Metadata-Version: 2.4
Name: tno.quantum.problems.mot
Version: 1.0.1
Summary: Quantum algorithms for multi-object tracking
Author-email: TNO Quantum Code Lab <tnoquantum@tno.nl>
Maintainer-email: TNO Quantum Code Lab <tnoquantum@tno.nl>
License: Apache License, Version 2.0
Project-URL: Homepage, https://github.com/TNO-Quantum/
Project-URL: Documentation, https://github.com/TNO-Quantum/documentation
Project-URL: Source, https://github.com/TNO-Quantum/problems.mot
Keywords: quantum, multi-object tracking, mot
Platform: any
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Programming Language :: Python :: 3.14
Classifier: Operating System :: OS Independent
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Information Technology
Classifier: Intended Audience :: Science/Research
Classifier: Typing :: Typed
Requires-Python: >=3.10
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: lap>=0.5.12
Requires-Dist: ultralytics~=8.3
Requires-Dist: scipy>=1.15
Requires-Dist: imageio
Requires-Dist: pandas
Requires-Dist: tno.quantum.optimization.qubo[dwave]
Provides-Extra: tests
Requires-Dist: pytest>=8.1.1; extra == "tests"
Requires-Dist: pytest-cov>=4.1.0; extra == "tests"
Dynamic: license-file

# TNO Quantum - MOT - Multi Object Tracking

This repository provides a Re-Identification (Re-ID) post-processing algorithm designed to enhance Multi-Object Tracking (MOT) pipelines. It is specifically intended to pair with Ultralytics YOLO trackers or similar object detection frameworks and leverages quantum-enhanced techniques and Binary Linear Programming (BLP) methods for advanced post-processing.

The goal of this module is to resolve identity switches and improve tracking consistency across frames by applying advanced optimization techniques after the initial tracking stage. While Ultralytics provides robust detection and tracking, identity consistency can degrade in challenging scenarios such as occlusions, crowded scenes, or long-term tracking. This algorithm addresses those issues through network flow optimization and QUBO-based formulations.

This work was carried out in collaboration with Wageningen University. 

This work is supported by the Dutch National Growth Fund (NGF) as part of the Quantum Delta NL programme.

## Documentation

Documentation and usage examples of the `tno.quantum.problems.mot` package can be found [here](https://tno-quantum.github.io/documentation/).

## Usage

Basic usage examples can be found in [the documentation](https://tno-quantum.github.io/documentation/content/problems/packages/tno.quantum.problems.mot/main.html). A more advanced example showing how the package can be combined with ultralytics can be found [here](https://tno-quantum.github.io/documentation/content/examples/multi_object_tracking.html). An example output is the following

Before re-id:
![til](./src/tno/quantum/problems/mot/dataset/before.gif)

After re-id:
![til](./src/tno/quantum/problems/mot/dataset/after.gif)

## (End)use limitations

The content of this software may solely be used for applications that comply with international export control laws.
