Multi-Object Tracking
174 papers with code • 17 benchmarks • 30 datasets
Multi-Object Tracking is a task in computer vision that involves detecting and tracking multiple objects within a video sequence. The goal is to identify and locate objects of interest in each frame and then associate them across frames to keep track of their movements over time. This task is challenging due to factors such as occlusion, motion blur, and changes in object appearance, and is typically solved using algorithms that integrate object detection and data association techniques.
Benchmarks
These leaderboards are used to track progress in Multi-Object Tracking
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Multi-Object Tracking models and implementations
KITTI
BDD100K
MOT17
MOTChallenge
MOT16
Virtual KITTI
UAVDT
MOT15
DanceTrack
TAO
Subtasks
Most implemented papers
Simple Online and Realtime Tracking
abewley/sort
•
•
This paper explores a pragmatic approach to multiple object tracking where the main focus is to associate objects efficiently for online and realtime applications.
FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking
ifzhang/FairMOT
•
•
Formulating MOT as multi-task learning of object detection and re-ID in a single network is appealing since it allows joint optimization of the two tasks and enjoys high computation efficiency.
Towards Real-Time Multi-Object Tracking
Zhongdao/Towards-Realtime-MOT
•
•
ECCV 2020
In this paper, we propose an MOT system that allows target detection and appearance embedding to be learned in a shared model.
Tracking without bells and whistles
phil-bergmann/tracking_wo_bnw
•
•
ICCV 2019
Therefore, we motivate our approach as a new tracking paradigm and point out promising future research directions.
StrongSORT: Make DeepSORT Great Again
As a result, the construction of a good baseline for a fair comparison is essential.
ByteTrack: Multi-Object Tracking by Associating Every Detection Box
ifzhang/ByteTrack
•
•
arXiv 2021
ByteTrack also achieves state-of-the-art performance on MOT20, HiEve and BDD100K tracking benchmarks.
MOT16: A Benchmark for Multi-Object Tracking
PaddlePaddle/PaddleDetection
•
•
Recently, a new benchmark for Multiple Object Tracking, MOTChallenge, was launched with the goal of collecting existing and new data and creating a framework for the standardized evaluation of multiple object tracking methods.
Tracking Objects as Points
xingyizhou/CenterTrack
•
•
ECCV 2020
Nowadays, tracking is dominated by pipelines that perform object detection followed by temporal association, also known as tracking-by-detection.
Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Tracking
Instead of relying only on the linear state estimate (i. e., estimation-centric approach), we use object observations (i. e., the measurements by object detector) to compute a virtual trajectory over the occlusion period to fix the error accumulation of filter parameters during the occlusion period.
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.
