Tracking the 6D pose of objects in video sequences is important for robot manipulation. Most prior efforts, however, often assume that the target object's CAD model, at least at a category-level, is available for offline training or during online template matching. This work proposes BundleTrack, a general framework for 6D pose tracking of novel objects, which does not depend upon 3D models, either at the instance or category-level. It leverages the complementary attributes of recent advances in deep learning for segmentation and robust feature extraction, as well as memory-augmented pose graph optimization for spatiotemporal consistency. This enables long-term, low-drift tracking under various challenging scenarios, including significant occlusions and object motions. Comprehensive experiments given two public benchmarks demonstrate that the proposed approach significantly outperforms state-of-art, category-level 6D tracking or dynamic SLAM methods. When compared against state-of-art methods that rely on an object instance CAD model, comparable performance is achieved, despite the proposed method's reduced information requirements. An efficient implementation in CUDA provides a real-time performance of 10Hz for the entire framework. Code is available at: https://github.com/wenbowen123/BundleTrack
Tracking objects of interest in a video is one of the most popular and widely applicable problems in computer vision. However, with the years, a Cambrian explosion of use cases and benchmarks has fragmented the problem in a multitude of different experimental setups. As a consequence, the literature has fragmented too, and now novel approaches proposed by the community are usually specialised to fit only one specific setup. To understand to what extent this specialisation is necessary, in this work we present UniTrack, a solution to address five different tasks within the same framework. UniTrack consists of a single and task-agnostic appearance model, which can be learned in a supervised or self-supervised fashion, and multiple ``heads'' that address individual tasks and do not require training. We show how most tracking tasks can be solved within this framework, and that the same appearance model can be successfully used to obtain results that are competitive against specialised methods for most of the tasks considered. The framework also allows us to analyse appearance models obtained with the most recent self-supervised methods, thus extending their evaluation and comparison to a larger variety of important problems.
Prior correlation filter (CF)-based tracking methods for unmanned aerial vehicles (UAVs) have virtually focused on tracking in the daytime. However, when the night falls, the trackers will encounter more harsh scenes, which can easily lead to tracking failure. In this regard, this work proposes a novel tracker with anti-dark function (ADTrack). The proposed method integrates an efficient and effective low-light image enhancer into a CF-based tracker. Besides, a target-aware mask is simultaneously generated by virtue of image illumination variation. The target-aware mask can be applied to jointly train a target-focused filter that assists the context filter for robust tracking. Specifically, ADTrack adopts dual regression, where the context filter and the target-focused filter restrict each other for dual filter learning. Exhaustive experiments are conducted on typical dark sceneries benchmark, consisting of 37 typical night sequences from authoritative benchmarks, i.e., UAVDark, and our newly constructed benchmark UAVDark70. The results have shown that ADTrack favorably outperforms other state-of-the-art trackers and achieves a real-time speed of 34 frames/s on a single CPU, greatly extending robust UAV tracking to night scenes.
Object tracking has achieved significant progress over the past few years. However, state-of-the-art trackers become increasingly heavy and expensive, which limits their deployments in resource-constrained applications. In this work, we present LightTrack, which uses neural architecture search (NAS) to design more lightweight and efficient object trackers. Comprehensive experiments show that our LightTrack is effective. It can find trackers that achieve superior performance compared to handcrafted SOTA trackers, such as SiamRPN++ and Ocean, while using much fewer model Flops and parameters. Moreover, when deployed on resource-constrained mobile chipsets, the discovered trackers run much faster. For example, on Snapdragon 845 Adreno GPU, LightTrack runs $12\times$ faster than Ocean, while using $13\times$ fewer parameters and $38\times$ fewer Flops. Such improvements might narrow the gap between academic models and industrial deployments in object tracking task. LightTrack is released at https://github.com/researchmm/LightTrack.
Boosting performance of the offline trained siamese trackers is getting harder nowadays since the fixed information of the template cropped from the first frame has been almost thoroughly mined, but they are poorly capable of resisting target appearance changes. Existing trackers with template updating mechanisms rely on time-consuming numerical optimization and complex hand-designed strategies to achieve competitive performance, hindering them from real-time tracking and practical applications. In this paper, we propose a novel tracking framework built on top of a space-time memory network that is competent to make full use of historical information related to the target for better adapting to appearance variations during tracking. Specifically, a novel memory mechanism is introduced, which stores the historical information of the target to guide the tracker to focus on the most informative regions in the current frame. Furthermore, the pixel-level similarity computation of the memory network enables our tracker to generate much more accurate bounding boxes of the target. Extensive experiments and comparisons with many competitive trackers on challenging large-scale benchmarks, OTB-2015, TrackingNet, GOT-10k, LaSOT, UAV123, and VOT2018, show that, without bells and whistles, our tracker outperforms all previous state-of-the-art real-time methods while running at 37 FPS. The code is available at https://github.com/fzh0917/STMTrack.
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.
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.
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.
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.
This paper considers the problem of spatiotemporal object-centric reasoning in videos. Central to our approach is the notion of object permanence, i.e., the ability to reason about the location of objects as they move through the video while being occluded, contained or carried by other objects. Existing deep learning based approaches often suffer from spatiotemporal biases when applied to video reasoning problems. We propose Hopper, which uses a Multi-hop Transformer for reasoning object permanence in videos. Given a video and a localization query, Hopper reasons over image and object tracks to automatically hop over critical frames in an iterative fashion to predict the final position of the object of interest. We demonstrate the effectiveness of using a contrastive loss to reduce spatiotemporal biases. We evaluate over CATER dataset and find that Hopper achieves 73.2% Top-1 accuracy using just 1 FPS by hopping through just a few critical frames. We also demonstrate Hopper can perform long-term reasoning by building a CATER-h dataset that requires multi-step reasoning to localize objects of interest correctly.
The task object tracking is vital in numerous applications such as autonomous driving, intelligent surveillance, robotics, etc. This task entails the assigning of a bounding box to an object in a video stream, given only the bounding box for that object on the first frame. In 2015, a new type of video object tracking (VOT) dataset was created that introduced rotated bounding boxes as an extension of axis-aligned ones. In this work, we introduce a novel end-to-end deep learning method based on the Transformer Multi-Head Attention architecture. We also present a new type of loss function, which takes into account the bounding box overlap and orientation. Our Deep Object Tracking model with Circular Loss Function (DOTCL) shows an considerable improvement in terms of robustness over current state-of-the-art end-to-end deep learning models. It also outperforms state-of-the-art object tracking methods on VOT2018 dataset in terms of expected average overlap (EAO) metric.
Neural networks have achieved success in a wide array of perceptual tasks but often fail at tasks involving both perception and higher-level reasoning. On these more challenging tasks, bespoke approaches (such as modular symbolic components, independent dynamics models or semantic parsers) targeted towards that specific type of task have typically performed better. The downside to these targeted approaches, however, is that they can be more brittle than general-purpose neural networks, requiring significant modification or even redesign according to the particular task at hand. Here, we propose a more general neural-network-based approach to dynamic visual reasoning problems that obtains state-of-the-art performance on three different domains, in each case outperforming bespoke modular approaches tailored specifically to the task. Our method relies on learned object-centric representations, self-attention and self-supervised dynamics learning, and all three elements together are required for strong performance to emerge. The success of this combination suggests that there may be no need to trade off flexibility for performance on problems involving spatio-temporal or causal-style reasoning. With the right soft biases and learning objectives in a neural network we may be able to attain the best of both worlds.
In this paper, we focus on the self-supervised learning of visual correspondence using unlabeled videos in the wild. Our method simultaneously considers intra- and inter-video representation associations for reliable correspondence estimation. The intra-video learning transforms the image contents across frames within a single video via the frame pair-wise affinity. To obtain the discriminative representation for instance-level separation, we go beyond the intra-video analysis and construct the inter-video affinity to facilitate the contrastive transformation across different videos. By forcing the transformation consistency between intra- and inter-video levels, the fine-grained correspondence associations are well preserved and the instance-level feature discrimination is effectively reinforced. Our simple framework outperforms the recent self-supervised correspondence methods on a range of visual tasks including video object tracking (VOT), video object segmentation (VOS), pose keypoint tracking, etc. It is worth mentioning that our method also surpasses the fully-supervised affinity representation (e.g., ResNet) and performs competitively against the recent fully-supervised algorithms designed for the specific tasks (e.g., VOT and VOS).
Recently, Siamese-based trackers have achieved promising performance in visual tracking. Most recent Siamese-based trackers typically employ a depth-wise cross-correlation (DW-XCorr) to obtain multi-channel correlation information from the two feature maps (target and search region). However, DW-XCorr has several limitations within Siamese-based tracking: it can easily be fooled by distractors, has fewer activated channels, and provides weak discrimination of object boundaries. Further, DW-XCorr is a handcrafted parameter-free module and cannot fully benefit from offline learning on large-scale data. We propose a learnable module, called the asymmetric convolution (ACM), which learns to better capture the semantic correlation information in offline training on large-scale data. Different from DW-XCorr and its predecessor(XCorr), which regard a single feature map as the convolution kernel, our ACM decomposes the convolution operation on a concatenated feature map into two mathematically equivalent operations, thereby avoiding the need for the feature maps to be of the same size (width and height)during concatenation. Our ACM can incorporate useful prior information, such as bounding-box size, with standard visual features. Furthermore, ACM can easily be integrated into existing Siamese trackers based on DW-XCorror XCorr. To demonstrate its generalization ability, we integrate ACM into three representative trackers: SiamFC, SiamRPN++, and SiamBAN. Our experiments reveal the benefits of the proposed ACM, which outperforms existing methods on six tracking benchmarks. On the LaSOT test set, our ACM-based tracker obtains a significant improvement of 5.8% in terms of success (AUC), over the baseline.
Advanced video analytic systems, including scene classification and object detection, have seen widespread success in various domains such as smart cities and autonomous transportation. With an ever-growing number of powerful client devices, there is incentive to move these heavy video analytics workloads from the cloud to mobile devices to achieve low latency and real-time processing and to preserve user privacy. However, most video analytic systems are heavyweight and are trained offline with some pre-defined latency or accuracy requirements. This makes them unable to adapt at runtime in the face of three types of dynamism -- the input video characteristics change, the amount of compute resources available on the node changes due to co-located applications, and the user's latency-accuracy requirements change. In this paper we introduce ApproxDet, an adaptive video object detection framework for mobile devices to meet accuracy-latency requirements in the face of changing content and resource contention scenarios. To achieve this, we introduce a multi-branch object detection kernel (layered on Faster R-CNN), which incorporates a data-driven modeling approach on the performance metrics, and a latency SLA-driven scheduler to pick the best execution branch at runtime. We couple this kernel with approximable video object tracking algorithms to create an end-to-end video object detection system. We evaluate ApproxDet on a large benchmark video dataset and compare quantitatively to AdaScale and YOLOv3. We find that ApproxDet is able to adapt to a wide variety of contention and content characteristics and outshines all baselines, e.g., it achieves 52% lower latency and 11.1% higher accuracy over YOLOv3.
Significant progress has been made in Video Object Segmentation (VOS), the video object tracking task in its finest level. While the VOS task can be naturally decoupled into image semantic segmentation and video object tracking, significantly much more research effort has been made in segmentation than tracking. In this paper, we introduce "tracking-by-detection" into VOS which can coherently integrate segmentation into tracking, by proposing a new temporal aggregation network and a novel dynamic time-evolving template matching mechanism to achieve significantly improved performance. Notably, our method is entirely online and thus suitable for one-shot learning, and our end-to-end trainable model allows multiple object segmentation in one forward pass. We achieve new state-of-the-art performance on the DAVIS benchmark without complicated bells and whistles in both speed and accuracy, with a speed of 0.14 second per frame and J&F measure of 75.9% respectively.
Visual object tracking was generally tackled by reasoning independently on fast processing algorithms, accurate online adaptation methods, and fusion of trackers. In this paper, we unify such goals by proposing a novel tracking methodology that takes advantage of other visual trackers, offline and online. A compact student model is trained via the marriage of knowledge distillation and reinforcement learning. The first allows to transfer and compress tracking knowledge of other trackers. The second enables the learning of evaluation measures which are then exploited online. After learning, the student can be ultimately used to build (i) a very fast single-shot tracker, (ii) a tracker with a simple and effective online adaptation mechanism, (iii) a tracker that performs fusion of other trackers. Extensive validation shows that the proposed algorithms compete with real-time state-of-the-art trackers.
Anchor-based Siamese trackers have achieved remarkable advancements in accuracy, yet the further improvement is restricted by the lagged tracking robustness. We find the underlying reason is that the regression network in anchor-based methods is only trained on the positive anchor boxes (i.e., $IoU \geq0.6$). This mechanism makes it difficult to refine the anchors whose overlap with the target objects are small. In this paper, we propose a novel object-aware anchor-free network to address this issue. First, instead of refining the reference anchor boxes, we directly predict the position and scale of target objects in an anchor-free fashion. Since each pixel in groundtruth boxes is well trained, the tracker is capable of rectifying inexact predictions of target objects during inference. Second, we introduce a feature alignment module to learn an object-aware feature from predicted bounding boxes. The object-aware feature can further contribute to the classification of target objects and background. Moreover, we present a novel tracking framework based on the anchor-free model. The experiments show that our anchor-free tracker achieves state-of-the-art performance on five benchmarks, including VOT-2018, VOT-2019, OTB-100, GOT-10k and LaSOT. The source code is available at https://github.com/researchmm/TracKit.
In this paper, the main task we aim to tackle is the multi-instance semi-supervised video object segmentation across a sequence of frames where only the first-frame box-level ground-truth is provided. Detection-based algorithms are widely adopted to handle this task, and the challenges lie in the selection of the matching method to predict the result as well as to decide whether to update the target template using the newly predicted result. The existing methods, however, make these selections in a rough and inflexible way, compromising their performance. To overcome this limitation, we propose a novel approach which utilizes reinforcement learning to make these two decisions at the same time. Specifically, the reinforcement learning agent learns to decide whether to update the target template according to the quality of the predicted result. The choice of the matching method will be determined at the same time, based on the action history of the reinforcement learning agent. Experiments show that our method is almost 10 times faster than the previous state-of-the-art method with even higher accuracy (region similarity of 69.1% on DAVIS 2017 dataset).