Skip to content
/ MDR-Net Public

The office implementation of MDR-Net: Multi-Directional Rotation-Aware Network for Oriented Ship Detection From Remote Sensing Imagery.

License

Notifications You must be signed in to change notification settings

cowqer/MDR-Net

Repository files navigation

MDR-Net:

Authors: Quan Cui, Yan Zhou*, Gaodian Zhou*, Jianxun Li, Xiaolin Zhu, Richard Irampaye. Multi-Directional Rotation-Aware Network for Oriented Ship Detection From Remote Sensing Imagery(IEEE JSTAR 2025).

Introduction

This is the official implementation of the paper, MDR-Net: Multi-Directional Rotation-Aware Network for Oriented Ship Detection From Remote Sensing Imagery In this paper, we propose a two-stage framework called Multi-Directional and Rotation aware Network(MDR-Net), which consists of three key modules. (1) Gated Pinwheel-shaped Convolution (GPC). The GPC enhances the detection of elongated targets aligned along horizontal and vertical axes by adaptively fusing receptive fields in orthogonal directions. (2) Rotated Convolution module with Attention-guided routing (RCA). RCA constructs a Multi-Scale Convolutional Attention(MSCA) framework to capture rotation angles and weights, then uses rotational convolution kernels to extract the features, to reduce the feature differences in ships caused by varying orientations. (3)Feature-Aligned Oriented Region Proposal Network (FAORPN). To generate proposals that more accurately localize multi-oriented and elongated targets, FAORPN is designed by integrating RCA and GPC through weighted fusion within the ORPN.

The Gated Pinwheel-shaped Convolution

The GPC-R50

The Rotated Convolution module with Attention-guided routing

The Achitecture of MDR-Net

Results and models

DOTA1.0

Model mAP50 mAP75 Batch Size Config Download
ORCNN 75.37 46.05 1×2 config model (pswd: mdrn)
MDR-Net 75.89 48.24 1×2 config model (pswd: mdrn)
MDR-Net (ms) 80.58 56.61 1×2 config model (pswd: mdrn)
RSSDD
Model mAP50 mAP75 Batch Size Config Download
---------- -------- -------- ------------ -------- ----------
MDR-Net 0.8935 41.5 1×2 config model (pswd: mdrn)

Installation

We ued the MMRotate toolbox, which depends on PyTorch, MMCV and MMDetection. Below are quick steps for installation. Please refer to Install Guide for more detailed instruction.

conda create -n open-mmlab python=3.7 pytorch==1.7.0 cudatoolkit=10.1 torchvision -c pytorch -y
conda activate open-mmlab
pip install openmim
mim install mmcv-full
mim install mmdet
git clone https://github.com/open-mmlab/mmrotate.git
cd mmrotate
pip install -r requirements/build.txt
pip install -v -e .

DATA

DOTA: official website
RSSDD: Official-SSDD-OPEN.rar

In the file ./configs/MDR-Net/base/datasets/dota.py or ssdd.py, change the data path following data_root to YOUR_DATA_PATH

Get Started

Please see get_started.md for the basic usage of MMRotate. We provide colab tutorial, and other tutorials for:

Usage

Training

python tools/train.py  configs/MDR-Net/oriented_rcnn_gatedpc_r50_fpn_1x_dota_le90_msca_adp_rpn.py

Test and Submit

python ./tools/test0.py \
configs/MDR-Net/oriented_rcnn_gatedpc_r50_fpn_1x_dota_le90_msca_adp_rpn.py \
YOUR_CHECKPOINT_PATH --eval mAP

python ./tools/test0.py \
configs/oriented_rcnn/oriented_rcnn_gatedpc_r50_fpn_1x_dota_le90_msca_adp_rpn.py \
YOUR_CHECKPOINT_PATH --gpu-ids 0 \
--format-only --eval-options \
submission_dir=YOUR_SAVE_DIR

Cite

@ARTICLE{11226875,
  author={Cui, Quan and Zhou, Yan and Zhou, Gaodian and Li, Jianxun and Zhu, Xiaolin and Irampaye, Richard},
  journal={IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing}, 
  title={Multidirectional Rotation-Aware Network for Oriented Ship Detection From Remote Sensing Imagery}, 
  year={2026},
  volume={19},
  number={},
  pages={190-208},
  keywords={Marine vehicles;Convolution;Feature extraction;Remote sensing;Kernel;Shape;Accuracy;Proposals;Object detection;Attention mechanisms;Oriented object detection;pinwheel-shaped convolution;remote sensing;rotational convolution kernel;ship detection},
  doi={10.1109/JSTARS.2025.3629101}}

Acknowledgement

This code is developed on the top of MMrotate, we thank to their efficient and neat codebase.

About

The office implementation of MDR-Net: Multi-Directional Rotation-Aware Network for Oriented Ship Detection From Remote Sensing Imagery.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages