Delineate Anything: Resolution-Agnostic Field Boundary Delineation on Satellite Imagery

by Mykola Lavreniuk, Nataliia Kussul, Andrii Shelestov, Bohdan Yailymov, Yevhenii Salii, Volodymyr Kuzin, Zoltan Szantoi

Delineate Anything is a resolution-agnostic deep learning framework for accurate agricultural field boundary detection from satellite imagery. Trained on the 22M+ instances in the FBIS-22M dataset, Delineate Anything sets a new SOTA by accurately delineating individual agricultural field boundaries across diverse satellite resolutions and geographic regions.

News

• 2025/11/17: New paper published Delineate Anything Flow: Fast, Country-Level Field Boundary Detection from Any Source arXiv:2511.13417.
• 2025/09/07: 🚀🚀🚀 Autobounds released for convenient field boundary detection with Delineate-Anything, directly in the browser!
  👉 Demo Video | Live App.
• 2025/08/30: 🚀🚀 Our paper on Delineate-Anything accepted at ECAI 2025 🎉.
• 2025/07/07: 🚀 Delineate-Anything integrated into the TorchGeo library.

🔗 Pre-trained Models

Method	mAP@0.5	mAP@0.5:0.95	Latency (ms)	Size	Download
Delineate Anything S	0.632	0.383	16.8	17.6 MB	Download
Delineate Anything	0.720	0.477	25.0	125 MB	Download

⚙️ Environment Setup

To set up the environment on a Linux system:

mkdir -p ~/miniconda3
wget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh -O ~/miniconda3/miniconda.sh
bash ~/miniconda3/miniconda.sh -b -u -p ~/miniconda3
rm ~/miniconda3/miniconda.sh

source ~/miniconda3/bin/activate
conda install -c conda-forge gdal

# optional: pip install torch==2.6.0
pip install -r requirements.txt

To set up the environment on a Windows system:

conda create --prefix=./.conda python=3.11
conda activate ./.conda
conda install -c conda-forge gdal
# optional: pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu128
pip install -r requirements.txt

🚀 Inference

💡 Try the Colab demo first, no installation needed, or run locally if you prefer full control.

1. Place your RGB images in the data/images/ folder. If available, also include the corresponding land cover map in the data/masks/ (Three Sentinel-2 sample images and a land cover map are provided for testing.)

2. Run the inference script:

   python delineate.py -b batch_sample.yaml
   

   The vectorized field boundaries will be saved as a GeoPackage in: data/delineated/

3. (Optional) To shift the resulting vector geometries:

   Shift using image pixels:

   python shift.py -i PATH_TO_SRC_GPKG -o PATH_TO_DST_GPKG -s PATH_TO_SAMPLE_IMAGE -x SHIFT_PIXELS_X -y SHIFT_PIXELS_Y
   

   Shift using spatial units (SRS):

   python shift.py -i PATH_TO_SRC_GPKG -o PATH_TO_DST_GPKG -x SHIFT_UNITS_X -y SHIFT_UNITS_Y
   

ℹ️ Tip: For advanced settings, refer to the instructions in delineation_config_guide.md

License

This project is licensed under the AGPL-3.0 License.

Acknowledgements

This code is based on Ultralytics.

Citation

If you find our work useful in your research, please consider citing it:

@article{lavreniuk2025delineateanything,
      title={Delineate Anything: Resolution-Agnostic Field Boundary Delineation on Satellite Imagery}, 
      author={Mykola Lavreniuk and Nataliia Kussul and Andrii Shelestov and Bohdan Yailymov and Yevhenii Salii and Volodymyr Kuzin and Zoltan Szantoi},
      year={2025},
      journal={arXiv preprint arXiv:2504.02534},
}

@article{lavreniuk2025delineateanythingflow,
      title={Delineate Anything Flow: Fast, Country-Level Field Boundary Detection from Any Source}, 
      author={Mykola Lavreniuk and Nataliia Kussul and Andrii Shelestov and Yevhenii Salii and Volodymyr Kuzin and Sergii Skakun and Zoltan Szantoi},
      year={2025},
      journal={https://arxiv.org/abs/2511.13417},
}