相关论文: TOPIC: A Parallel Association Paradigm for Multi-O…

Multi-object tracking (MOT) with camera-LiDAR fusion demands accurate results of object detection, affinity computation and data association in real time. This paper presents an efficient multi-modal MOT framework with online joint…

Multi-object tracking (MOT) in video sequences remains a challenging task, especially in scenarios with significant camera movements. This is because targets can drift considerably on the image plane, leading to erroneous tracking outcomes.…

Robust multi-object tracking (MOT) is a prerequisite fora safe deployment of self-driving cars. Tracking objects, however, remains a highly challenging problem, especially in cluttered autonomous driving scenes in which objects tend to…

We propose a new visual hierarchical representation paradigm for multi-object tracking. It is more effective to discriminate between objects by attending to objects' compositional visual regions and contrasting with the background…

The ever-increasing use of artificial intelligence in autonomous systems has significantly contributed to advance the research on multi-object tracking, adopted in several real-time applications (e.g., autonomous driving, surveillance…

For a long time, the most common paradigm in Multi-Object Tracking was tracking-by-detection (TbD), where objects are first detected and then associated over video frames. For association, most models resourced to motion and appearance…

Multi-Object Tracking (MOT) aims to detect and associate all targets of given classes across frames. Current dominant solutions, e.g. ByteTrack and StrongSORT++, follow the hybrid pipeline, which first accomplish most of the associations in…

3D Multi-object tracking (MOT) ensures consistency during continuous dynamic detection, conducive to subsequent motion planning and navigation tasks in autonomous driving. However, camera-based methods suffer in the case of occlusions and…

Data association-based multiple object tracking (MOT) involves multiple separated modules processed or optimized differently, which results in complex method design and requires non-trivial tuning of parameters. In this paper, we present an…

Multi-object tracking (MOT) has been dominated by the use of track by detection approaches due to the success of convolutional neural networks (CNNs) on detection in the last decade. As the datasets and bench-marking sites are published,…

In this paper, we focus on improving online multi-object tracking (MOT). In particular, we introduce a region-based Siamese Multi-Object Tracking network, which we name SiamMOT. SiamMOT includes a motion model that estimates the instance's…

Multiple Object Tracking (MOT) focuses on modeling the relationship of detected objects among consecutive frames and merge them into different trajectories. MOT remains a challenging task as noisy and confusing detection results often…

Multiple people tracking is a key problem for many applications such as surveillance, animation or car navigation, and a key input for tasks such as activity recognition. In crowded environments occlusions and false detections are common,…

Compared with real-time multi-object tracking (MOT), offline multi-object tracking (OMOT) has the advantages to perform 2D-3D detection fusion, erroneous link correction, and full track optimization but has to deal with the challenges from…

Current motion-based multiple object tracking (MOT) approaches rely heavily on Intersection-over-Union (IoU) for object association. Without using 3D features, they are ineffective in scenarios with occlusions or visually similar objects.…

The task of 3D single object tracking (SOT) with LiDAR point clouds is crucial for various applications, such as autonomous driving and robotics. However, existing approaches have primarily relied on appearance matching or motion modeling…

In this work, we propose TransTrack, a simple but efficient scheme to solve the multiple object tracking problems. TransTrack leverages the transformer architecture, which is an attention-based query-key mechanism. It applies object…

Most modern multi-object tracking (MOT) systems follow the tracking-by-detection paradigm. It first localizes the objects of interest, then extracting their individual appearance features to make data association. The individual features,…

Most state-of-the-art trackers adopt one-stream paradigm, using a single Vision Transformer for joint feature extraction and relation modeling of template and search region images. However, relation modeling between different image patches…

Multiple Object Tracking (MOT) is an important task in computer vision. MOT is still challenging due to the occlusion problem, especially in dense scenes. Following the tracking-by-detection framework, we propose the Box-Plane Matching…