过去一年中，有几种基于Segment Anything Model 2（SAM2）的对象跟踪管道被提出，其方法是根据用户提供的初始帧中的单个示例模板来跟踪和分割目标。我们提出将这些高性能跟踪器（SAM2、EfficientTAM、DAM4SAM和SAMURAI）在包含快速移动对象（FMO）的数据集上进行基准测试，这些数据集专门设计为对跟踪方法具有挑战性。目标是通过提供这些跟踪器行为的更详细见解，更好地理解当前最先进的跟踪器的局限性。我们展示整体而言，DAM4SAM和SAMURAI在更具挑战性的序列上表现较好。
英文摘要：
Several object tracking pipelines extending Segment Anything Model 2 (SAM2) have been proposed in the past year, where the approach is to follow and segment the object from a single exemplar template provided by the user on a initialization frame. We propose to benchmark these high performing trackers (SAM2, EfficientTAM, DAM4SAM and SAMURAI) on datasets containing fast moving objects (FMO) specifically designed to be challenging for tracking approaches. The goal is to understand better current limitations in state-of-the-art trackers by providing more detailed insights on the behavior of these trackers. We show that overall the trackers DAM4SAM and SAMURAI perform well on more challenging sequences.
In recent years, deep learning-based visual object trackers have achieved state-of-the-art performance on several visual object tracking benchmarks. However, most tracking benchmarks are focused on ground level videos, whereas aerial tracking presents a new set of challenges. In this paper, we compare ten trackers based on deep learning techniques on four aerial datasets. We choose top performing trackers utilizing different approaches, specifically tracking by detection, discriminative correlation filters, Siamese networks and reinforcement learning. In our experiments, we use a subset of OTB…
Multi-object tracking (MOT) has been dominated by the use of track by detection approaches due to the success of convolutional neural networks (CNNs) on detection in the last decade. As the datasets and bench-marking sites are published, research direction has shifted towards yielding best accuracy on generic scenarios including re-identification (reID) of objects while tracking. In this study, we narrow the scope of MOT for surveillance by providing a dedicated dataset of pedestrians and focus on in-depth analyses of well performing multi-object trackers to observe the weak and strong sides o…
Benchmarking Microsaccade Recognition with Event Cameras: A Novel Dataset and Evaluation
C3I Imaging Lab, School of Engineering, University of Galway, Ireland（C3I成像实验室，工程学院，Galway大学，爱尔兰）；School of Computer Science, University of Galway, Ireland（计算机科学学院，Galway大学，爱尔兰）；Department of Electronic and Electrical Engineering, Trinity College Dublin, Ireland（电子与电气工程系，Trinity College Dublin大学，爱尔兰）
SurgT challenge: Benchmark of Soft-Tissue Trackers for Robotic Surgery
Imperial College London（伦敦帝国理工学院）；Jmees（Jmees公司）；Electronics and Telecommunications Research Institute (ETRI)（电子通信研究院）；Ajou University（亚洲大学）；University of Toronto（多伦多大学）；University College London（伦敦大学学院）
Current multi-category Multiple Object Tracking (MOT) metrics use class labels to group tracking results for per-class evaluation. Similarly, MOT methods typically only associate objects with the same class predictions. These two prevalent strategies in MOT implicitly assume that the classification performance is near-perfect. However, this is far from the case in recent large-scale MOT datasets, which contain large numbers of classes with many rare or semantically similar categories. Therefore, the resulting inaccurate classification leads to sub-optimal tracking and inadequate benchmarking o…
University of Surrey（萨里大学）；Jiangnan University（江南大学）
Siamese approaches have achieved promising performance in visual object tracking recently. The key to the success of Siamese trackers is to learn appearance-invariant feature embedding functions via pair-wise offline training on large-scale video datasets. However, the Siamese paradigm uses one-shot learning to model the online tracking task, which impedes online adaptation in the tracking process. Additionally, the uncertainty of an online tracking response is not measured, leading to the problem of ignoring potential failures. In this paper, we advocate online adaptation in the tracking stag…
Jiangnan University（江南大学）；University of Surrey（萨里大学）
Recent visual object tracking methods have witnessed a continuous improvement in the state-of-the-art with the development of efficient discriminative correlation filters (DCF) and robust deep neural network features. Despite the outstanding performance achieved by the above combination, existing advanced trackers suffer from the burden of high computational complexity of the deep feature extraction and online model learning. We propose an accelerated ADMM optimisation method obtained by adding a momentum to the optimisation sequence iterates, and by relaxing the impact of the error between DC…
This paper presents a new algorithm to track mobile objects in different scene conditions. The main idea of the proposed tracker includes estimation, multi-features similarity measures and trajectory filtering. A feature set (distance, area, shape ratio, color histogram) is defined for each tracked object to search for the best matching object. Its best matching object and its state estimated by the Kalman filter are combined to update position and size of the tracked object. However, the mobile object trajectories are usually fragmented because of occlusions and misdetections. Therefore, we a…
University of Ljubljana（卢布尔雅那大学）；Czech Technical University in Prague（布拉格捷克理工大学）
We propose a new long-term tracking performance evaluation methodology and present a new challenging dataset of carefully selected sequences with many target disappearances. We perform an extensive evaluation of six long-term and nine short-term state-of-the-art trackers, using new performance measures, suitable for evaluating long-term tracking - tracking precision, recall and F-score. The evaluation shows that a good model update strategy and the capability of image-wide re-detection are critical for long-term tracking performance. We integrated the methodology in the VOT toolkit to automate…
University of Ljubljana（卢布尔雅那大学）；Tampere University（坦佩雷大学）；Czech Technical University in Prague（捷克布拉格技术大学）
A long-term visual object tracking performance evaluation methodology and a benchmark are proposed. Performance measures are designed by following a long-term tracking definition to maximize the analysis probing strength. The new measures outperform existing ones in interpretation potential and in better distinguishing between different tracking behaviors. We show that these measures generalize the short-term performance measures, thus linking the two tracking problems. Furthermore, the new measures are highly robust to temporal annotation sparsity and allow annotation of sequences hundreds of…
Czech Technical University in Prague（捷克技术大学）；University of Ljubljana（卢布尔雅那大学）
A long-term visual object tracking performance evaluation methodology and a benchmark are proposed. Performance measures are designed by following a long-term tracking definition to maximize the analysis probing strength. The new measures outperform existing ones in interpretation potential and in better distinguishing between different tracking behaviors. We show that these measures generalize the short-term performance measures, thus linking the two tracking problems. Furthermore, the new measures are highly robust to temporal annotation sparsity and allow annotation of sequences hundreds of…
We introduce a tracking-by-detection method that integrates a deep object detector with a particle filter tracker under the regularization framework where the tracked object is represented by a sparse dictionary. A novel observation model which establishes consensus between the detector and tracker is formulated that enables us to update the dictionary with the guidance of the deep detector. This yields an efficient representation of the object appearance through the video sequence hence improves robustness to occlusion and pose changes. Moreover we propose a new state vector consisting of tra…
Rotation is among the long prevailing, yet still unresolved, hard challenges encountered in visual object tracking. The existing deep learning-based tracking algorithms use regular CNNs that are inherently translation equivariant, but not designed to tackle rotations. In this paper, we first demonstrate that in the presence of rotation instances in videos, the performance of existing trackers is severely affected. To circumvent the adverse effect of rotations, we present rotation-equivariant Siamese networks (RE-SiamNets), built through the use of group-equivariant convolutional layers compris…
