https://github.com/roboflow/trackers
A unified library for object tracking featuring clean room re-implementations of leading multi-object tracking algorithms
https://github.com/roboflow/trackers
deep-sort multi-object-tracking reidentification sort
Last synced: 9 months ago
JSON representation
A unified library for object tracking featuring clean room re-implementations of leading multi-object tracking algorithms
- Host: GitHub
- URL: https://github.com/roboflow/trackers
- Owner: roboflow
- License: apache-2.0
- Created: 2025-04-14T16:12:26.000Z (11 months ago)
- Default Branch: main
- Last Pushed: 2025-06-10T20:33:40.000Z (9 months ago)
- Last Synced: 2025-06-10T21:38:46.677Z (9 months ago)
- Topics: deep-sort, multi-object-tracking, reidentification, sort
- Language: Python
- Homepage: https://roboflow.github.io/trackers
- Size: 2.67 MB
- Stars: 1,755
- Watchers: 21
- Forks: 149
- Open Issues: 14
-
Metadata Files:
- Readme: README.md
- Contributing: CONTRIBUTING.md
- License: LICENSE
- Code of conduct: CODE_OF_CONDUCT.md
- Codeowners: .github/CODEOWNERS
Awesome Lists containing this project
- StarryDivineSky - roboflow/trackers
- awesome-repositories - roboflow/trackers - Trackers gives you clean, modular re-implementations of leading multi-object tracking algorithms released under the permissive Apache 2.0 license. You combine them with any detection model you already (Python)
- AiTreasureBox - roboflow/trackers - 02-24_2863_19](https://img.shields.io/github/stars/roboflow/trackers.svg)|Trackers gives you clean, modular re-implementations of leading multi-object tracking algorithms released under the permissive Apache 2.0 license. You combine them with any detection model you already use.| (Repos)
README
trackers
[](https://badge.fury.io/py/trackers)
[](https://pypistats.org/packages/trackers)
[](https://github.com/roboflow/trackers/blob/main/LICENSE.md)
[](https://badge.fury.io/py/trackers)
[](https://colab.research.google.com/drive/1VT_FYIe3kborhWrfKKBqqfR0EjQeQNiO?usp=sharing)
[](https://discord.gg/GbfgXGJ8Bk)
## Hello
`trackers` is a unified library offering clean room re-implementations of leading multi-object tracking algorithms. Its modular design allows you to easily swap trackers and integrate them with object detectors from various libraries like `inference`, `ultralytics`, or `transformers`.
Tracker
Paper
MOTA
Year
Status
Colab
SORT
74.6
2016
✅
DeepSORT
75.4
2017
✅
ByteTrack
77.8
2021
🚧
🚧
OC-SORT
75.9
2022
🚧
🚧
BoT-SORT
77.8
2022
🚧
🚧
https://github.com/user-attachments/assets/eef9b00a-cfe4-40f7-a495-954550e3ef1f
## Installation
Pip install the `trackers` package in a [**Python>=3.9**](https://www.python.org/) environment.
```bash
pip install trackers
```
install from source
By installing `trackers` from source, you can explore the most recent features and enhancements that have not yet been officially released. Please note that these updates are still in development and may not be as stable as the latest published release.
```bash
pip install git+https://github.com/roboflow/trackers.git
```
## Quickstart
With a modular design, `trackers` lets you combine object detectors from different libraries with the tracker of your choice. Here's how you can use `SORTTracker` with various detectors:
```python
import supervision as sv
from trackers import SORTTracker
from inference import get_model
tracker = SORTTracker()
model = get_model(model_id="yolov11m-640")
annotator = sv.LabelAnnotator(text_position=sv.Position.CENTER)
def callback(frame, _):
result = model.infer(frame)[0]
detections = sv.Detections.from_inference(result)
detections = tracker.update(detections)
return annotator.annotate(frame, detections, labels=detections.tracker_id)
sv.process_video(
source_path="",
target_path="",
callback=callback,
)
```
run with ultralytics
```python
import supervision as sv
from trackers import SORTTracker
from ultralytics import YOLO
tracker = SORTTracker()
model = YOLO("yolo11m.pt")
annotator = sv.LabelAnnotator(text_position=sv.Position.CENTER)
def callback(frame, _):
result = model(frame)[0]
detections = sv.Detections.from_ultralytics(result)
detections = tracker.update(detections)
return annotator.annotate(frame, detections, labels=detections.tracker_id)
sv.process_video(
source_path="",
target_path="",
callback=callback,
)
```
run with transformers
```python
import torch
import supervision as sv
from trackers import SORTTracker
from transformers import RTDetrV2ForObjectDetection, RTDetrImageProcessor
tracker = SORTTracker()
image_processor = RTDetrImageProcessor.from_pretrained("PekingU/rtdetr_v2_r18vd")
model = RTDetrV2ForObjectDetection.from_pretrained("PekingU/rtdetr_v2_r18vd")
annotator = sv.LabelAnnotator(text_position=sv.Position.CENTER)
def callback(frame, _):
inputs = image_processor(images=frame, return_tensors="pt")
with torch.no_grad():
outputs = model(**inputs)
h, w, _ = frame.shape
results = image_processor.post_process_object_detection(
outputs,
target_sizes=torch.tensor([(h, w)]),
threshold=0.5
)[0]
detections = sv.Detections.from_transformers(
transformers_results=results,
id2label=model.config.id2label
)
detections = tracker.update(detections)
return annotator.annotate(frame, detections, labels=detections.tracker_id)
sv.process_video(
source_path="",
target_path="",
callback=callback,
)
```
## License
The code is released under the [Apache 2.0 license](https://github.com/roboflow/trackers/blob/main/LICENSE).
## Contribution
We welcome all contributions—whether it’s reporting issues, suggesting features, or submitting pull requests. Please read our [contributor guidelines](https://github.com/roboflow/trackers/blob/main/CONTRIBUTING.md) to learn about our processes and best practices.