By Chuang Niu, Qiuju Yang, Shenghan Ren, Haihong Hu, Desheng Han, Zejun Hu, and Jimin Liang.
A fully automatic method for computing auroral arc width based on Marsk R-CNN is implemented in this project, and the related paper is submitted to GRSL. More details will be described.
This project is based on Mask R-CNN, PyTorch 1.0, and Python 3.5.
- Install the Mask R-CNN benchmark.
- Replace the maskrcnn-benchmark with the aurora-maskrcnn in this project.
-
git clone https://github.com/niuchuangnn/aurora-maskrcnn.git cd ~/aurora-maskrcnn python3 setup.py build develop
Run demo:
cd ~/aurora-maskrcnn
python3 ./Aurora/demo.py
It will output the following results:
- Original image:
- Detection results of one-stage inference process:
- Detection results of rotated image:
- Detection results of two-stage inference process:
- Predicted normal of aurora arcs:
- Intensity vs. zenith-angle curve:
maskrcnn-benchmark is released under the MIT license. See LICENSE for additional details.