A visual single-object tracker is an indispensable component of underwater vehicles (UVs) in marine organism grasping tasks. Its accuracy and stability are imperative to guide the UVs to perform grasping behavior. Although single-object trackers show competitive performance in the challenge of underwater image degradation, there are still issues with sample imbalance and exclusion of similar objects that need to be addressed for application in marine organism grasping. This paper proposes Underwater OSTrack (UOSTrack), which consists of underwater image and open-air sequence hybrid training (UOHT), and motion-based post-processing (MBPP). The UOHT training paradigm is designed to train the sample-imbalanced underwater tracker so that the tracker is exposed to a great number of underwater domain training samples and learns the feature expressions. The MBPP paradigm is proposed to exclude similar objects. It uses the estimation box predicted with a Kalman filter and the candidate boxes in the response map to relocate the lost tracked object in the candidate area. UOSTrack achieves an average performance improvement of 4.41% and 7.98% maximum compared to state-of-the-art methods on various benchmarks, respectively. Field experiments have verified the accuracy and stability of our proposed UOSTrack for UVs in marine organism grasping tasks. More details can be found at https://github.com/LiYunfengLYF/UOSTrack.
In this paper, we propose a robust 3D detector, named Cross Modal Transformer (CMT), for end-to-end 3D multi-modal detection. Without explicit view transformation, CMT takes the image and point clouds tokens as inputs and directly outputs accurate 3D bounding boxes. The spatial alignment of multi-modal tokens is performed by encoding the 3D points into multi-modal features. The core design of CMT is quite simple while its performance is impressive. It achieves 74.1\% NDS (state-of-the-art with single model) on nuScenes test set while maintaining fast inference speed. Moreover, CMT has a strong robustness even if the LiDAR is missing. Code is released at https://github.com/junjie18/CMT.
We introduce a novel framework to track multiple objects in overhead camera videos for airport checkpoint security scenarios where targets correspond to passengers and their baggage items. We propose a Self-Supervised Learning (SSL) technique to provide the model information about instance segmentation uncertainty from overhead images. Our SSL approach improves object detection by employing a test-time data augmentation and a regression-based, rotation-invariant pseudo-label refinement technique. Our pseudo-label generation method provides multiple geometrically-transformed images as inputs to a Convolutional Neural Network (CNN), regresses the augmented detections generated by the network to reduce localization errors, and then clusters them using the mean-shift algorithm. The self-supervised detector model is used in a single-camera tracking algorithm to generate temporal identifiers for the targets. Our method also incorporates a multi-view trajectory association mechanism to maintain consistent temporal identifiers as passengers travel across camera views. An evaluation of detection, tracking, and association performances on videos obtained from multiple overhead cameras in a realistic airport checkpoint environment demonstrates the effectiveness of the proposed approach. Our results show that self-supervision improves object detection accuracy by up to $42\%$ without increasing the inference time of the model. Our multi-camera association method achieves up to $89\%$ multi-object tracking accuracy with an average computation time of less than $15$ ms.
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 users to tackle key remaining challenges in GOT, aiming to increase robustness and reduce computation through joint tracking of multiple objects simultaneously. In addition, we propose a transformer-based GOT tracker baseline capable of joint processing of multiple objects through shared computation. Our approach 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. In addition, our approach 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.
Algorithmic solutions for multi-object tracking (MOT) are a key enabler for applications in autonomous navigation and applied ocean sciences. State-of-the-art MOT methods fully rely on a statistical model and typically use preprocessed sensor data as measurements. In particular, measurements are produced by a detector that extracts potential object locations from the raw sensor data collected for a discrete time step. This preparatory processing step reduces data flow and computational complexity but may result in a loss of information. State-of-the-art Bayesian MOT methods that are based on belief propagation (BP) systematically exploit graph structures of the statistical model to reduce computational complexity and improve scalability. However, as a fully model-based approach, BP can only provide suboptimal estimates when there is a mismatch between the statistical model and the true data-generating process. Existing BP-based MOT methods can further only make use of preprocessed measurements. In this paper, we introduce a variant of BP that combines model-based with data-driven MOT. The proposed neural enhanced belief propagation (NEBP) method complements the statistical model of BP by information learned from raw sensor data. This approach conjectures that the learned information can reduce model mismatch and thus improve data association and false alarm rejection. Our NEBP method improves tracking performance compared to model-based methods. At the same time, it inherits the advantages of BP-based MOT, i.e., it scales only quadratically in the number of objects, and it can thus generate and maintain a large number of object tracks. We evaluate the performance of our NEBP approach for MOT on the nuScenes autonomous driving dataset and demonstrate that it has state-of-the-art performance.
Visual object tracking under challenging conditions of motion and light can be hindered by the capabilities of conventional cameras, prone to producing images with motion blur. Event cameras are novel sensors suited to robustly perform vision tasks under these conditions. However, due to the nature of their output, applying them to object detection and tracking is non-trivial. In this work, we propose a framework to take advantage of both event cameras and off-the-shelf deep learning for object tracking. We show that reconstructing event data into intensity frames improves the tracking performance in conditions under which conventional cameras fail to provide acceptable results.
This is a brief technical report of our proposed method for Multiple-Object Tracking (MOT) Challenge in Complex Environments. In this paper, we treat the MOT task as a two-stage task including human detection and trajectory matching. Specifically, we designed an improved human detector and associated most of detection to guarantee the integrity of the motion trajectory. We also propose a location-wise matching matrix to obtain more accurate trace matching. Without any model merging, our method achieves 66.672 HOTA and 93.971 MOTA on the DanceTrack challenge dataset.
Although the manipulating of the unmanned aerial manipulator (UAM) has been widely studied, vision-based UAM approaching, which is crucial to the subsequent manipulating, generally lacks effective design. The key to the visual UAM approaching lies in object tracking, while current UAM tracking typically relies on costly model-based methods. Besides, UAM approaching often confronts more severe object scale variation issues, which makes it inappropriate to directly employ state-of-the-art model-free Siamese-based methods from the object tracking field. To address the above problems, this work proposes a novel Siamese network with pairwise scale-channel attention (SiamSA) for vision-based UAM approaching. Specifically, SiamSA consists of a pairwise scale-channel attention network (PSAN) and a scale-aware anchor proposal network (SA-APN). PSAN acquires valuable scale information for feature processing, while SA-APN mainly attaches scale awareness to anchor proposing. Moreover, a new tracking benchmark for UAM approaching, namely UAMT100, is recorded with 35K frames on a flying UAM platform for evaluation. Exhaustive experiments on the benchmarks and real-world tests validate the efficiency and practicality of SiamSA with a promising speed. Both the code and UAMT100 benchmark are now available at https://github.com/vision4robotics/SiamSA.
The evaluation of object detection models is usually performed by optimizing a single metric, e.g. mAP, on a fixed set of datasets, e.g. Microsoft COCO and Pascal VOC. Due to image retrieval and annotation costs, these datasets consist largely of images found on the web and do not represent many real-life domains that are being modelled in practice, e.g. satellite, microscopic and gaming, making it difficult to assert the degree of generalization learned by the model. We introduce the Roboflow-100 (RF100) consisting of 100 datasets, 7 imagery domains, 224,714 images, and 805 class labels with over 11,170 labelling hours. We derived RF100 from over 90,000 public datasets, 60 million public images that are actively being assembled and labelled by computer vision practitioners in the open on the web application Roboflow Universe. By releasing RF100, we aim to provide a semantically diverse, multi-domain benchmark of datasets to help researchers test their model's generalizability with real-life data. RF100 download and benchmark replication are available on GitHub.
Object trackers deployed on low-power devices need to be light-weight, however, most of the current state-of-the-art (SOTA) methods rely on using compute-heavy backbones built using CNNs or transformers. Large sizes of such models do not allow their deployment in low-power conditions and designing compressed variants of large tracking models is of great importance. This paper demonstrates how highly compressed light-weight object trackers can be designed using neural architectural pruning of large CNN and transformer based trackers. Further, a comparative study on architectural choices best suited to design light-weight trackers is provided. A comparison between SOTA trackers using CNNs, transformers as well as the combination of the two is presented to study their stability at various compression ratios. Finally results for extreme pruning scenarios going as low as 1% in some cases are shown to study the limits of network pruning in object tracking. This work provides deeper insights into designing highly efficient trackers from existing SOTA methods.
It is crucial to choose actions from an appropriate distribution while learning a sequential decision-making process in which a set of actions is expected given the states and previous reward. Yet, if there are more than two latent variables and every two variables have a covariance value, learning a known prior from data becomes challenging. Because when the data are big and diverse, many posterior estimate methods experience posterior collapse. In this paper, we propose the $\beta$-Multivariational Autoencoder ($\beta$MVAE) to learn a Multivariate Gaussian prior from video frames for use as part of a single object-tracking in form of a decision-making process. We present a novel formulation for object motion in videos with a set of dependent parameters to address a single object-tracking task. The true values of the motion parameters are obtained through data analysis on the training set. The parameters population is then assumed to have a Multivariate Gaussian distribution. The $\beta$MVAE is developed to learn this entangled prior $p = N(\mu, \Sigma)$ directly from frame patches where the output is the object masks of the frame patches. We devise a bottleneck to estimate the posterior's parameters, i.e. $\mu', \Sigma'$. Via a new reparameterization trick, we learn the likelihood $p(\hat{x}|z)$ as the object mask of the input. Furthermore, we alter the neural network of $\beta$MVAE with the U-Net architecture and name the new network $\beta$Multivariational U-Net ($\beta$MVUnet). Our networks are trained from scratch via over 85k video frames for 24 ($\beta$MVUnet) and 78 ($\beta$MVAE) million steps. We show that $\beta$MVUnet enhances both posterior estimation and segmentation functioning over the test set. Our code and the trained networks are publicly released.
Current 3D single object tracking methods are typically based on VoteNet, a 3D region proposal network. Despite the success, using a single seed point feature as the cue for offset learning in VoteNet prevents high-quality 3D proposals from being generated. Moreover, seed points with different importance are treated equally in the voting process, aggravating this defect. To address these issues, we propose a novel global-local transformer voting scheme to provide more informative cues and guide the model pay more attention on potential seed points, promoting the generation of high-quality 3D proposals. Technically, a global-local transformer (GLT) module is employed to integrate object- and patch-aware prior into seed point features to effectively form strong feature representation for geometric positions of the seed points, thus providing more robust and accurate cues for offset learning. Subsequently, a simple yet effective training strategy is designed to train the GLT module. We develop an importance prediction branch to learn the potential importance of the seed points and treat the output weights vector as a training constraint term. By incorporating the above components together, we exhibit a superior tracking method GLT-T. Extensive experiments on challenging KITTI and NuScenes benchmarks demonstrate that GLT-T achieves state-of-the-art performance in the 3D single object tracking task. Besides, further ablation studies show the advantages of the proposed global-local transformer voting scheme over the original VoteNet. Code and models will be available at https://github.com/haooozi/GLT-T.
Visual object tracking is essential to intelligent robots. Most existing approaches have ignored the online latency that can cause severe performance degradation during real-world processing. Especially for unmanned aerial vehicles (UAVs), where robust tracking is more challenging and onboard computation is limited, the latency issue can be fatal. In this work, we present a simple framework for end-to-end latency-aware tracking, i.e., end-to-end predictive visual tracking (PVT++). Unlike existing solutions that naively append Kalman Filters after trackers, PVT++ can be jointly optimized, so that it takes not only motion information but can also leverage the rich visual knowledge in most pre-trained tracker models for robust prediction. Besides, to bridge the training-evaluation domain gap, we propose a relative motion factor, empowering PVT++ to generalize to the challenging and complex UAV tracking scenes. These careful designs have made the small-capacity lightweight PVT++ a widely effective solution. Additionally, this work presents an extended latency-aware evaluation benchmark for assessing an any-speed tracker in the online setting. Empirical results on a robotic platform from the aerial perspective show that PVT++ can achieve significant performance gain on various trackers and exhibit higher accuracy than prior solutions, largely mitigating the degradation brought by latency.
Combining the Color and Event cameras (also called Dynamic Vision Sensors, DVS) for robust object tracking is a newly emerging research topic in recent years. Existing color-event tracking framework usually contains multiple scattered modules which may lead to low efficiency and high computational complexity, including feature extraction, fusion, matching, interactive learning, etc. In this paper, we propose a single-stage backbone network for Color-Event Unified Tracking (CEUTrack), which achieves the above functions simultaneously. Given the event points and RGB frames, we first transform the points into voxels and crop the template and search regions for both modalities, respectively. Then, these regions are projected into tokens and parallelly fed into the unified Transformer backbone network. The output features will be fed into a tracking head for target object localization. Our proposed CEUTrack is simple, effective, and efficient, which achieves over 75 FPS and new SOTA performance. To better validate the effectiveness of our model and address the data deficiency of this task, we also propose a generic and large-scale benchmark dataset for color-event tracking, termed COESOT, which contains 90 categories and 1354 video sequences. Additionally, a new evaluation metric named BOC is proposed in our evaluation toolkit to evaluate the prominence with respect to the baseline methods. We hope the newly proposed method, dataset, and evaluation metric provide a better platform for color-event-based tracking. The dataset, toolkit, and source code will be released on: \url{https://github.com/Event-AHU/COESOT}.
In this paper, we propose MOTRv2, a simple yet effective pipeline to bootstrap end-to-end multi-object tracking with a pretrained object detector. Existing end-to-end methods, MOTR and TrackFormer are inferior to their tracking-by-detection counterparts mainly due to their poor detection performance. We aim to improve MOTR by elegantly incorporating an extra object detector. We first adopt the anchor formulation of queries and then use an extra object detector to generate proposals as anchors, providing detection prior to MOTR. The simple modification greatly eases the conflict between joint learning detection and association tasks in MOTR. MOTRv2 keeps the query propogation feature and scales well on large-scale benchmarks. MOTRv2 ranks the 1st place (73.4% HOTA on DanceTrack) in the 1st Multiple People Tracking in Group Dance Challenge. Moreover, MOTRv2 reaches state-of-the-art performance on the BDD100K dataset. We hope this simple and effective pipeline can provide some new insights to the end-to-end MOT community. Code is available at \url{https://github.com/megvii-research/MOTRv2}.
Keypoint annotation in point clouds is an important task for 3D reconstruction, object tracking and alignment, in particular in deformable or moving scenes. In the context of agriculture robotics, it is a critical task for livestock automation to work toward condition assessment or behaviour recognition. In this work, we propose a novel approach for semantic keypoint annotation in point clouds, by reformulating the keypoint extraction as a regression problem of the distance between the keypoints and the rest of the point cloud. We use the distance on the point cloud manifold mapped into a radial basis function (RBF), which is then learned using an encoder-decoder architecture. Special consideration is given to the data augmentation specific to multi-depth-camera systems by considering noise over the extrinsic calibration and camera frame dropout. Additionally, we investigate computationally efficient non-rigid deformation methods that can be applied to animal point clouds. Our method is tested on data collected in the field, on moving beef cattle, with a calibrated system of multiple hardware-synchronised RGB-D cameras.
Recently, transformer-based methods have achieved impressive results on Video Instance Segmentation (VIS). However, most of these top-performing methods run in an offline manner by processing the entire video clip at once to predict instance mask volumes. This makes them incapable of handling the long videos that appear in challenging new video instance segmentation datasets like UVO and OVIS. We propose a fully online transformer-based video instance segmentation model that performs comparably to top offline methods on the YouTube-VIS 2019 benchmark and considerably outperforms them on UVO and OVIS. This method, called Robust Online Video Segmentation (ROVIS), augments the Mask2Former image instance segmentation model with track queries, a lightweight mechanism for carrying track information from frame to frame, originally introduced by the TrackFormer method for multi-object tracking. We show that, when combined with a strong enough image segmentation architecture, track queries can exhibit impressive accuracy while not being constrained to short videos.
Despite recent progress in Multiple Object Tracking (MOT), several obstacles such as occlusions, similar objects, and complex scenes remain an open challenge. Meanwhile, a systematic study of the cost-performance tradeoff for the popular tracking-by-detection paradigm is still lacking. This paper introduces SMILEtrack, an innovative object tracker that effectively addresses these challenges by integrating an efficient object detector with a Siamese network-based Similarity Learning Module (SLM). The technical contributions of SMILETrack are twofold. First, we propose an SLM that calculates the appearance similarity between two objects, overcoming the limitations of feature descriptors in Separate Detection and Embedding (SDE) models. The SLM incorporates a Patch Self-Attention (PSA) block inspired by the vision Transformer, which generates reliable features for accurate similarity matching. Second, we develop a Similarity Matching Cascade (SMC) module with a novel GATE function for robust object matching across consecutive video frames, further enhancing MOT performance. Together, these innovations help SMILETrack achieve an improved trade-off between the cost ({\em e.g.}, running speed) and performance (e.g., tracking accuracy) over several existing state-of-the-art benchmarks, including the popular BYTETrack method. SMILETrack outperforms BYTETrack by 0.4-0.8 MOTA and 2.1-2.2 HOTA points on MOT17 and MOT20 datasets. Code is available at https://github.com/pingyang1117/SMILEtrack_Official
The SportsMOT dataset aims to solve multiple object tracking of athletes in different sports scenes such as basketball or soccer. The dataset is challenging because of the unstable camera view, athletes' complex trajectory, and complicated background. Previous MOT methods can not match enough high-quality tracks of athletes. To pursue higher performance of MOT in sports scenes, we introduce an innovative tracker named SportsTrack, we utilize tracking by detection as our detection paradigm. Then we will introduce a three-stage matching process to solve the motion blur and body overlapping in sports scenes. Meanwhile, we present another innovation point: one-to-many correspondence between detection bboxes and crowded tracks to handle the overlap of athletes' bodies during sports competitions. Compared to other trackers such as BOT-SORT and ByteTrack, We carefully restored edge-lost tracks that were ignored by other trackers. Finally, we reached the SOTA result in the SportsMOT dataset.
We propose a post-processor, called NeighborTrack, that leverages neighbor information of the tracking target to validate and improve single-object tracking (SOT) results. It requires no additional data or retraining. Instead, it uses the confidence score predicted by the backbone SOT network to automatically derive neighbor information and then uses this information to improve the tracking results. When tracking an occluded target, its appearance features are untrustworthy. However, a general siamese network often cannot tell whether the tracked object is occluded by reading the confidence score alone, because it could be misled by neighbors with high confidence scores. Our proposed NeighborTrack takes advantage of unoccluded neighbors' information to reconfirm the tracking target and reduces false tracking when the target is occluded. It not only reduces the impact caused by occlusion, but also fixes tracking problems caused by object appearance changes. NeighborTrack is agnostic to SOT networks and post-processing methods. For the VOT challenge dataset commonly used in short-term object tracking, we improve three famous SOT networks, Ocean, TransT, and OSTrack, by an average of ${1.92\%}$ EAO and ${2.11\%}$ robustness. For the mid- and long-term tracking experiments based on OSTrack, we achieve state-of-the-art ${72.25\%}$ AUC on LaSOT and ${75.7\%}$ AO on GOT-10K. Code duplication can be found in https://github.com/franktpmvu/NeighborTrack.