Home

Awesome

<div align="center"> <img src="resources/opencd-logo.png" width="600"/> </div>
<div align="center"> <a href="https://arxiv.org/abs/2407.15317"><img src="https://hits.seeyoufarm.com/api/count/incr/badge.svg?url=https%3A%2F%2Farxiv.org%2Fabs%2F2407.15317&count_bg=%23FF0000&title_bg=%23555555&icon=arxiv.svg&icon=&icon_color=%23E7E7E7&title=Technical+Report&edge_flat=false"/></a> <a href="https://github.com/likyoo/open-cd"><img src="https://hits.seeyoufarm.com/api/count/incr/badge.svg?url=https%3A%2F%2Fgithub.com%2Flikyoo%2Fopen-cdA&count_bg=%2379C83D&title_bg=%23555555&icon=github.svg&icon_color=%23E7E7E7&title=Github&edge_flat=false"/></a> <a href="https://huggingface.co/likyoo/Open-CD_Model_Zoo"><img src="https://hits.seeyoufarm.com/api/count/incr/badge.svg?url=https%3A%2F%2Fhuggingface.co%2Flikyoo%2FOpen-CD_Model_Zoo&count_bg=%23684BD3&title_bg=%23555555&icon=&icon_color=%23E7E7E7&title=%F0%9F%A4%97%20Hugging%20Face&edge_flat=false"/></a> </div>

Introduction

Open-CD is an open source change detection toolbox based on a series of open source general vision task tools.

News

Benchmark and model zoo

Supported toolboxes:

Supported change detection model: (The code of some models are borrowed directly from their official repositories.)

Supported datasets: | Descriptions

Usage

Docs

Please refer to get_started.md in mmseg.

A Colab tutorial is also provided. You may directly run on Colab. (thanks to @Agustin for this demo) Colab

Install

# Install OpenMMLab Toolkits as Python packages
pip install -U openmim
mim install mmengine
mim install "mmcv>=2.0.0"
mim install "mmpretrain>=1.0.0rc7"
pip install "mmsegmentation>=1.2.2"
pip install "mmdet>=3.0.0"
git clone https://github.com/likyoo/open-cd.git
cd open-cd
pip install -v -e .

For more details, please see here.

Train

python tools/train.py configs/changer/changer_ex_r18_512x512_40k_levircd.py --work-dir ./changer_r18_levir_workdir

Test

# get .png results
python tools/test.py configs/changer/changer_ex_r18_512x512_40k_levircd.py changer_r18_levir_workdir/latest.pth --show-dir tmp_infer
# get metrics
python tools/test.py configs/changer/changer_ex_r18_512x512_40k_levircd.py changer_r18_levir_workdir/latest.pth

Infer

Please refer inference doc.

Citation

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

@article{opencd,
  title   = {{Open-CD}: A Comprehensive Toolbox for Change Detection},
  author  = {Li, Kaiyu and Jiang, Jiawei and Codegoni, Andrea and Han, Chengxi and Deng, Yupeng and Chen, Keyan and Zheng, Zhuo and
             Chen, Hao and Zou, Zhengxia and Shi, Zhenwei and Fang, Sheng and Meng, Deyu and Wang, Zhi and Cao, Xiangyong},
  journal= {arXiv preprint arXiv:2407.15317},
  year={2024}
}

You might also consider citing:

@ARTICLE{10438490,
  author={Li, Kaiyu and Cao, Xiangyong and Meng, Deyu},
  journal={IEEE Transactions on Geoscience and Remote Sensing}, 
  title={A New Learning Paradigm for Foundation Model-based Remote Sensing Change Detection}, 
  year={2024},
  volume={},
  number={},
  pages={1-1},
  keywords={Adaptation models;Task analysis;Data models;Computational modeling;Feature extraction;Transformers;Tuning;Change detection;foundation model;visual tuning;remote sensing image processing;deep learning},
  doi={10.1109/TGRS.2024.3365825}}

@ARTICLE{10129139,
  author={Fang, Sheng and Li, Kaiyu and Li, Zhe},
  journal={IEEE Transactions on Geoscience and Remote Sensing}, 
  title={Changer: Feature Interaction is What You Need for Change Detection}, 
  year={2023},
  volume={61},
  number={},
  pages={1-11},
  doi={10.1109/TGRS.2023.3277496}}

License

Open-CD is released under the Apache 2.0 license.