Recent advances in Multi-Object Tracking (MOT) have achieved remarkable success in short-term association within the decoupled tracking-by-detection online paradigm. However, long-term tracking still remains a challenging task. Although graph-based approaches can address this issue by modeling trajectories as a graph in the decoupled manner, their non-online nature poses obstacles for real-time applications. In this paper, we demonstrate that the trajectory graph is a directed acyclic graph, which can be represented by an object sequence arranged by frame and a binary adjacency matrix. It is a coincidence that the binary matrix matches the attention mask in the Transformer, and the object sequence serves exactly as a natural input sequence. Intuitively, we propose that a pure Transformer can naturally unify short- and long-term associations in a decoupled and online manner. Our experiments show that a classic Transformer architecture naturally suits the association problem and achieves a strong baseline compared to existing foundational methods across four datasets: DanceTrack, SportsMOT, MOT17, and MOT20, as well as superior generalizability in domain shift. Moreover, the decoupled property also enables efficient training and inference. This work pioneers a promising Transformer-based approach for the MOT task, and provides code to facilitate further research. https://github.com/chongweiliu/PuTR
Multi-modal object tracking (MMOT) is an emerging field that combines data from various modalities, \eg vision (RGB), depth, thermal infrared, event, language and audio, to estimate the state of an arbitrary object in a video sequence. It is of great significance for many applications such as autonomous driving and intelligent surveillance. In recent years, MMOT has received more and more attention. However, existing MMOT algorithms mainly focus on two modalities (\eg RGB+depth, RGB+thermal infrared, and RGB+language). To leverage more modalities, some recent efforts have been made to learn a unified visual object tracking model for any modality. Additionally, some large-scale multi-modal tracking benchmarks have been established by simultaneously providing more than two modalities, such as vision-language-audio (\eg WebUAV-3M) and vision-depth-language (\eg UniMod1K). To track the latest progress in MMOT, we conduct a comprehensive investigation in this report. Specifically, we first divide existing MMOT tasks into five main categories, \ie RGBL tracking, RGBE tracking, RGBD tracking, RGBT tracking, and miscellaneous (RGB+X), where X can be any modality, such as language, depth, and event. Then, we analyze and summarize each MMOT task, focusing on widely used datasets and mainstream tracking algorithms based on their technical paradigms (\eg self-supervised learning, prompt learning, knowledge distillation, generative models, and state space models). Finally, we maintain a continuously updated paper list for MMOT at https://github.com/983632847/Awesome-Multimodal-Object-Tracking.
Object tracking is a fundamental task in computer vision with broad practical applications across various domains, including traffic monitoring, robotics, and autonomous vehicle tracking. In this project, we aim to develop a sophisticated aerial vehicle system known as Track Anything Rapter (TAR), designed to detect, segment, and track objects of interest based on user-provided multimodal queries, such as text, images, and clicks. TAR utilizes cutting-edge pre-trained models like DINO, CLIP, and SAM to estimate the relative pose of the queried object. The tracking problem is approached as a Visual Servoing task, enabling the UAV to consistently focus on the object through advanced motion planning and control algorithms. We showcase how the integration of these foundational models with a custom high-level control algorithm results in a highly stable and precise tracking system deployed on a custom-built PX4 Autopilot-enabled Voxl2 M500 drone. To validate the tracking algorithm's performance, we compare it against Vicon-based ground truth. Additionally, we evaluate the reliability of the foundational models in aiding tracking in scenarios involving occlusions. Finally, we test and validate the model's ability to work seamlessly with multiple modalities, such as click, bounding box, and image templates.
This paper presents a novel approach to the digital signing of electronic documents through the use of a camera-based interaction system, single-finger tracking for sign recognition, and multi commands executing hand gestures. The proposed solution, referred to as "Air Signature," involves writing the signature in front of the camera, rather than relying on traditional methods such as mouse drawing or physically signing on paper and showing it to a web camera. The goal is to develop a state-of-the-art method for detecting and tracking gestures and objects in real-time. The proposed methods include applying existing gesture recognition and object tracking systems, improving accuracy through smoothing and line drawing, and maintaining continuity during fast finger movements. An evaluation of the fingertip detection, sketching, and overall signing process is performed to assess the effectiveness of the proposed solution. The secondary objective of this research is to develop a model that can effectively recognize the unique signature of a user. This type of signature can be verified by neural cores that analyze the movement, speed, and stroke pixels of the signing in real time. The neural cores use machine learning algorithms to match air signatures to the individual's stored signatures, providing a secure and efficient method of verification. Our proposed System does not require sensors or any hardware other than the camera.
Many query-based approaches for 3D Multi-Object Tracking (MOT) adopt the tracking-by-attention paradigm, utilizing track queries for identity-consistent detection and object queries for identity-agnostic track spawning. Tracking-by-attention, however, entangles detection and tracking queries in one embedding for both the detection and tracking task, which is sub-optimal. Other approaches resemble the tracking-by-detection paradigm and detect objects using decoupled track and detection queries followed by a subsequent association. These methods, however, do not leverage synergies between the detection and association task. Combining the strengths of both paradigms, we introduce ADA-Track++, a novel end-to-end framework for 3D MOT from multi-view cameras. We introduce a learnable data association module based on edge-augmented cross-attention, leveraging appearance and geometric features. We also propose an auxiliary token in this attention-based association module, which helps mitigate disproportionately high attention to incorrect association targets caused by attention normalization. Furthermore, we integrate this association module into the decoder layer of a DETR-based 3D detector, enabling simultaneous DETR-like query-to-image cross-attention for detection and query-to-query cross-attention for data association. By stacking these decoder layers, queries are refined for the detection and association task alternately, effectively harnessing the task dependencies. We evaluate our method on the nuScenes dataset and demonstrate the advantage of our approach compared to the two previous paradigms.
Low-light scenes are prevalent in real-world applications (e.g. autonomous driving and surveillance at night). Recently, multi-object tracking in various practical use cases have received much attention, but multi-object tracking in dark scenes is rarely considered. In this paper, we focus on multi-object tracking in dark scenes. To address the lack of datasets, we first build a Low-light Multi-Object Tracking (LMOT) dataset. LMOT provides well-aligned low-light video pairs captured by our dual-camera system, and high-quality multi-object tracking annotations for all videos. Then, we propose a low-light multi-object tracking method, termed as LTrack. We introduce the adaptive low-pass downsample module to enhance low-frequency components of images outside the sensor noises. The degradation suppression learning strategy enables the model to learn invariant information under noise disturbance and image quality degradation. These components improve the robustness of multi-object tracking in dark scenes. We conducted a comprehensive analysis of our LMOT dataset and proposed LTrack. Experimental results demonstrate the superiority of the proposed method and its competitiveness in real night low-light scenes. Dataset and Code: https: //github.com/ying-fu/LMOT
We derive a novel, provably robust, and closed-form Bayesian update rule for online filtering in state-space models in the presence of outliers and misspecified measurement models. Our method combines generalised Bayesian inference with filtering methods such as the extended and ensemble Kalman filter. We use the former to show robustness and the latter to ensure computational efficiency in the case of nonlinear models. Our method matches or outperforms other robust filtering methods (such as those based on variational Bayes) at a much lower computational cost. We show this empirically on a range of filtering problems with outlier measurements, such as object tracking, state estimation in high-dimensional chaotic systems, and online learning of neural networks.
There is currently strong interest in improving visual object tracking by augmenting the RGB modality with the output of a visual event camera that is particularly informative about the scene motion. However, existing approaches perform event feature extraction for RGB-E tracking using traditional appearance models, which have been optimised for RGB only tracking, without adapting it for the intrinsic characteristics of the event data. To address this problem, we propose an Event backbone (Pooler), designed to obtain a high-quality feature representation that is cognisant of the innate characteristics of the event data, namely its sparsity. In particular, Multi-Scale Pooling is introduced to capture all the motion feature trends within event data through the utilisation of diverse pooling kernel sizes. The association between the derived RGB and event representations is established by an innovative module performing adaptive Mutually Guided Fusion (MGF). Extensive experimental results show that our method significantly outperforms state-of-the-art trackers on two widely used RGB-E tracking datasets, including VisEvent and COESOT, where the precision and success rates on COESOT are improved by 4.9% and 5.2%, respectively. Our code will be available at https://github.com/SSSpc333/TENet.
Roadside perception is a key component in intelligent transportation systems. In this paper, we present a novel three-dimensional (3D) extended object tracking (EOT) method, which simultaneously estimates the object kinematics and extent state, in roadside perception using both the radar and camera data. Because of the influence of sensor viewing angle and limited angle resolution, radar measurements from objects are sparse and non-uniformly distributed, leading to inaccuracies in object extent and position estimation. To address this problem, we present a novel spherical Gaussian function weighted Gaussian mixture model. This model assumes that radar measurements originate from a series of probabilistic weighted radar reflectors on the vehicle's extent. Additionally, we utilize visual detection of vehicle keypoints to provide additional information on the positions of radar reflectors. Since keypoints may not always correspond to radar reflectors, we propose an elastic skeleton fusion mechanism, which constructs a virtual force to establish the relationship between the radar reflectors on the vehicle and its extent. Furthermore, to better describe the kinematic state of the vehicle and constrain its extent state, we develop a new 3D constant turn rate and velocity motion model, considering the complex 3D motion of the vehicle relative to the roadside sensor. Finally, we apply variational Bayesian approximation to the intractable measurement update step to enable recursive Bayesian estimation of the object's state. Simulation results using the Carla simulator and experimental results on the nuScenes dataset demonstrate the effectiveness and superiority of the proposed method in comparison to several state-of-the-art 3D EOT methods.
Quantification of microscopy time-series of in vitro reconstituted motor driven microtubule (MT) transport in 'gliding assays' is typically performed using computational object tracking tools. However, these are limited to non-intersecting and rod-like filaments. Here, we describe a novel computational image-analysis pipeline, KnotResolver, to track image time-series of highly curved self-intersecting looped filaments (knots) by resolving cross-overs. The code integrates filament segmentation and cross-over or 'knot' identification based on directed graph representation, where nodes represent cross-overs and edges represent the path connecting them. The graphs are mapped back to contours and the distance to a reference minimized. We demonstrate the utility of the tool by segmentation and tracking MTs from experiments with dynein-driven wave like filament looping. The accuracy of contour detection is sub-pixel accuracy, and Dice scores indicate a robustness to noise, better than currently used tools. Thus KnotResolver overcomes multiple limitations of widely used tools in microscopy of cytoskeletal filament-like structures.
State-of-the-art Multiple Object Tracking (MOT) approaches have shown remarkable performance when trained and evaluated on current benchmarks. However, these benchmarks primarily consist of clear weather scenarios, overlooking adverse atmospheric conditions such as fog, haze, smoke and dust. As a result, the robustness of trackers against these challenging conditions remains underexplored. To address this gap, we introduce physics-based volumetric fog simulation method for arbitrary MOT datasets, utilizing frame-by-frame monocular depth estimation and a fog formation optical model. We enhance our simulation by rendering both homogeneous and heterogeneous fog and propose to use the dark channel prior method to estimate atmospheric light, showing promising results even in night and indoor scenes. We present the leading benchmark MOTChallenge (third release) augmented with fog (smoke for indoor scenes) of various intensities and conduct a comprehensive evaluation of MOT methods, revealing their limitations under fog and fog-like challenges.
This paper introduces SFSORT, the world's fastest multi-object tracking system based on experiments conducted on MOT Challenge datasets. To achieve an accurate and computationally efficient tracker, this paper employs a tracking-by-detection method, following the online real-time tracking approach established in prior literature. By introducing a novel cost function called the Bounding Box Similarity Index, this work eliminates the Kalman Filter, leading to reduced computational requirements. Additionally, this paper demonstrates the impact of scene features on enhancing object-track association and improving track post-processing. Using a 2.2 GHz Intel Xeon CPU, the proposed method achieves an HOTA of 61.7\% with a processing speed of 2242 Hz on the MOT17 dataset and an HOTA of 60.9\% with a processing speed of 304 Hz on the MOT20 dataset. The tracker's source code, fine-tuned object detection model, and tutorials are available at \url{https://github.com/gitmehrdad/SFSORT}.
LiDAR-based 3D single object tracking (3D SOT) is a critical issue in robotics and autonomous driving. Existing 3D SOT methods typically adhere to a point-based processing pipeline, wherein the re-sampling operation invariably leads to either redundant or missing information, thereby impacting performance. To address these issues, we propose PillarTrack, a novel pillar-based 3D SOT framework. First, we transform sparse point clouds into dense pillars to preserve the local and global geometrics. Second, we propose a Pyramid-Encoded Pillar Feature Encoder (PE-PFE) design to enhance the robustness of pillar feature for translation/rotation/scale. Third, we present an efficient Transformer-based backbone from the perspective of modality differences. Finally, we construct our PillarTrack based on above designs. Extensive experiments show that our method achieves comparable performance on the KITTI and NuScenes datasets, significantly enhancing the performance of the baseline.
Visual object tracking plays a critical role in visual-based autonomous systems, as it aims to estimate the position and size of the object of interest within a live video. Despite significant progress made in this field, state-of-the-art (SOTA) trackers often fail when faced with adversarial perturbations in the incoming frames. This can lead to significant robustness and security issues when these trackers are deployed in the real world. To achieve high accuracy on both clean and adversarial data, we propose building a spatial-temporal continuous representation using the semantic text guidance of the object of interest. This novel continuous representation enables us to reconstruct incoming frames to maintain semantic and appearance consistency with the object of interest and its clean counterparts. As a result, our proposed method successfully defends against different SOTA adversarial tracking attacks while maintaining high accuracy on clean data. In particular, our method significantly increases tracking accuracy under adversarial attacks with around 90% relative improvement on UAV123, which is even higher than the accuracy on clean data.
Accurately distinguishing each object is a fundamental goal of Multi-object tracking (MOT) algorithms. However, achieving this goal still remains challenging, primarily due to: (i) For crowded scenes with occluded objects, the high overlap of object bounding boxes leads to confusion among closely located objects. Nevertheless, humans naturally perceive the depth of elements in a scene when observing 2D videos. Inspired by this, even though the bounding boxes of objects are close on the camera plane, we can differentiate them in the depth dimension, thereby establishing a 3D perception of the objects. (ii) For videos with rapidly irregular camera motion, abrupt changes in object positions can result in ID switches. However, if the camera pose are known, we can compensate for the errors in linear motion models. In this paper, we propose \textit{DepthMOT}, which achieves: (i) detecting and estimating scene depth map \textit{end-to-end}, (ii) compensating the irregular camera motion by camera pose estimation. Extensive experiments demonstrate the superior performance of DepthMOT in VisDrone-MOT and UAVDT datasets. The code will be available at \url{https://github.com/JackWoo0831/DepthMOT}.
In this paper, we propose a novel concept of path consistency to learn robust object matching without using manual object identity supervision. Our key idea is that, to track a object through frames, we can obtain multiple different association results from a model by varying the frames it can observe, i.e., skipping frames in observation. As the differences in observations do not alter the identities of objects, the obtained association results should be consistent. Based on this rationale, we generate multiple observation paths, each specifying a different set of frames to be skipped, and formulate the Path Consistency Loss that enforces the association results are consistent across different observation paths. We use the proposed loss to train our object matching model with only self-supervision. By extensive experiments on three tracking datasets (MOT17, PersonPath22, KITTI), we demonstrate that our method outperforms existing unsupervised methods with consistent margins on various evaluation metrics, and even achieves performance close to supervised methods.
Multi-object tracking (MOT) is a prominent task in computer vision with application in autonomous driving, responsible for the simultaneous tracking of multiple object trajectories. Detection-based multi-object tracking (DBT) algorithms detect objects using an independent object detector and predict the imminent location of each target. Conventional prediction methods in DBT utilize Kalman Filter(KF) to extrapolate the target location in the upcoming frames by supposing a constant velocity motion model. These methods are especially hindered in autonomous driving applications due to dramatic camera motion or unavailable detections. Such limitations lead to tracking failures manifested by numerous identity switches and disrupted trajectories. In this paper, we introduce a novel KF-based prediction module called the Ego-motion Aware Target Prediction (EMAP) module by focusing on the integration of camera motion and depth information with object motion models. Our proposed method decouples the impact of camera rotational and translational velocity from the object trajectories by reformulating the Kalman Filter. This reformulation enables us to reject the disturbances caused by camera motion and maximizes the reliability of the object motion model. We integrate our module with four state-of-the-art base MOT algorithms, namely OC-SORT, Deep OC-SORT, ByteTrack, and BoT-SORT. In particular, our evaluation on the KITTI MOT dataset demonstrates that EMAP remarkably drops the number of identity switches (IDSW) of OC-SORT and Deep OC-SORT by 73% and 21%, respectively. At the same time, it elevates other performance metrics such as HOTA by more than 5%. Our source code is available at https://github.com/noyzzz/EMAP.
Achieving high-performance in multi-object tracking algorithms heavily relies on modeling spatio-temporal relationships during the data association stage. Mainstream approaches encompass rule-based and deep learning-based methods for spatio-temporal relationship modeling. While the former relies on physical motion laws, offering wider applicability but yielding suboptimal results for complex object movements, the latter, though achieving high-performance, lacks interpretability and involves complex module designs. This work aims to simplify deep learning-based spatio-temporal relationship models and introduce interpretability into features for data association. Specifically, a lightweight single-layer transformer encoder is utilized to model spatio-temporal relationships. To make features more interpretative, two contrastive regularization losses based on representation alignment are proposed, derived from spatio-temporal consistency rules. By applying weighted summation to affinity matrices, the aligned features can seamlessly integrate into the data association stage of the original tracking workflow. Experimental results showcase that our model enhances the majority of existing tracking networks' performance without excessive complexity, with minimal increase in training overhead and nearly negligible computational and storage costs.
Considering the complementarity of scene flow estimation in the spatial domain's focusing capability and 3D object tracking in the temporal domain's coherence, this study aims to address a comprehensive new task that can simultaneously capture fine-grained and long-term 3D motion in an online manner: long-term scene flow estimation (LSFE). We introduce SceneTracker, a novel learning-based LSFE network that adopts an iterative approach to approximate the optimal trajectory. Besides, it dynamically indexes and constructs appearance and depth correlation features simultaneously and employs the Transformer to explore and utilize long-range connections within and between trajectories. With detailed experiments, SceneTracker shows superior capabilities in handling 3D spatial occlusion and depth noise interference, highly tailored to the LSFE task's needs. Finally, we build the first real-world evaluation dataset, LSFDriving, further substantiating SceneTracker's commendable generalization capacity. The code and data for SceneTracker is available at https://github.com/wwsource/SceneTracker.
The core of video understanding tasks, such as recognition, captioning, and tracking, is to automatically detect objects or actions in a video and analyze their temporal evolution. Despite sharing a common goal, different tasks often rely on distinct model architectures and annotation formats. In contrast, natural language processing benefits from a unified output space, i.e., text sequences, which simplifies the training of powerful foundational language models, such as GPT-3, with extensive training corpora. Inspired by this, we seek to unify the output space of video understanding tasks by using languages as labels and additionally introducing time and box tokens. In this way, a variety of video tasks could be formulated as video-grounded token generation. This enables us to address various types of video tasks, including classification (such as action recognition), captioning (covering clip captioning, video question answering, and dense video captioning), and localization tasks (such as visual object tracking) within a fully shared encoder-decoder architecture, following a generative framework. Through comprehensive experiments, we demonstrate such a simple and straightforward idea is quite effective and can achieve state-of-the-art or competitive results on seven video benchmarks, providing a novel perspective for more universal video understanding. Code is available at https://github.com/wangjk666/OmniVid.