Home

Awesome

Open In Colab

<!-- PROJECT SUMMARY --> <p align="center"> <img src="src/image.classification.on.EuroSAT.jpg" align="center" alt="Readme Template" /> <h2 align="center">Image Classification on EuroSAT</h2> <h4 align="center">PyTorch Implementation</h4> <p align="center"> <strong> <a href="https://colab.research.google.com/github/canturan10/image.classification.on.EuroSAT/blob/master/notebooks/image_classification_on_EuroSAT.ipynb">Notebook</a> </strong> </p>

-----------------------------------------------------

<p align="center"> <p align="center"><strong> !! New Framework Released for Satellite Image Classification !!</strong></p> <p align="center"><strong> <a href="https://github.com/canturan10/satellighte">satellighte: PyTorch Lightning Implementations of Recent Satellite Image Classification ! </a></strong></p>

-----------------------------------------------------

<!-- TABLE OF CONTENTS --> <details> <summary> <strong> TABLE OF CONTENTS </strong> </summary> <ol> <li> <a href="#about">About</a> </li> <li><a href="#license">License</a></li> <li><a href="#references">References</a></li> <li><a href="#citations">Citations</a></li> </ol> </details> <!-- ABOUT THE PROJECT -->

About

EuroSAT is a large-scale land use and land cover classification dataset derived from multispectral Sentinel-2 satellite imagery covering European continent. EuroSAT is composed of 27,000 georeferenced image patches (64 x 64 pixels) - each patch comprises 13 spectral bands (optical through to shortwave infrared ) resampled to 10m spatila resolution and labelled with one of 10 distinct land cover classes: AnnualCrop, Forest, HerbaceousVegetation, Highway, Industrial, Pasture, PermanentCrop, Residential, River, SeaLake. Full details including links to journal papers and download instructions may be found here: https://github.com/phelber/eurosat.

Source: eurosat-github-page

<!-- LICENSE -->

License

This project is licensed under MIT license. See LICENSE for more information.

<!-- REFERENCES -->

References

The references used in the development of the project are as follows.

<!-- CITATIONS -->

Citations

@article{helber2019eurosat,
  title={Eurosat: A novel dataset and deep learning benchmark for land use and land cover classification},
  author={Helber, Patrick and Bischke, Benjamin and Dengel, Andreas and Borth, Damian},
  journal={IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing},
  year={2019},
  publisher={IEEE}
}

@inproceedings{helber2018introducing,
  title={Introducing EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification},
  author={Helber, Patrick and Bischke, Benjamin and Dengel, Andreas and Borth, Damian},
  booktitle={IGARSS 2018-2018 IEEE International Geoscience and Remote Sensing Symposium},
  pages={204--207},
  year={2018},
  organization={IEEE}
}
<!-- You can find more line options at https://github.com/canturan10/readme-template/tree/master/src -->

Give a ⭐️ if this project helped you! ----------------------------------------------------- This readme file is made using the readme-template