Modern online multiple object tracking (MOT) methods usually focus on two directions to improve tracking performance. One is to predict new positions in an incoming frame based on tracking information from previous frames, and the other is to enhance data association by generating more discriminative identity embeddings. Some works combined both directions within one framework but handled them as two individual tasks, thus gaining little mutual benefits. In this paper, we propose a novel unified model with synergy between position prediction and embedding association. The two tasks are linked by temporal-aware target attention and distractor attention, as well as identity-aware memory aggregation model. Specifically, the attention modules can make the prediction focus more on targets and less on distractors, therefore more reliable embeddings can be extracted accordingly for association. On the other hand, such reliable embeddings can boost identity-awareness through memory aggregation, hence strengthen attention modules and suppress drifts. In this way, the synergy between position prediction and embedding association is achieved, which leads to strong robustness to occlusions. Extensive experiments demonstrate the superiority of our proposed model over a wide range of existing methods on MOTChallenge benchmarks. Our code and models are publicly available at https://github.com/songguocode/TADAM.
Learning a good representation for space-time correspondence is the key for various computer vision tasks, including tracking object bounding boxes and performing video object pixel segmentation. To learn generalizable representation for correspondence in large-scale, a variety of self-supervised pretext tasks are proposed to explicitly perform object-level or patch-level similarity learning. Instead of following the previous literature, we propose to learn correspondence using Video Frame-level Similarity (VFS) learning, i.e, simply learning from comparing video frames. Our work is inspired by the recent success in image-level contrastive learning and similarity learning for visual recognition. Our hypothesis is that if the representation is good for recognition, it requires the convolutional features to find correspondence between similar objects or parts. Our experiments show surprising results that VFS surpasses state-of-the-art self-supervised approaches for both OTB visual object tracking and DAVIS video object segmentation. We perform detailed analysis on what matters in VFS and reveals new properties on image and frame level similarity learning. Project page with code is available at https://jerryxu.net/VFS
Tracking by natural language specification is a new rising research topic that aims at locating the target object in the video sequence based on its language description. Compared with traditional bounding box (BBox) based tracking, this setting guides object tracking with high-level semantic information, addresses the ambiguity of BBox, and links local and global search organically together. Those benefits may bring more flexible, robust and accurate tracking performance in practical scenarios. However, existing natural language initialized trackers are developed and compared on benchmark datasets proposed for tracking-by-BBox, which can't reflect the true power of tracking-by-language. In this work, we propose a new benchmark specifically dedicated to the tracking-by-language, including a large scale dataset, strong and diverse baseline methods. Specifically, we collect 2k video sequences (contains a total of 1,244,340 frames, 663 words) and split 1300/700 for the train/testing respectively. We densely annotate one sentence in English and corresponding bounding boxes of the target object for each video. We also introduce two new challenges into TNL2K for the object tracking task, i.e., adversarial samples and modality switch. A strong baseline method based on an adaptive local-global-search scheme is proposed for future works to compare. We believe this benchmark will greatly boost related researches on natural language guided tracking.
In this paper, we present a new tracking architecture with an encoder-decoder transformer as the key component. The encoder models the global spatio-temporal feature dependencies between target objects and search regions, while the decoder learns a query embedding to predict the spatial positions of the target objects. Our method casts object tracking as a direct bounding box prediction problem, without using any proposals or predefined anchors. With the encoder-decoder transformer, the prediction of objects just uses a simple fully-convolutional network, which estimates the corners of objects directly. The whole method is end-to-end, does not need any postprocessing steps such as cosine window and bounding box smoothing, thus largely simplifying existing tracking pipelines. The proposed tracker achieves state-of-the-art performance on five challenging short-term and long-term benchmarks, while running at real-time speed, being 6x faster than Siam R-CNN. Code and models are open-sourced at https://github.com/researchmm/Stark.
Data association across frames is at the core of Multiple Object Tracking (MOT) task. This problem is usually solved by a traditional graph-based optimization or directly learned via deep learning. Despite their popularity, we find some points worth studying in current paradigm: 1) Existing methods mostly ignore the context information among tracklets and intra-frame detections, which makes the tracker hard to survive in challenging cases like severe occlusion. 2) The end-to-end association methods solely rely on the data fitting power of deep neural networks, while they hardly utilize the advantage of optimization-based assignment methods. 3) The graph-based optimization methods mostly utilize a separate neural network to extract features, which brings the inconsistency between training and inference. Therefore, in this paper we propose a novel learnable graph matching method to address these issues. Briefly speaking, we model the relationships between tracklets and the intra-frame detections as a general undirected graph. Then the association problem turns into a general graph matching between tracklet graph and detection graph. Furthermore, to make the optimization end-to-end differentiable, we relax the original graph matching into continuous quadratic programming and then incorporate the training of it into a deep graph network with the help of the implicit function theorem. Lastly, our method GMTracker, achieves state-of-the-art performance on several standard MOT datasets. Our code will be available at https://github.com/jiaweihe1996/GMTracker .
The presence of objects that are confusingly similar to the tracked target, poses a fundamental challenge in appearance-based visual tracking. Such distractor objects are easily misclassified as the target itself, leading to eventual tracking failure. While most methods strive to suppress distractors through more powerful appearance models, we take an alternative approach. We propose to keep track of distractor objects in order to continue tracking the target. To this end, we introduce a learned association network, allowing us to propagate the identities of all target candidates from frame-to-frame. To tackle the problem of lacking ground-truth correspondences between distractor objects in visual tracking, we propose a training strategy that combines partial annotations with self-supervision. We conduct comprehensive experimental validation and analysis of our approach on several challenging datasets. Our tracker sets a new state-of-the-art on six benchmarks, achieving an AUC score of 67.1% on LaSOT and a +5.8% absolute gain on the OxUvA long-term dataset.
Most of the existing single object trackers track the target in a unitary local search window, making them particularly vulnerable to challenging factors such as heavy occlusions and out-of-view movements. Despite the attempts to further incorporate global search, prevailing mechanisms that cooperate local and global search are relatively static, thus are still sub-optimal for improving tracking performance. By further studying the local and global search results, we raise a question: can we allow more dynamics for cooperating both results? In this paper, we propose to introduce more dynamics by devising a dynamic attention-guided multi-trajectory tracking strategy. In particular, we construct dynamic appearance model that contains multiple target templates, each of which provides its own attention for locating the target in the new frame. Guided by different attention, we maintain diversified tracking results for the target to build multi-trajectory tracking history, allowing more candidates to represent the true target trajectory. After spanning the whole sequence, we introduce a multi-trajectory selection network to find the best trajectory that delivers improved tracking performance. Extensive experimental results show that our proposed tracking strategy achieves compelling performance on various large-scale tracking benchmarks. The project page of this paper can be found at https://sites.google.com/view/mt-track/.
Multiobject tracking provides situational awareness that enables new applications for modern convenience, public safety, and homeland security. This paper presents a factor graph formulation and a particle-based sum-product algorithm (SPA) for scalable detection and tracking of extended objects. The proposed method dynamically introduces states of newly detected objects, efficiently performs probabilistic multiple-measurement to object association, and jointly infers the geometric shapes of objects. Scalable extended object tracking (EOT) is enabled by modeling association uncertainty by measurement-oriented association variables and newly detected objects by a Poisson birth process. Contrary to conventional EOT methods, a fully particle-based approach makes it possible to describe different geometric object shapes. The proposed method can reliably detect, localize, and track a large number of closely-spaced extended objects without gating and clustering of measurements. We demonstrate significant performance advantages of our approach compared to the recently introduced Poisson multi-Bernoulli mixture filter. In particular, we consider a simulated scenarios with up to twenty closely-spaced objects and a real autonomous driving application where measurements are captured by a lidar sensor.
Tracking a time-varying indefinite number of objects in a video sequence over time remains a challenge despite recent advances in the field. Most existing approaches are not able to properly handle multi-object tracking challenges such as occlusion, in part because they ignore long-term temporal information. To address these shortcomings, we present MO3TR: a truly end-to-end Transformer-based online multi-object tracking (MOT) framework that learns to handle occlusions, track initiation and termination without the need for an explicit data association module or any heuristics. MO3TR encodes object interactions into long-term temporal embeddings using a combination of spatial and temporal Transformers, and recursively uses the information jointly with the input data to estimate the states of all tracked objects over time. The spatial attention mechanism enables our framework to learn implicit representations between all the objects and the objects to the measurements, while the temporal attention mechanism focuses on specific parts of past information, allowing our approach to resolve occlusions over multiple frames. Our experiments demonstrate the potential of this new approach, achieving results on par with or better than the current state-of-the-art on multiple MOT metrics for several popular multi-object tracking benchmarks.
Object tracking becomes critical especially when similar objects are present in the same area. Recent state-of-the-art (SOTA) approaches are proposed based on taking a matching network with a heavy structure to distinguish the target from other objects in the area which indeed drastically downgrades the performance of the tracker in terms of speed. Besides, several candidates are considered and processed to localize the intended object in a region of interest for each frame which is time-consuming. In this article, a special architecture is proposed based on which in contrast to the previous approaches, it is possible to identify the object location in a single shot while taking its template into account to distinguish it from the similar objects in the same area. In brief, first of all, a window containing the object with twice the target size is considered. This window is then fed into a fully convolutional neural network (CNN) to extract a region of interest (RoI) in a form of a matrix for each of the frames. In the beginning, a template of the target is also taken as the input to the CNN. Considering this RoI matrix, the next movement of the tracker is determined based on a simple and fast method. Moreover, this matrix helps to estimate the object size which is crucial when it changes over time. Despite the absence of a matching network, the presented tracker performs comparatively with the SOTA in challenging situations while having a super speed compared to them (up to $120 FPS$ on 1080ti). To investigate this claim, a comparison study is carried out on the GOT-10k dataset. Results reveal the outstanding performance of the proposed method in fulfilling the task.
Adversarial attack arises due to the vulnerability of deep neural networks to perceive input samples injected with imperceptible perturbations. Recently, adversarial attack has been applied to visual object tracking to evaluate the robustness of deep trackers. Assuming that the model structures of deep trackers are known, a variety of white-box attack approaches to visual tracking have demonstrated promising results. However, the model knowledge about deep trackers is usually unavailable in real applications. In this paper, we propose a decision-based black-box attack method for visual object tracking. In contrast to existing black-box adversarial attack methods that deal with static images for image classification, we propose IoU attack that sequentially generates perturbations based on the predicted IoU scores from both current and historical frames. By decreasing the IoU scores, the proposed attack method degrades the accuracy of temporal coherent bounding boxes (i.e., object motions) accordingly. In addition, we transfer the learned perturbations to the next few frames to initialize temporal motion attack. We validate the proposed IoU attack on state-of-the-art deep trackers (i.e., detection based, correlation filter based, and long-term trackers). Extensive experiments on the benchmark datasets indicate the effectiveness of the proposed IoU attack method. The source code is available at https://github.com/VISION-SJTU/IoUattack.
Event cameras are promising devices for lowlatency tracking and high-dynamic range imaging. In this paper,we propose a novel approach for 6 degree-of-freedom (6-DoF)object motion tracking that combines measurements of eventand frame-based cameras. We formulate tracking from highrate events with a probabilistic generative model of the eventmeasurement process of the object. On a second layer, we refinethe object trajectory in slower rate image frames through directimage alignment. We evaluate the accuracy of our approach inseveral object tracking scenarios with synthetic data, and alsoperform experiments with real data.
Correlation acts as a critical role in the tracking field, especially in recent popular Siamese-based trackers. The correlation operation is a simple fusion manner to consider the similarity between the template and the search region. However, the correlation operation itself is a local linear matching process, leading to lose semantic information and fall into local optimum easily, which may be the bottleneck of designing high-accuracy tracking algorithms. Is there any better feature fusion method than correlation? To address this issue, inspired by Transformer, this work presents a novel attention-based feature fusion network, which effectively combines the template and search region features solely using attention. Specifically, the proposed method includes an ego-context augment module based on self-attention and a cross-feature augment module based on cross-attention. Finally, we present a Transformer tracking (named TransT) method based on the Siamese-like feature extraction backbone, the designed attention-based fusion mechanism, and the classification and regression head. Experiments show that our TransT achieves very promising results on six challenging datasets, especially on large-scale LaSOT, TrackingNet, and GOT-10k benchmarks. Our tracker runs at approximatively 50 fps on GPU. Code and models are available at https://github.com/chenxin-dlut/TransT.
Transformers have proven superior performance for a wide variety of tasks since they were introduced. In recent years, they have drawn attention from the vision community in tasks such as image classification and object detection. Despite this wave, an accurate and efficient multiple-object tracking (MOT) method based on transformers is yet to be designed. We argue that the direct application of a transformer architecture with quadratic complexity and insufficient noise-initialized sparse queries - is not optimal for MOT. We propose TransCenter, a transformer-based MOT architecture with dense representations for accurately tracking all the objects while keeping a reasonable runtime. Methodologically, we propose the use of image-related dense detection queries and efficient sparse tracking queries produced by our carefully designed query learning networks (QLN). On one hand, the dense image-related detection queries allow us to infer targets' locations globally and robustly through dense heatmap outputs. On the other hand, the set of sparse tracking queries efficiently interacts with image features in our TransCenter Decoder to associate object positions through time. As a result, TransCenter exhibits remarkable performance improvements and outperforms by a large margin the current state-of-the-art methods in two standard MOT benchmarks with two tracking settings (public/private). TransCenter is also proven efficient and accurate by an extensive ablation study and comparisons to more naive alternatives and concurrent works. For scientific interest, the code is made publicly available at https://github.com/yihongxu/transcenter.
Tracking by detection, the dominant approach for online multi-object tracking, alternates between localization and association steps. As a result, it strongly depends on the quality of instantaneous observations, often failing when objects are not fully visible. In contrast, tracking in humans is underlined by the notion of object permanence: once an object is recognized, we are aware of its physical existence and can approximately localize it even under full occlusions. In this work, we introduce an end-to-end trainable approach for joint object detection and tracking that is capable of such reasoning. We build on top of the recent CenterTrack architecture, which takes pairs of frames as input, and extend it to videos of arbitrary length. To this end, we augment the model with a spatio-temporal, recurrent memory module, allowing it to reason about object locations and identities in the current frame using all the previous history. It is, however, not obvious how to train such an approach. We study this question on a new, large-scale, synthetic dataset for multi-object tracking, which provides ground truth annotations for invisible objects, and propose several approaches for supervising tracking behind occlusions. Our model, trained jointly on synthetic and real data, outperforms the state of the art on KITTI and MOT17 datasets thanks to its robustness to occlusions.
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 OTB2015 dataset with aerial style videos; the UAV123 dataset without synthetic sequences; the UAV20L dataset, which contains 20 long sequences; and DTB70 dataset as our benchmark datasets. We compare the advantages and disadvantages of different trackers in different tracking situations encountered in aerial data. Our findings indicate that the trackers perform significantly worse in aerial datasets compared to standard ground level videos. We attribute this effect to smaller target size, camera motion, significant camera rotation with respect to the target, out of view movement, and clutter in the form of occlusions or similar looking distractors near tracked object.
Multi-object tracking (MOT) has made great progress in recent years, but there are still some problems. Most MOT algorithms follow tracking-by-detection framework, which separates detection and tracking into two independent parts. Early tracking-by-detection algorithms need to do two feature extractions for detection and tracking. Recently, some algorithms make the feature extraction into one network, but the tracking part still relies on data association and needs complex post-processing for life cycle management. Those methods do not combine detection and tracking well. In this paper, we present a novel network to realize joint multi-object detection and tracking in an end-to-end way, called Global Correlation Network (GCNet). Different from most object detection methods, GCNet introduces the global correlation layer for regression of absolute size and coordinates of bounding boxes instead of offsets prediction. The pipeline of detection and tracking by GCNet is conceptually simple, which does not need non-maximum suppression, data association, and other complicated tracking strategies. GCNet was evaluated on a multi-vehicle tracking dataset, UA-DETRAC, and demonstrates promising performance compared to the state-of-the-art detectors and trackers.
Recent tracking-by-detection approaches use deep object detectors as target detection baseline, because of their high performance on still images. For effective video object tracking, object detection is integrated with a data association step performed by either a custom design inference architecture or an end-to-end joint training for tracking purpose. In this work, we adopt the former approach and use the pre-trained Mask R-CNN deep object detector as the baseline. We introduce a novel inference architecture placed on top of FPN-ResNet101 backbone of Mask R-CNN to jointly perform detection and tracking, without requiring additional training for tracking purpose. The proposed single object tracker, TDIOT, applies an appearance similarity-based temporal matching for data association. In order to tackle tracking discontinuities, we incorporate a local search and matching module into the inference head layer that exploits SiamFC for short term tracking. Moreover, in order to improve robustness to scale changes, we introduce a scale adaptive region proposal network that enables to search the target at an adaptively enlarged spatial neighborhood specified by the trace of the target. In order to meet long term tracking requirements, a low cost verification layer is incorporated into the inference architecture to monitor presence of the target based on its LBP histogram model. Performance evaluation on videos from VOT2016, VOT2018 and VOT-LT2018 datasets demonstrate that TDIOT achieves higher accuracy compared to the state-of-the-art short-term trackers while it provides comparable performance in long term tracking.
In video object tracking, there exist rich temporal contexts among successive frames, which have been largely overlooked in existing trackers. In this work, we bridge the individual video frames and explore the temporal contexts across them via a transformer architecture for robust object tracking. Different from classic usage of the transformer in natural language processing tasks, we separate its encoder and decoder into two parallel branches and carefully design them within the Siamese-like tracking pipelines. The transformer encoder promotes the target templates via attention-based feature reinforcement, which benefits the high-quality tracking model generation. The transformer decoder propagates the tracking cues from previous templates to the current frame, which facilitates the object searching process. Our transformer-assisted tracking framework is neat and trained in an end-to-end manner. With the proposed transformer, a simple Siamese matching approach is able to outperform the current top-performing trackers. By combining our transformer with the recent discriminative tracking pipeline, our method sets several new state-of-the-art records on prevalent tracking benchmarks.
Detecting aligned 3D keypoints is essential under many scenarios such as object tracking, shape retrieval and robotics. However, it is generally hard to prepare a high-quality dataset for all types of objects due to the ambiguity of keypoint itself. Meanwhile, current unsupervised detectors are unable to generate aligned keypoints with good coverage. In this paper, we propose an unsupervised aligned keypoint detector, Skeleton Merger, which utilizes skeletons to reconstruct objects. It is based on an Autoencoder architecture. The encoder proposes keypoints and predicts activation strengths of edges between keypoints. The decoder performs uniform sampling on the skeleton and refines it into small point clouds with pointwise offsets. Then the activation strengths are applied and the sub-clouds are merged. Composite Chamfer Distance (CCD) is proposed as a distance between the input point cloud and the reconstruction composed of sub-clouds masked by activation strengths. We demonstrate that Skeleton Merger is capable of detecting semantically-rich salient keypoints with good alignment, and shows comparable performance to supervised methods on the KeypointNet dataset. It is also shown that the detector is robust to noise and subsampling. Our code is available at https://github.com/eliphatfs/SkeletonMerger.