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
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
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
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
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
我们介绍了一个基于仅用于跟踪的变压器的暹罗样的双分支网络。给定模板和搜索映像,我们将它们分成非重叠补丁,并基于其在注意窗口中的其他人的匹配结果提取每个补丁的特征向量。对于每个令牌,我们估计它是否包含目标对象和相应的大小。该方法的优点是,该特征从匹配中学到,最终匹配。因此,功能与目标跟踪任务对齐。该方法实现更好或比较的结果作为首先使用CNN提取特征的最佳性能,然后使用变压器熔断它们。它优于GOT-10K和VOT2020基准上的最先进的方法。此外,该方法在一个GPU上实现了实时推理速度(约为40美元的FPS)。代码和模型将被释放。
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
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 popular two-stream, two-stage tracking framework extracts the template and the search region features separately and then performs relation modeling, thus the extracted features lack the awareness of the target and have limited target-background discriminability. To tackle the above issue, we propose a novel one-stream tracking (OSTrack) framework that unifies feature learning and relation modeling by bridging the template-search image pairs with bidirectional information flows. In this way, discriminative target-oriented features can be dynamically extracted by mutual guidance. Since no extra heavy relation modeling module is needed and the implementation is highly parallelized, the proposed tracker runs at a fast speed. To further improve the inference efficiency, an in-network candidate early elimination module is proposed based on the strong similarity prior calculated in the one-stream framework. As a unified framework, OSTrack achieves state-of-the-art performance on multiple benchmarks, in particular, it shows impressive results on the one-shot tracking benchmark GOT-10k, i.e., achieving 73.7% AO, improving the existing best result (SwinTrack) by 4.3\%. Besides, our method maintains a good performance-speed trade-off and shows faster convergence. The code and models are available at https://github.com/botaoye/OSTrack.
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
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
最近的跟踪器采用变压器来组合或替换广泛使用的重新NET作为其新的骨干网络。尽管他们的跟踪器在常规场景中运行良好,但是他们只是将2D功能弄平为序列,以更好地匹配变压器。我们认为这些操作忽略了目标对象的空间先验,这可能仅导致次优结果。此外,许多作品表明,自我注意力实际上是一个低通滤波器,它与输入功能或键/查询无关。也就是说,它可能会抑制输入功能的高频组成部分,并保留甚至放大低频信息。为了解决这些问题,在本文中,我们提出了一个统一的空间频率变压器,该变压器同时建模高斯空间先验和高频强调(GPHA)。具体而言,高斯空间先验是使用双重多层感知器(MLP)生成的,并注入了通过将查询和自我注意的关键特征乘产生的相似性矩阵。输出将被馈入软磁层,然后分解为两个组件,即直接信号和高频信号。低通和高通的分支被重新缩放并组合以实现全通,因此,高频特征将在堆叠的自发层中得到很好的保护。我们进一步将空间频率变压器整合到暹罗跟踪框架中,并提出一种新颖的跟踪算法,称为SFTRANST。基于跨级融合的SwintransFormer被用作骨干,还使用多头交叉意见模块来增强搜索和模板功能之间的相互作用。输出将被馈入跟踪头以进行目标定位。短期和长期跟踪基准的广泛实验都证明了我们提出的框架的有效性。
translated by 谷歌翻译
变压器最近展示了改进视觉跟踪算法的明显潜力。尽管如此,基于变压器的跟踪器主要使用变压器熔断并增强由卷积神经网络(CNNS)产生的功能。相比之下,在本文中,我们提出了一个完全基于注意力的变压器跟踪算法,Swin-Cranstormer Tracker(SwintRack)。 SwintRack使用变压器进行特征提取和特征融合,允许目标对象和搜索区域之间的完全交互进行跟踪。为了进一步提高性能,我们调查了全面的不同策略,用于特征融合,位置编码和培训损失。所有这些努力都使SwintRack成为一个简单但坚实的基线。在我们的彻底实验中,SwintRack在leasot上设置了一个新的记录,在4.6 \%的情况下超过4.6 \%,同时仍然以45 fps运行。此外,它达到了最先进的表演,0.483 Suc,0.832 Suc和0.694 Ao,其他具有挑战性的leasot _ {ext} $,trackingnet和got-10k。我们的实施和培训型号可在HTTPS://github.com/litinglin/swintrack获得。
translated by 谷歌翻译
最近,基于模板的跟踪器已成为领先的跟踪算法,在效率和准确性方面具有希望的性能。然而,查询特征与给定模板之间的相关操作仅利用准确的目标本地化,导致状态估计误差,特别是当目标遭受严重可变形变化时。为了解决这个问题,已经提出了基于分段的跟踪器,以便使用每像素匹配来有效地提高可变形物体的跟踪性能。然而,大多数现有跟踪器仅指初始帧中的目标特征,从而缺乏处理具有挑战性因素的辨别能力,例如,类似的分心,背景杂乱,外观变化等。在此目的,我们提出了一种动态的紧凑型存储器嵌入以增强基于分段的可变形视觉跟踪方法的辨别。具体而言,我们初始化与第一帧中的目标功能嵌入的内存嵌入。在跟踪过程中,与现有内存具有高相关的当前目标特征被更新为在线嵌入的内存。为了进一步提高可变形对象的分割精度,我们采用了点对集的匹配策略来测量像素 - 方向查询特征和整个模板之间的相关性,以捕获更详细的变形信息。关于六个具有挑战性的跟踪基准的广泛评估,包括VOT2016,VOT2018,VOT2019,GOT-10K,TrackingNet和莱斯特展示了我们对近期近似追踪者的方法的优势。此外,我们的方法优于基于出色的基于分段的跟踪器,即DVIS2017基准测试。
translated by 谷歌翻译
已经提出了高效和自适应计算机视觉系统以使计算机视觉任务,例如图像分类和对象检测,针对嵌入或移动设备进行了优化。这些解决方案最近的起源,专注于通过设计具有近似旋钮的自适应系统来优化模型(深神经网络,DNN)或系统。尽管最近的几项努力,但我们表明现有解决方案遭受了两个主要缺点。首先,系统不考虑模型的能量消耗,同时在制定要运行的模型的决定时。其次,由于其他共同居民工作负载,评估不考虑设备上的争用的实际情况。在这项工作中,我们提出了一种高效和自适应的视频对象检测系统,这是联合优化的精度,能量效率和延迟。底层Virtuoso是一个多分支执行内核,它能够在精度 - 能量 - 延迟轴上的不同运行点处运行,以及轻量级运行时调度程序,以选择最佳的执行分支以满足用户要求。要与Virtuoso相当比较,我们基准于15件最先进的或广泛使用的协议,包括更快的R-CNN(FRCNN),YOLO V3,SSD,培训台,SELSA,MEGA,REPP,FastAdapt和我们的内部FRCNN +,YOLO +,SSD +和高效+(我们的变体具有增强的手机效率)的自适应变体。通过这种全面的基准,Virtuoso对所有上述协议显示出优势,在NVIDIA Jetson Mobile GPU上的每一项效率水平上引领精度边界。具体而言,Virtuoso的准确性为63.9%,比一些流行的物体检测模型高于10%,51.1%,yolo为49.5%。
translated by 谷歌翻译
深神网络的对象探测器正在不断发展,并用于多种应用程序,每个应用程序都有自己的要求集。尽管关键安全应用需要高准确性和可靠性,但低延迟任务需要资源和节能网络。不断提出了实时探测器,在高影响现实世界中是必需的,但是它们过分强调了准确性和速度的提高,而其他功能(例如多功能性,鲁棒性,资源和能源效率)则被省略。现有网络的参考基准不存在,设计新网络的标准评估指南也不存在,从而导致比较模棱两可和不一致的比较。因此,我们对广泛的数据集进行了多个实时探测器(基于锚点,关键器和变压器)的全面研究,并报告了一系列广泛指标的结果。我们还研究了变量,例如图像大小,锚固尺寸,置信阈值和架构层对整体性能的影响。我们分析了检测网络的鲁棒性,以防止分配变化,自然腐败和对抗性攻击。此外,我们提供了校准分析来评估预测的可靠性。最后,为了强调现实世界的影响,我们对自动驾驶和医疗保健应用进行了两个独特的案例研究。为了进一步衡量关键实时应用程序中网络的能力,我们报告了在Edge设备上部署检测网络后的性能。我们广泛的实证研究可以作为工业界对现有网络做出明智选择的指南。我们还希望激发研究社区的设计和评估网络的新方向,该网络着重于更大而整体的概述,以实现深远的影响。
translated by 谷歌翻译
变压器跟踪器最近取得了令人印象深刻的进步,注意力机制起着重要作用。但是,注意机制的独立相关计算可能导致嘈杂和模棱两可的注意力重量,从而抑制了进一步的性能改善。为了解决这个问题,我们提出了注意力(AIA)模块,该模块通过在所有相关向量之间寻求共识来增强适当的相关性并抑制错误的相关性。我们的AIA模块可以很容易地应用于自我注意解区和交叉注意区块,以促进特征聚集和信息传播以进行视觉跟踪。此外,我们通过引入有效的功能重复使用和目标背景嵌入来充分利用时间参考,提出了一个流线型的变压器跟踪框架,称为AIATRACK。实验表明,我们的跟踪器以实时速度运行时在六个跟踪基准测试中实现最先进的性能。
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
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
我们提出了一种称为独角兽的统一方法,可以使用相同的模型参数同时使用单个网络解决四个跟踪问题(SOT,MOT,VOS,MOTS)。由于对象跟踪问题本身的定义零散,因此开发了大多数现有的跟踪器来解决任务的单个或一部分,并过分地对特定任务的特征进行了专业化。相比之下,Unicorn提供了一个统一的解决方案,在所有跟踪任务中采用相同的输入,骨干,嵌入和头部。我们第一次完成了跟踪网络体系结构和学习范式的巨大统一。Unicorn在8个跟踪数据集中的特定于任务特定的对应物(包括Lasot,TrackingNet,Mot17,BDD100K,Davis16-17,MOTS20和BDD100K MOT)在PAR上或更好的对应物。我们认为,独角兽将是朝着一般视觉模型迈出的坚实一步。代码可从https://github.com/masterbin-iiau/unicorn获得。
translated by 谷歌翻译