没有全面的指标来描述多对象跟踪(MOT)序列的复杂性。缺乏指标可降低解释性,使数据集的比较变得复杂,并将跟踪器绩效的对话降低到排行榜位置的问题。作为一种补救措施,我们介绍了新型的MOT数据集复杂度度量(MOTCOM),该度量是由MOT中的关键问题启发的三个子计量学的组合:闭塞,运动不稳定和视觉相似性。MOTCOM的见解可以开放有关跟踪器性能的细微讨论,并可能导致对鲜为人知的数据集或旨在解决子问题的新颖贡献的更广泛认可。我们在综合MOT17,MOT20和Motsynth数据集上评估了MOTCOM,并表明MOTCOM在描述与传统密度和轨道数量相比描述MOT序列的复杂性要好得多。项目页面https://vap.aau.dk/motcom
translated by 谷歌翻译
长期以来,多对象跟踪中最常见的范式是逐个检测(TBD),首先检测到对象,然后通过视频帧关联。对于关联,大多数模型用于运动和外观提示。尽管仍然依靠这些提示,但最新的方法(例如,注意力)表明对训练数据和整体复杂框架的需求不断增加。我们声称1)如果采用某些关键的设计选择,可以从很少的培训数据中获得强大的提示,2)鉴于这些强大的提示,标准的基于匈牙利匹配的关联足以获得令人印象深刻的结果。我们的主要见解是确定允许标准重新识别网络在基于外观的跟踪方面表现出色的关键组件。我们广泛地分析了其故障案例,并表明我们的外观特征与简单运动模型的结合导致了强大的跟踪结果。我们的模型在MOT17和MOT20数据集上实现了最新的性能,在IDF1中最多可超过5.4pp,在IDF1和HOTA中的4.4pp优于先前的最新跟踪器。我们将在本文接受后发布代码和模型。
translated by 谷歌翻译
The problem of tracking multiple objects in a video sequence poses several challenging tasks. For tracking-bydetection, these include object re-identification, motion prediction and dealing with occlusions. We present a tracker (without bells and whistles) that accomplishes tracking without specifically targeting any of these tasks, in particular, we perform no training or optimization on tracking data. To this end, we exploit the bounding box regression of an object detector to predict the position of an object in the next frame, thereby converting a detector into a Tracktor. We demonstrate the potential of Tracktor and provide a new state-of-the-art on three multi-object tracking benchmarks by extending it with a straightforward re-identification and camera motion compensation.We then perform an analysis on the performance and failure cases of several state-of-the-art tracking methods in comparison to our Tracktor. Surprisingly, none of the dedicated tracking methods are considerably better in dealing with complex tracking scenarios, namely, small and occluded objects or missing detections. However, our approach tackles most of the easy tracking scenarios. Therefore, we motivate our approach as a new tracking paradigm and point out promising future research directions. Overall, Tracktor yields superior tracking performance than any current tracking method and our analysis exposes remaining and unsolved tracking challenges to inspire future research directions.
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
多对象跟踪(MOT)的目标是检测和跟踪场景中的所有对象,同时为每个对象保留唯一的标识符。在本文中,我们提出了一种新的可靠的最新跟踪器,该跟踪器可以结合运动和外观信息的优势,以及摄像机运动补偿以及更准确的Kalman滤波器状态矢量。我们的新跟踪器在Mot17和Mot20测试集的Motchallenge [29,11]的数据集[29,11]中,Bot-Sort-Reid排名第一,就所有主要MOT指标而言:MOTA,IDF1和HOTA。对于Mot17:80.5 Mota,80.2 IDF1和65.0 HOTA。源代码和预培训模型可在https://github.com/niraharon/bot-sort上找到
translated by 谷歌翻译
多目标跟踪(MOT)的典型管道是使用探测器进行对象本地化,并在重新识别(RE-ID)之后进行对象关联。该管道通过对象检测和重新ID的最近进展部分而部分地激励,并且部分地通过现有的跟踪数据集中的偏差激励,其中大多数物体倾向于具有区分外观和RE-ID模型足以建立关联。为了响应这种偏见,我们希望重新强调多目标跟踪的方法也应该在对象外观不充分辨别时起作用。为此,我们提出了一个大型数据集,用于多人跟踪,人类具有相似的外观,多样化的运动和极端关节。由于数据集包含主要组跳舞视频,我们将其命名为“DanceTrack”。我们预计DanceTrack可以提供更好的平台,以开发更多的MOT算法,这些算法依赖于视觉识别并更依赖于运动分析。在我们的数据集上,我们在数据集上基准测试了几个最先进的追踪器,并在与现有基准测试中遵守DanceTrack的显着性能下降。 DataSet,项目代码和竞争服务器播放:\ url {https://github.com/danceTrack}。
translated by 谷歌翻译
近年来,多个对象跟踪引起了研究人员的极大兴趣,它已成为计算机视觉中的趋势问题之一,尤其是随着自动驾驶的最新发展。 MOT是针对不同问题的关键视觉任务之一,例如拥挤的场景中的闭塞,相似的外观,小物体检测难度,ID切换等,以应对这些挑战,因为研究人员试图利用变压器的注意力机制,与田径的相互关系,与田径的相互关系,图形卷积神经网络,与暹罗网络不同帧中对象的外观相似性,他们还尝试了基于IOU匹配的CNN网络,使用LSTM的运动预测。为了将这些零散的技术在雨伞下采用,我们研究了过去三年发表的一百多篇论文,并试图提取近代研究人员更关注的技术来解决MOT的问题。我们已经征集了许多应用,可能性以及MOT如何与现实生活有关。我们的评论试图展示研究人员使用过时的技术的不同观点,并为潜在的研究人员提供了一些未来的方向。此外,我们在这篇评论中包括了流行的基准数据集和指标。
translated by 谷歌翻译
由于卷积神经网络(CNN)在过去的十年中检测成功,多对象跟踪(MOT)通过检测方法的使用来控制。随着数据集和基础标记网站的发布,研究方向已转向在跟踪时在包括重新识别对象的通用场景(包括重新识别(REID))上的最佳准确性。在这项研究中,我们通过提供专用的行人数据集并专注于对性能良好的多对象跟踪器的深入分析来缩小监视的范围)现实世界应用的技术。为此,我们介绍SOMPT22数据集;一套新的,用于多人跟踪的新套装,带有带注释的简短视频,该视频从位于杆子上的静态摄像头捕获,高度为6-8米,用于城市监视。与公共MOT数据集相比,这提供了室外监视的MOT的更为集中和具体的基准。我们分析了该新数据集上检测和REID网络的使用方式,分析了将MOT跟踪器分类为单发和两阶段。我们新数据集的实验结果表明,SOTA远非高效率,而单一跟踪器是统一快速执行和准确性的良好候选者,并具有竞争性的性能。该数据集将在以下网址提供:sompt22.github.io
translated by 谷歌翻译
多摄像机多对象跟踪目前在计算机视野中引起了注意力,因为它在现实世界应用中的卓越性能,如具有拥挤场景或巨大空间的视频监控。在这项工作中,我们提出了一种基于空间升降的多乳制型配方的数学上优雅的多摄像多对象跟踪方法。我们的模型利用单摄像头跟踪器产生的最先进的TOOTWLET作为提案。由于这些Tracklet可能包含ID-Switch错误,因此我们通过从3D几何投影获得的新型预簇来完善它们。因此,我们派生了更好的跟踪图,没有ID交换机,更精确的数据关联阶段的亲和力成本。然后通过求解全局提升的多乳制型制剂,将轨迹与多摄像机轨迹匹配,该组件包含位于同一相机和相互相机间的Tracklet上的短路和远程时间交互。在Wildtrack DataSet的实验结果是近乎完美的结果,在校园上表现出最先进的追踪器,同时在PETS-09数据集上处于校准状态。我们将在接受纸质时进行我们的实施。
translated by 谷歌翻译
3D多对象跟踪(MOT)确保在连续动态检测过程中保持一致性,有利于自动驾驶中随后的运动计划和导航任务。但是,基于摄像头的方法在闭塞情况下受到影响,准确跟踪基于激光雷达的方法的对象的不规则运动可能是具有挑战性的。某些融合方法效果很好,但不认为在遮挡下出现外观特征的不可信问题。同时,错误检测问题也显着影响跟踪。因此,我们根据组合的外观运动优化(Camo-Mot)提出了一种新颖的相机融合3D MOT框架,该框架使用相机和激光镜数据,并大大减少了由遮挡和错误检测引起的跟踪故障。对于遮挡问题,我们是第一个提出遮挡头来有效地选择最佳对象外观的人,从而减少了闭塞的影响。为了减少错误检测在跟踪中的影响,我们根据置信得分设计一个运动成本矩阵,从而提高了3D空间中的定位和对象预测准确性。由于现有的多目标跟踪方法仅考虑一个类别,因此我们还建议建立多类损失,以在多类别场景中实现多目标跟踪。在Kitti和Nuscenes跟踪基准测试上进行了一系列验证实验。我们提出的方法在KITTI测试数据集上的所有多模式MOT方法中实现了最先进的性能和最低的身份开关(IDS)值(CAR为23,行人为137)。并且我们提出的方法在Nuscenes测试数据集上以75.3%的AMOTA进行了所有算法中的最新性能。
translated by 谷歌翻译
卫星摄像机可以为大型区域提供连续观察,这对于许多遥感应用很重要。然而,由于对象的外观信息不足和缺乏高质量数据集,在卫星视频中实现移动对象检测和跟踪仍然具有挑战性。在本文中,我们首先构建一个具有丰富注释的大型卫星视频数据集,用于移动对象检测和跟踪的任务。该数据集由Jilin-1卫星星座收集,并由47个高质量视频组成,对象检测有1,646,038兴趣的情况和用于对象跟踪的3,711个轨迹。然后,我们引入运动建模基线,以提高检测速率并基于累积多帧差异和鲁棒矩阵完成来减少误报。最后,我们建立了第一个用于在卫星视频中移动对象检测和跟踪的公共基准,并广泛地评估在我们数据集上几种代表方法的性能。还提供了综合实验分析和富有魅力的结论。数据集可在https://github.com/qingyonghu/viso提供。
translated by 谷歌翻译
跟踪视频感兴趣的对象是计算机视觉中最受欢迎和最广泛应用的问题之一。然而,随着年的几年,寒武纪的用例和基准已经将问题分散在多种不同的实验设置中。因此,文献也已经分散,现在社区提出的新方法通常是专门用于仅适合一个特定的设置。要了解在多大程度上,这项专业化是必要的,在这项工作中,我们展示了UnitRack,一个解决方案来解决同一框架内的五个不同任务。 Unitrack由单一和任务不可知的外观模型组成,可以以监督或自我监督的方式学习,以及解决个人任务的多个`“头”,并且不需要培训。我们展示了在该框架内可以解决的大多数跟踪任务,并且可以成功地成功地使用相同的外观模型来获得对针对考虑大多数任务的专业方法具有竞争力的结果。该框架还允许我们分析具有最新自我监督方法获得的外观模型,从而扩展了他们的评估并与更大种类的重要问题进行比较。
translated by 谷歌翻译
Tracking has traditionally been the art of following interest points through space and time. This changed with the rise of powerful deep networks. Nowadays, tracking is dominated by pipelines that perform object detection followed by temporal association, also known as tracking-by-detection. We present a simultaneous detection and tracking algorithm that is simpler, faster, and more accurate than the state of the art. Our tracker, CenterTrack, applies a detection model to a pair of images and detections from the prior frame. Given this minimal input, CenterTrack localizes objects and predicts their associations with the previous frame. That's it. CenterTrack is simple, online (no peeking into the future), and real-time. It achieves 67.8% MOTA on the MOT17 challenge at 22 FPS and 89.4% MOTA on the KITTI tracking benchmark at 15 FPS, setting a new state of the art on both datasets. CenterTrack is easily extended to monocular 3D tracking by regressing additional 3D attributes. Using monocular video input, it achieves 28.3% AMOTA@0.2 on the newly released nuScenes 3D tracking benchmark, substantially outperforming the monocular baseline on this benchmark while running at 28 FPS.
translated by 谷歌翻译
How would you fairly evaluate two multi-object tracking algorithms (i.e. trackers), each one employing a different object detector? Detectors keep improving, thus trackers can make less effort to estimate object states over time. Is it then fair to compare a new tracker employing a new detector with another tracker using an old detector? In this paper, we propose a novel performance measure, named Tracking Effort Measure (TEM), to evaluate trackers that use different detectors. TEM estimates the improvement that the tracker does with respect to its input data (i.e. detections) at frame level (intra-frame complexity) and sequence level (inter-frame complexity). We evaluate TEM over well-known datasets, four trackers and eight detection sets. Results show that, unlike conventional tracking evaluation measures, TEM can quantify the effort done by the tracker with a reduced correlation on the input detections. Its implementation is publicly available online at https://github.com/vpulab/MOT-evaluation.
translated by 谷歌翻译
This paper presents a new large scale multi-person tracking dataset -- \texttt{PersonPath22}, which is over an order of magnitude larger than currently available high quality multi-object tracking datasets such as MOT17, HiEve, and MOT20 datasets. The lack of large scale training and test data for this task has limited the community's ability to understand the performance of their tracking systems on a wide range of scenarios and conditions such as variations in person density, actions being performed, weather, and time of day. \texttt{PersonPath22} dataset was specifically sourced to provide a wide variety of these conditions and our annotations include rich meta-data such that the performance of a tracker can be evaluated along these different dimensions. The lack of training data has also limited the ability to perform end-to-end training of tracking systems. As such, the highest performing tracking systems all rely on strong detectors trained on external image datasets. We hope that the release of this dataset will enable new lines of research that take advantage of large scale video based training data.
translated by 谷歌翻译
本文旨在解决多个对象跟踪(MOT),这是计算机视觉中的一个重要问题,但由于许多实际问题,尤其是阻塞,因此仍然具有挑战性。确实,我们提出了一种新的实时深度透视图 - 了解多个对象跟踪(DP-MOT)方法,以解决MOT中的闭塞问题。首先提出了一个简单但有效的主题深度估计(SODE),以在2D场景中自动以无监督的方式自动订购检测到的受试者的深度位置。使用SODE的输出,提出了一个新的活动伪3D KALMAN滤波器,即具有动态控制变量的Kalman滤波器的简单但有效的扩展,以动态更新对象的运动。此外,在数据关联步骤中提出了一种新的高阶关联方法,以合并检测到的对象之间的一阶和二阶关系。与标准MOT基准的最新MOT方法相比,提出的方法始终达到最先进的性能。
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
Accurate representation and localization of relevant objects is important for robots to perform tasks. Building a generic representation that can be used across different environments and tasks is not easy, as the relevant objects vary depending on the environment and the task. Furthermore, another challenge arises in agro-food environments due to their complexity, and high levels of clutter and occlusions. In this paper, we present a method to build generic representations in highly occluded agro-food environments using multi-view perception and 3D multi-object tracking. Our representation is built upon a detection algorithm that generates a partial point cloud for each detected object. The detected objects are then passed to a 3D multi-object tracking algorithm that creates and updates the representation over time. The whole process is performed at a rate of 10 Hz. We evaluated the accuracy of the representation on a real-world agro-food environment, where it was able to successfully represent and locate tomatoes in tomato plants despite a high level of occlusion. We were able to estimate the total count of tomatoes with a maximum error of 5.08% and to track tomatoes with a tracking accuracy up to 71.47%. Additionally, we showed that an evaluation using tracking metrics gives more insight in the errors in localizing and representing the fruits.
translated by 谷歌翻译
This paper explores a pragmatic approach to multiple object tracking where the main focus is to associate objects efficiently for online and realtime applications. To this end, detection quality is identified as a key factor influencing tracking performance, where changing the detector can improve tracking by up to 18.9%. Despite only using a rudimentary combination of familiar techniques such as the Kalman Filter and Hungarian algorithm for the tracking components, this approach achieves an accuracy comparable to state-of-the-art online trackers. Furthermore, due to the simplicity of our tracking method, the tracker updates at a rate of 260 Hz which is over 20x faster than other state-of-the-art trackers.
translated by 谷歌翻译
Figure 1: We introduce datasets for 3D tracking and motion forecasting with rich maps for autonomous driving. Our 3D tracking dataset contains sequences of LiDAR measurements, 360 • RGB video, front-facing stereo (middle-right), and 6-dof localization. All sequences are aligned with maps containing lane center lines (magenta), driveable region (orange), and ground height. Sequences are annotated with 3D cuboid tracks (green). A wider map view is shown in the bottom-right.
translated by 谷歌翻译