和执行速度上引入基准来扩展模型效率的定义。源代码,预先训练的模型和评估协议将根据要求提供
translated by 谷歌翻译
尽管机器学习在视觉对象跟踪的任务上进行了广泛采用,但最近基于学习的方法在很大程度上忽略了一个事实,即视觉跟踪是其本质上的序列级任务。他们在很大程度上依赖框架级训练,这不可避免地会导致数据分布和任务目标的培训和测试之间的不一致。这项工作介绍了基于强化学习的视觉跟踪序列训练策略,并讨论了数据采样,学习目标和数据增强的序列级设计如何提高跟踪算法的准确性和稳健性。我们对包括LASOT,TrackingNet和GoT-10K在内的标准基准测试的实验表明,四个代表性跟踪模型,SiamRPN ++,Siamattn,Transt和TRDIMP,通过在不修改建筑架构的情况下将提出的方法纳入训练中,从而不断改进。
translated by 谷歌翻译
更复杂和强大的神经网络模型的设计在视觉对象跟踪中具有显着提升的最先进。这些前进可以归因于更深的网络,或引入新的构建块,例如变形金刚。然而,在追求增加的跟踪性能时,有效的跟踪架构令人惊讶地注意到很少的关注。在本文中,我们介绍了用于实时视觉对象跟踪的高效变压器的示例变压器。 E.T.Track我们的视觉跟踪器包含示例变换器层,在CPU上以47 FPS运行。这比其他基于变压器的型号快8倍,使其成为唯一基于实时变压器的跟踪器。与可在标准CPU上实时运行的轻量级跟踪器相比,E.T.Track始终如一地优于锯齿,OTB-100,NFS,TrackingNet和Vot-ST2020数据集上的所有其他方法。代码很快将在https://github.com/visionml/pytracking上发布。
translated by 谷歌翻译
Generic Object Tracking (GOT) is the problem of tracking target objects, specified by bounding boxes in the first frame of a video. While the task has received much attention in the last decades, researchers have almost exclusively focused on the single object setting. Multi-object GOT benefits from a wider applicability, rendering it more attractive in real-world applications. We attribute the lack of research interest into this problem to the absence of suitable benchmarks. In this work, we introduce a new large-scale GOT benchmark, LaGOT, containing multiple annotated target objects per sequence. Our benchmark allows researchers to tackle key remaining challenges in GOT, aiming to increase robustness and reduce computation through joint tracking of multiple objects simultaneously. Furthermore, we propose a Transformer-based GOT tracker TaMOS capable of joint processing of multiple objects through shared computation. TaMOs achieves a 4x faster run-time in case of 10 concurrent objects compared to tracking each object independently and outperforms existing single object trackers on our new benchmark. Finally, TaMOs achieves highly competitive results on single-object GOT datasets, setting a new state-of-the-art on TrackingNet with a success rate AUC of 84.4%. Our benchmark, code, and trained models will be made publicly available.
translated by 谷歌翻译
最近,我们看到了基于深神经网络(DNN)的视觉跟踪解决方案的快速发展。一些跟踪器将基于DNN的解决方案与判别相关滤波器(DCF)相结合,以提取语义特征并成功地提供最新的跟踪准确性。但是,这些解决方案是高度计算密集型的,需要长时间处理时间,从而导致无抵押的实时性能。为了提供高精度和可靠的实时性能,我们提出了一个名为Siamvgg的新颖跟踪器。它结合了卷积神经网络(CNN)主链和互相关操作员,并利用示例图像中的功能以进行更准确的对象跟踪。 Siamvgg的体系结构是根据VGG-16自定义的,其参数由示例性图像和所需的输入视频帧共享。我们在OTB-2013/50/100和Dot 2015/2016/2017数据集中证明了拟议的暹罗,具有STATE-ORT-TEA-ART精度,同时保持在GTX 1080TI上运行的50 FPS的体面实时性能。与Dot2017挑战中的ECO和C-COT相比,我们的设计可以实现预期平均重叠(EAO)的预期平均重叠(EAO)。
translated by 谷歌翻译
周等人提出了一个无人监督,轻质和高性能的单一对象追踪器,称为UHP-SOT。最近。作为一个扩展,我们在这项工作中介绍了一个增强版本并将其命名为UHP-SOT ++。基于基于鉴别相关滤波器的(基于DCF的)跟踪器的基础,在UHP-SOT和UHP-SOT ++中引入了两种新成分:1)背景运动建模和2)对象盒轨迹建模。 UHP-SOT和UHP-SOT ++之间的主要区别是来自三种模型的提案的融合策略(即DCF,背景运动和对象盒轨迹模型)。 UHP-SOT ++采用了一种改进的融合策略,可针对大规模跟踪数据集更加强大的跟踪性能。我们的第二件贡献在于通过在四个SOT基准数据集 - OTB2015,TC128,UAV123和LASOT上进行测试,对最先进的监督和无监督方法进行了广泛的评估。实验表明,UHP-SOT ++优于所有先前的无监督方法和几种深度学习(DL)方法,以跟踪准确性。由于UHP-SOT ++具有极小的模型大小,高跟踪性能和低计算复杂性(即使在I5 CPU上以20 fps运行,即使没有代码优化),则是资源实时对象跟踪中的理想解决方案 - 有限平台。基于实验结果,我们比较监督和无监督者的优缺点,并提供了一种新的视角,了解监督和无监督方法之间的性能差距,这是这项工作的第三次贡献。
translated by 谷歌翻译