Related papers: MotionTrack: End-to-End Transformer-based Multi-Ob…

Recent machine learning-based multi-object tracking (MOT) frameworks are becoming popular for 3-D point clouds. Most traditional tracking approaches use filters (e.g., Kalman filter or particle filter) to predict object locations in a time…

LiDAR-based 3D single object tracking (3D SOT) is a critical task in robotics and autonomous systems. Existing methods typically follow frame-wise motion estimation or a sequence-based paradigm. However, the two-frame methods are efficient…

Persistent multi-object tracking (MOT) allows autonomous vehicles to navigate safely in highly dynamic environments. One of the well-known challenges in MOT is object occlusion when an object becomes unobservant for subsequent frames. The…

Multi-object tracking (MOT) methods have seen a significant boost in performance recently, due to strong interest from the research community and steadily improving object detection methods. The majority of tracking methods follow the…

The fusion of camera- and LiDAR-based detections offers a promising solution to mitigate tracking failures in 3D multi-object tracking (MOT). However, existing methods predominantly exploit camera detections to correct tracking failures…

3D object detection serves as the core basis of the perception tasks in autonomous driving. Recent years have seen the rapid progress of multi-modal fusion strategies for more robust and accurate 3D object detection. However, current…

In the classical tracking-by-detection (TBD) paradigm, detection and tracking are separately and sequentially conducted, and data association must be properly performed to achieve satisfactory tracking performance. In this paper, a new…

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…

We present a method to perform online Multiple Object Tracking (MOT) of known object categories in monocular video data. Current Tracking-by-Detection MOT approaches build on top of 2D bounding box detections. In contrast, we exploit…

Tracking has traditionally been the art of following interest points through space and time. This changed with the rise of powerful deep networks. Nowadays, tracking is dominated by pipelines that perform object detection followed by…

This work proposes an end-to-end multi-camera 3D multi-object tracking (MOT) framework. It emphasizes spatio-temporal continuity and integrates both past and future reasoning for tracked objects. Thus, we name it "Past-and-Future reasoning…

Multi-object tracking (MOT) is a critical and challenging task in computer vision, particularly in situations involving objects with similar appearances but diverse movements, as seen in team sports. Current methods, largely reliant on…

Detecting and tracking vehicles in urban scenes is a crucial step in many traffic-related applications as it helps to improve road user safety among other benefits. Various challenges remain unresolved in multi-object tracking (MOT)…

3D multi-object tracking (MOT) has witnessed numerous novel benchmarks and approaches in recent years, especially those under the "tracking-by-detection" paradigm. Despite their progress and usefulness, an in-depth analysis of their…

The recent trend in multiple object tracking (MOT) is heading towards leveraging deep learning to boost the tracking performance. In this paper, we propose a novel solution named TransSTAM, which leverages Transformer to effectively model…

We propose a conceptually simple and thus fast multi-object tracking (MOT) model that does not require any attached modules, such as the Kalman filter, Hungarian algorithm, transformer blocks, or graph networks. Conventional MOT models are…

Object motion and object appearance are commonly used information in multiple object tracking (MOT) applications, either for associating detections across frames in tracking-by-detection methods or direct track predictions for…

Object detection has been extensively utilized in autonomous systems in recent years, encompassing both 2D and 3D object detection. Recent research in this field has primarily centered around multimodal approaches for addressing this…

Multiple Object Tracking (MOT) is a core capability in modern computer vision, essential to autonomous driving, surveillance, sports analytics, robotics, and biomedical imaging. Persistent identity assignment across frames remains…

Multi-object tracking (MOT) at low frame rates can reduce computational, storage and power overhead to better meet the constraints of edge devices. Many existing MOT methods suffer from significant performance degradation in low-frame-rate…