English | 简体中文

Documentation: https://mmtracking.readthedocs.io/

Introduction

MMTracking is an open source video perception toolbox based on PyTorch. It is a part of the OpenMMLab project.

The master branch works with PyTorch1.5+.

Major features

• The First Unified Video Perception Platform

  We are the first open source toolbox that unifies versatile video perception tasks include video object detection, multiple object tracking, single object tracking and video instance segmentation.

• Modular Design

  We decompose the video perception framework into different components and one can easily construct a customized method by combining different modules.

• Simple, Fast and Strong

  Simple: MMTracking interacts with other OpenMMLab projects. It is built upon MMDetection that we can capitalize any detector only through modifying the configs.

  Fast: All operations run on GPUs. The training and inference speeds are faster than or comparable to other implementations.

  Strong: We reproduce state-of-the-art models and some of them even outperform the official implementations.

License

This project is released under the Apache 2.0 license.

Changelog

Release ByteTrack pretrained models.

v0.9.0 was released in 05/01/2022. Please refer to changelog.md for details and release history.

Benchmark and model zoo

Results and models are available in the model zoo.

Supported methods of video object detection:

• DFF (CVPR 2017)
• FGFA (ICCV 2017)
• SELSA (ICCV 2019)
• Temporal RoI Align (AAAI 2021)

Supported methods of multi object tracking:

• SORT/DeepSORT (ICIP 2016/2017)
• Tracktor (ICCV 2019)
• ByteTrack (arXiv 2021)

Supported methods of single object tracking:

• SiameseRPN++ (CVPR 2019)
• STARK (ICCV 2021) (WIP)

Supported methods of video instance segmentation:

• MaskTrack R-CNN (ICCV 2019)

Installation

Please refer to install.md for install instructions.

Getting Started

Please see dataset.md and quick_run.md for the basic usage of MMTracking. We also provide usage tutorials, such as learning about configs, an example about detailed description of vid config, an example about detailed description of mot config, an example about detailed description of sot config, customizing dataset, customizing data pipeline, customizing vid model, customizing mot model, customizing sot model, customizing runtime settings and useful tools.

Contributing

We appreciate all contributions to improve MMTracking. Please refer to CONTRIBUTING.md for the contributing guideline.

Acknowledgement

MMTracking is an open source project that welcome any contribution and feedback. We wish that the toolbox and benchmark could serve the growing research community by providing a flexible as well as standardized toolkit to reimplement existing methods and develop their own new video perception methods.

Citation

If you find this project useful in your research, please consider cite:

@misc{mmtrack2020,
    title={{MMTracking: OpenMMLab} video perception toolbox and benchmark},
    author={MMTracking Contributors},
    howpublished = {\url{https://github.com/open-mmlab/mmtracking}},
    year={2020}
}

Projects in OpenMMLab

• MMCV: OpenMMLab foundational library for computer vision.
• MIM: MIM Installs OpenMMLab Packages.
• MMClassification: OpenMMLab image classification toolbox and benchmark.
• MMDetection: OpenMMLab detection toolbox and benchmark.
• MMDetection3D: OpenMMLab's next-generation platform for general 3D object detection.
• MMSegmentation: OpenMMLab semantic segmentation toolbox and benchmark.
• MMAction2: OpenMMLab's next-generation action understanding toolbox and benchmark.
• MMTracking: OpenMMLab video perception toolbox and benchmark.
• MMPose: OpenMMLab pose estimation toolbox and benchmark.
• MMEditing: OpenMMLab image and video editing toolbox.
• MMOCR: OpenMMLab text detection, recognition and understanding toolbox.
• MMGeneration: OpenMMLab Generative Model toolbox and benchmark.
• MMFlow: OpenMMLab optical flow toolbox and benchmark.
• MMFewShot: OpenMMLab FewShot Learning Toolbox and Benchmark.
• MMHuman3D: OpenMMLab Human Pose and Shape Estimation Toolbox and Benchmark.
• MMSelfSup: OpenMMLab self-supervised learning Toolbox and Benchmark.
• MMRazor: OpenMMLab Model Compression Toolbox and Benchmark.
• MMDeploy: OpenMMlab deep learning model deployment toolset.