https://github.com/khdlr/hed-unet

Simultaneous Semantic Segmentation and Edge Detection
https://github.com/khdlr/hed-unet

Last synced: over 1 year ago
JSON representation

Simultaneous Semantic Segmentation and Edge Detection

• Host: GitHub
• URL: https://github.com/khdlr/hed-unet
• Owner: khdlr
• License: mit
• Created: 2021-02-22T16:15:25.000Z (over 5 years ago)
• Default Branch: master
• Last Pushed: 2024-01-19T12:51:13.000Z (over 2 years ago)
• Last Synced: 2025-03-16T05:31:43.029Z (over 1 year ago)
• Language: Python
• Size: 14.1 MB
• Stars: 98
• Watchers: 3
• Forks: 5
• Open Issues: 2
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# HED-UNet

Code for HED-UNet, a model for simultaneous semantic segmentation and edge detection.

## Glacier Fronts

This model was originally developed to detect calving front margins in Antarctica from Sentinel-1 SAR imagery.

![glaciers](figures/glaciers.jpg)

## Building Footprints

As the original dataset isn't publicly available, this repository contains an adaption of the model for building footprint extraction on the [Inria Aerial Image Labeling dataset](https://project.inria.fr/aerialimagelabeling/). Here are some example results:

##### Bloomington

![bloomington27-overview-binary](figures/bloomington27-overview-binary.jpg)

##### Innsbruck

![innsbruck20-overview-binary](figures/innsbruck20-overview-binary.jpg)

##### San Francisco

![sfo20-overview-binary](figures/sfo20-overview-binary.jpg)

## Usage

In order to use this for your project, you will need adapt either the `get_dataloader` function in `train.py` or the methods in `data_loading.py`.

## Citation

If you find our code helpful and use it in your research, please use the following BibTeX entry.

```tex

@article{HEDUNet2021,

  author={Heidler, Konrad and Mou, Lichao and Baumhoer, Celia and Dietz, Andreas and Zhu, Xiao Xiang},

  journal={IEEE Transactions on Geoscience and Remote Sensing}, 

  title={HED-UNet: Combined Segmentation and Edge Detection for Monitoring the Antarctic Coastline}, 

  year={2021},

  volume={},

  number={},

  pages={1-14},

  doi={10.1109/TGRS.2021.3064606}

}

```