The repository is a code implementation of DAFNet. Since the dataset is private, we only provide the code. We provide an implementation based on Faster R-CNN, and other detection methods can be implemented with minor changes.
The configurations of all fusion methods can be found in ./DAFNet_configs
where: ./DAFNet_configs/DAFNet_faster_rcnn_AFF.py is our DAFNet
You can prepare the environment by following steps:
conda create -n DAFNet python=3.9 -y
conda activate DAFNet
pip install torch==1.10.1+cu102
pip install torchvision==0.11.2
pip install -r requirements/build.txt
pip install mmcv-full
pip install tifffile
python setup.py develop
Please follow the guidance of MMDetection
If you use this toolbox or benchmark in your research, please cite this project.
@ARTICLE{10081347,
author={Huang, Ziyue and Liu, Qingjie and Zhou, Huanyu and Gao, Guangshuai and Xu, Tao and Wen, Qi and Wang, Yunhong},
journal={IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing},
title={Building Detection from Panchromatic and Multi-spectral Images with Dual-stream Asymmetric Fusion Networks},
year={2023},
volume={},
number={},
pages={1-14},
doi={10.1109/JSTARS.2023.3261866}}
@article{mmdetection,
title = {{MMDetection}: Open MMLab Detection Toolbox and Benchmark},
author = {Chen, Kai and Wang, Jiaqi and Pang, Jiangmiao and Cao, Yuhang and
Xiong, Yu and Li, Xiaoxiao and Sun, Shuyang and Feng, Wansen and
Liu, Ziwei and Xu, Jiarui and Zhang, Zheng and Cheng, Dazhi and
Zhu, Chenchen and Cheng, Tianheng and Zhao, Qijie and Li, Buyu and
Lu, Xin and Zhu, Rui and Wu, Yue and Dai, Jifeng and Wang, Jingdong
and Shi, Jianping and Ouyang, Wanli and Loy, Chen Change and Lin, Dahua},
journal= {arXiv preprint arXiv:1906.07155},
year={2019}
}