Online Multi-Object Tracking
28 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
PersonPath22
BEE23
CholecTrack20
Oxford Town Center
Most implemented papers
PP-YOLOE: An evolved version of YOLO
PaddlePaddle/PaddleDetection
•
•
In this report, we present PP-YOLOE, an industrial state-of-the-art object detector with high performance and friendly deployment.
No Blind Spots: Full-Surround Multi-Object Tracking for Autonomous Vehicles using Cameras & LiDARs
In this paper, we present a modular framework for tracking multiple objects (vehicles), capable of accepting object proposals from different sensor modalities (vision and range) and a variable number of sensors, to produce continuous object tracks.
Real-time Multiple People Tracking with Deeply Learned Candidate Selection and Person Re-Identification
longcw/MOTDT
•
•
Online multi-object tracking is a fundamental problem in time-critical video analysis applications.
Online Multi-Object Tracking Framework with the GMPHD Filter and Occlusion Group Management
In this paper, we propose an efficient online multi-object tracking framework based on the GMPHD filter and occlusion group management scheme where the GMPHD filter utilizes hierarchical data association to reduce the false negatives caused by miss detection.
GCNNMatch: Graph Convolutional Neural Networks for Multi-Object Tracking via Sinkhorn Normalization
This new paradigm enables the network to leverage the "context" information of the geometry of objects and allows us to model the interactions among the features of multiple objects.
Large-Scale Pre-training for Person Re-identification with Noisy Labels
dengpanfu/luperson-nl
•
•
CVPR 2022
Since theses ID labels automatically derived from tracklets inevitably contain noises, we develop a large-scale Pre-training framework utilizing Noisy Labels (PNL), which consists of three learning modules: supervised Re-ID learning, prototype-based contrastive learning, and label-guided contrastive learning.
Hybrid-SORT: Weak Cues Matter for Online Multi-Object Tracking
Also, our method shows strong generalization for diverse trackers and scenarios in a plug-and-play and training-free manner.
Online multi-object tracking via robust collaborative model and sample selection
For each frame, we construct an association between detections and trackers, and treat each detected image region as a key sample, for online update, if it is associated to a tracker.
Beyond Pixels: Leveraging Geometry and Shape Cues for Online Multi-Object Tracking
This paper introduces geometry and object shape and pose costs for multi-object tracking in urban driving scenarios.
Tracking by Animation: Unsupervised Learning of Multi-Object Attentive Trackers
zhen-he/tracking-by-animation
•
•
CVPR 2019
To achieve both label-free and end-to-end learning of MOT, we propose a Tracking-by-Animation framework, where a differentiable neural model first tracks objects from input frames and then animates these objects into reconstructed frames.
