Awesome
<!-- Improved compatibility of back to top link: See: https://github.com/ZHU-Zhiyu/High-Rank_RGB-Event_Tracker/pull/73 --><a name="readme-top"></a>
<!-- [![MyHomePage][linkedin-shield]][linkedin-url] --> <!-- PROJECT LOGO --> <br /> <div align="center"> <a href="https://github.com/ZHU-Zhiyu/High-Rank_RGB-Event_Tracker"> <img src="images/Tracker.png" alt="Logo" width="450" height="220"> </a> <h3 align="center">Cross-modal Orthogonal High-rank Augmentation for RGB-Event Transformer-trackers</h3> <h3 align="center">[ICCV 2023]</h3> <p align="center"> <a href="https://arxiv.org/abs/2307.04129">Paper</a> · <a href="https://github.com/ZHU-Zhiyu/High-Rank_RGB-Event_Tracker/issues">Report Bug</a> · <a href="https://github.com/ZHU-Zhiyu/High-Rank_RGB-Event_Tracker/issues">Request Feature</a> </p> </div> <br /> <div align="center"> <!-- <a href="https://github.com/ZHU-Zhiyu/High-Rank_RGB-Event_Tracker"> --> <img src="./images/CM_Tracking_022.gif" alt="Logo" width="250" height="180" > <img src="./images/CM_Tracking_011.gif" alt="Logo" width="250" height="180" > <img src="./images/CM_Tracking_032.gif" alt="Logo" width="250" height="180" > <!-- </a> --> <h6 align="center">Demos </h6> </div> <details> <summary>Table of Contents</summary> <ol> <li> <a href="#getting-started">Getting Started</a> <ul> <li><a href="#prerequisites">Prerequisites</a></li> <li><a href="#installation">Installation</a></li> <li><a href="#training">Training</a></li> <li><a href="#evaluation">Evaluation</a></li> </ul> </li> <!-- <li><a href="#usage">Usage</a></li> --> <!-- <li><a href="#roadmap">Roadmap</a></li> --> <!-- <li><a href="#contributing">Contributing</a></li> --> <li><a href="#license">License</a></li> <li><a href="#contact">Contact</a></li> <li><a href="#acknowledgments">Acknowledgments</a></li> </ol> </details> <!-- ABOUT THE PROJECT ## About The Project [![Product Name Screen Shot][product-screenshot]](https://example.com) There are many great README templates available on GitHub; however, I didn't find one that really suited my needs so I created this enhanced one. I want to create a README template so amazing that it'll be the last one you ever need -- I think this is it. Here's why: * Your time should be focused on creating something amazing. A project that solves a problem and helps others * You shouldn't be doing the same tasks over and over like creating a README from scratch * You should implement DRY principles to the rest of your life :smile: Of course, no one template will serve all projects since your needs may be different. So I'll be adding more in the near future. You may also suggest changes by forking this repo and creating a pull request or opening an issue. Thanks to all the people have contributed to expanding this template! Use the `BLANK_README.md` to get started. <p align="right">(<a href="#readme-top">back to top</a>)</p> ### Built With This section should list any major frameworks/libraries used to bootstrap your project. Leave any add-ons/plugins for the acknowledgements section. Here are a few examples. * [![Next][Next.js]][Next-url] * [![React][React.js]][React-url] * [![Vue][Vue.js]][Vue-url] * [![Angular][Angular.io]][Angular-url] * [![Svelte][Svelte.dev]][Svelte-url] * [![Laravel][Laravel.com]][Laravel-url] * [![Bootstrap][Bootstrap.com]][Bootstrap-url] * [![JQuery][JQuery.com]][JQuery-url] <p align="right">(<a href="#readme-top">back to top</a>)</p> --> <!-- GETTING STARTED -->Getting Started
<!-- This is an example of how you may give instructions on setting up your project locally. To get a local copy up and running follow these simple example steps. -->Prerequisites
- clone the project
git clone https://github.com/ZHU-Zhiyu/High-Rank_RGB-Event_Tracker.git
- FE108
* Download data from FE108
* Transfer and clip data into h5py format
sh python ./Utils/Evt_convert.py
The directory should have the below format:
<details open> <summary>Format of FE108 (click to expand)</summary>
```Shell
├── FE108 dataset (108 sequences)
├── airplane
├── inter3_stack
├── 0001_1.jpg
├── 0001_2.jpg
├── 0001_3.jpg
├── 0002_1.jpg
├── ...
├── img
├── 0001.jpg
├── 0002.jpg
├── ...
├── events.aedat4
├── groundtruth_rect.txt
├── airplane_motion
├── ...
├── ...
├── Event file(108 sequences)
├── airplane.h5
├── airplane_motion.h5
├── ...
```
</details>
3. COESOT
* Download data from COESOT
* Transfer and clip data into mat files
sh python ./COESOT/data.py
The directory should have the below format:
<details open> <summary>Format of COESOT (click to expand)</summary>
```Shell
├── COESOT dataset
├── Training Subset (827 sequences)
├── dvSave-2021_09_01_06_59_10
├── dvSave-2021_09_01_06_59_10.aedat4
├── groundtruth.txt
├── absent.txt
├── start_end_index.txt
├── ...
├── trainning voxel (827 sequences)
├── dvSave-2022_03_21_09_05_49
├── dvSave-2022_03_21_09_05_49_voxel
├── frame0000.mat
├── frame0001.mat
├── ...
├── ...
├── Testing Subset (528 sequences)
├── dvSave-2021_07_30_11_04_12
├── dvSave-2021_07_30_11_04_12_aps
├── dvSave-2021_07_30_11_04_12_dvs
├── dvSave-2021_07_30_11_04_12.aedat4
├── groundtruth.txt
├── absent.txt
├── start_end_index.txt
├── ...
├── testing voxel (528 sequences)
├── dvSave-2022_03_21_11_12_27
├── dvSave-2022_03_21_11_12_27_voxel
├── frame0000.mat
├── frame0001.mat
├── ...
├── ...
```
</details>
Installation
-
One-stream tracker: CEUTrack
conda create -n CEUTrack python==3.8 conda activate CEUTrack cd ./CEUTrack sh install.sh
-
Two-streams tracker: MonTrack
conda create -n montrack python==3.8 conda activate montrack cd ./MonTrack conda install -c pytorch pytorch=1.5 torchvision=0.6.1 cudatoolkit=10.2 conda install matplotlib pandas tqdm pip install opencv-python tb-nightly visdom scikit-image tikzplotlib gdown conda install cython scipy sudo apt-get install libturbojpeg pip install pycocotools jpeg4py pip install wget yacs pip install shapely==1.6.4.post2 python -c "from pytracking.evaluation.environment import create_default_local_file; create_default_local_file()" python -c "from ltr.admin.environment import create_default_local_file; create_default_local_file()"
Then install KNN_CUDA
Training
-
One-stream tracker: CEUTrack
cd CEUTrack sh train.sh
-
Two-streams tracker: MonTrack download SwinV2 Tiny/Base and put them into
./ltr/checkpoint
Then run the following code
cd ./MonTrack/ltr sh train.sh
Evaluation
<br /> <div align="center"> <a href="https://github.com/ZHU-Zhiyu/High-Rank_RGB-Event_Tracker"> <img src="images/FE108.png" alt="Logo" width="300" height="380"> <img src="images/COESOT.png" alt="Logo" width="300" height="380"> </a> <!-- <h6 align="center">Demos </h6> --> </div> <br /> <div align="center"> <a href="https://github.com/ZHU-Zhiyu/High-Rank_RGB-Event_Tracker"> <img src="images/Performance.png" alt="Logo" width="700" height="400"> </a> <!-- <h6 align="center">Demos </h6> --> </div>Download pretrained weights Google Drive baidu:coming soon
-
One stream tracker: MonTrack
sh eval.sh
Then install KNN_CUDA
-
Two-streams tracker: CEUTrack
sh eval.sh
License
Distributed under the MIT License. See LICENSE.txt
for more information.
Contact
Email - Zhu Zhiyu
<p align="right">(<a href="#readme-top">back to top</a>)</p> <!-- ACKNOWLEDGMENTS -->Acknowledgments
Thanks to FE108, COESOT datasets, TransT and OsTrack.
If you find the project is interesting, please cite
@article{zhu2023cross,
title={Cross-modal Orthogonal High-rank Augmentation for RGB-Event Transformer-trackers},
author={Zhu, Zhiyu and Hou, Junhui and Wu, Dapeng Oliver},
journal={International Conference on Computer Vision},
year={2023}
}
@article{zhu2022learning,
title={Learning Graph-embedded Key-event Back-tracing for Object Tracking in Event Clouds},
author={Zhu, Zhiyu and Hou, Junhui and Lyu, Xianqiang},
journal={Advances in Neural Information Processing Systems},
volume={35},
pages={7462--7476},
year={2022}
}
Template from othneildrew.
<p align="right">(<a href="#readme-top">back to top</a>)</p> <!-- MARKDOWN LINKS & IMAGES --> <!-- https://www.markdownguide.org/basic-syntax/#reference-style-links -->