Object Tracking
588 papers with code • 7 benchmarks • 62 datasets
Object tracking is the task of taking an initial set of object detections, creating a unique ID for each of the initial detections, and then tracking each of the objects as they move around frames in a video, maintaining the ID assignment. State-of-the-art methods involve fusing data from RGB and event-based cameras to produce more reliable object tracking. CNN-based models using only RGB images as input are also effective. The most popular benchmark is OTB. There are several evaluation metrics specific to object tracking, including HOTA, MOTA, IDF1, and Track-mAP.
( Image credit: Towards-Realtime-MOT )
Benchmarks
These leaderboards are used to track progress in Object Tracking
Libraries
Use these libraries to find Object Tracking models and implementationsDatasets
KITTI
LaSOT
GOT-10k
MOTChallenge
VOT2018
Virtual KITTI
UAVDT
VOT2017
UA-DETRAC
Event-Camera Dataset
Subtasks
Latest papers with no code
View-Centric Multi-Object Tracking with Homographic Matching in Moving UAV
In this paper, we address the challenge of multi-object tracking (MOT) in moving Unmanned Aerial Vehicle (UAV) scenarios, where irregular flight trajectories, such as hovering, turning left/right, and moving up/down, lead to significantly greater complexity compared to fixed-camera MOT.
Exploring Learning-based Motion Models in Multi-Object Tracking
In the field of multi-object tracking (MOT), traditional methods often rely on the Kalman Filter for motion prediction, leveraging its strengths in linear motion scenarios.
OneTracker: Unifying Visual Object Tracking with Foundation Models and Efficient Tuning
To evaluate the effectiveness of our general framework OneTracker, which is consisted of Foundation Tracker and Prompt Tracker, we conduct extensive experiments on 6 popular tracking tasks across 11 benchmarks and our OneTracker outperforms other models and achieves state-of-the-art performance.
Learning Data Association for Multi-Object Tracking using Only Coordinates
We propose a novel Transformer-based module to address the data association problem for multi-object tracking.
SSF-Net: Spatial-Spectral Fusion Network with Spectral Angle Awareness for Hyperspectral Object Tracking
Hyperspectral video (HSV) offers valuable spatial, spectral, and temporal information simultaneously, making it highly suitable for handling challenges such as background clutter and visual similarity in object tracking.
Beyond MOT: Semantic Multi-Object Tracking
Current multi-object tracking (MOT) aims to predict trajectories of targets (i. e.,"where") in videos.
Multi-Object Tracking with Camera-LiDAR Fusion for Autonomous Driving
This paper presents a novel multi-modal Multi-Object Tracking (MOT) algorithm for self-driving cars that combines camera and LiDAR data.
DeconfuseTrack:Dealing with Confusion for Multi-Object Tracking
Moreover, DeconfuseTrack achieves state-of-the-art performance on the MOT17 and MOT20 test sets, significantly outperforms the baseline tracker ByteTrack in metrics such as HOTA, IDF1, AssA.
Integrating Efficient Optimal Transport and Functional Maps For Unsupervised Shape Correspondence Learning
In the realm of computer vision and graphics, accurately establishing correspondences between geometric 3D shapes is pivotal for applications like object tracking, registration, texture transfer, and statistical shape analysis.
DiffMOT: A Real-time Diffusion-based Multiple Object Tracker with Non-linear Prediction
In Multiple Object Tracking, objects often exhibit non-linear motion of acceleration and deceleration, with irregular direction changes.
