Online Multi-Object Tracking
25 papers with code • 5 benchmarks • 9 datasets
The goal of Online Multi-Object Tracking is to estimate the spatio-temporal trajectories of multiple objects in an online video stream (i.e., the video is provided frame-by-frame), which is a fundamental problem for numerous real-time applications, such as video surveillance, autonomous driving, and robot navigation.
Source: A Hybrid Data Association Framework for Robust Online Multi-Object Tracking
Benchmarks
These leaderboards are used to track progress in Online Multi-Object Tracking
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Online Multi-Object Tracking models and implementationsDatasets
MOT17
MOTChallenge
MOT16
MOT15
MMPTRACK
BEE23
Oxford Town Center
PersonPath22
CholecTrack20
Most implemented papers
Looking Beyond Two Frames: End-to-End Multi-Object Tracking Using Spatial and Temporal Transformers
alanzty/mo3tr
•
•
Tracking a time-varying indefinite number of objects in a video sequence over time remains a challenge despite recent advances in the field.
Learnable Graph Matching: Incorporating Graph Partitioning with Deep Feature Learning for Multiple Object Tracking
jiaweihe1996/GMTracker
•
•
CVPR 2021
Then the association problem turns into a general graph matching between tracklet graph and detection graph.
SiamMOT: Siamese Multi-Object Tracking
amazon-research/siam-mot
•
•
CVPR 2021
In this paper, we focus on improving online multi-object tracking (MOT).
Do Different Tracking Tasks Require Different Appearance Models?
Zhongdao/UniTrack
•
•
NeurIPS 2021
We show how most tracking tasks can be solved within this framework, and that the same appearance model can be successfully used to obtain results that are competitive against specialised methods for most of the tasks considered.
Detection Recovery in Online Multi-Object Tracking with Sparse Graph Tracker
hyunjs/sgt
•
•
The strong edge features allow SGT to track targets with tracking candidates selected by top-K scored detections with large K. As a result, even low-scored detections can be tracked, and the missed detections are also recovered.
