This is the code of MRDet: A Multihead Network for Accurate Rotated Object Detection in Aerial Images(https://ieeexplore.ieee.org/document/9555822).

The master branch works with PyTorch 1.1 or higher.

MRDet is based on mmdetection and AerialDetection(https://github.com/dingjiansw101/AerialDetection).

This project is released under the Apache 2.0 license.

You can find detailed configs in configs/mrdet.

The trained models are available at Baidu Drive (2lx5) and Google Drive.

Please refer to INSTALL.md for installation and dataset preparation.

Please see GETTING_STARTED.md for the basic usage of MMDetection.

If you use this toolbox or benchmark in your research, please cite this project.

@ARTICLE{MrDet,
  author={Qin, Ran and Liu, Qingjie and Gao, Guangshuai and Huang, Di and Wang, Yunhong},
  journal={IEEE Transactions on Geoscience and Remote Sensing}, 
  title={MRDet: A Multihead Network for Accurate Rotated Object Detection in Aerial Images}, 
  year={2022},
  volume={60},
  pages={1-12},
  doi={10.1109/TGRS.2021.3113473}}