Published May 24, 2024 | Version 1.0.0
Dataset Open

MagicBathyNet: A Multimodal Remote Sensing Dataset for Bathymetry Prediction and Pixel-based Classification in Shallow Waters

  • 1. ROR icon Technische Universität Berlin
  • 1. Technische Universität Berlin, Remote Sensing Image Analysis Group
  • 2. ROR icon Gdynia Maritime University
  • 3. Cyprus University of Technology

Description

The dataset

MagicBathyNet is a benchmark dataset made up of image patches of Sentinel-2, SPOT-6 and aerial imagery, bathymetry in raster format and seabed classes annotations. MagicBathyNet has been designed to be geographically well distributed. It’s coverage includes two very different coastal areas (in terms of water column characteristics and bottom type): i) Agia Napa area in Cyprus, covering a wide range of typical Mediterranean waters and seabed types, and ii) Puck Lagoon area in Poland, representing in a great degree Baltic Sea waters and bottom.

MagicBathyNet contains 3355 RGB co-registered triplets of Sentinel-2 (S2), SPOT-6, and aerial image patches, complemented by 1244 RGB co-registered S2 and SPOT-6 doublets, 3354 DSM (Digital Surface Model) raster patches for the aerial patches and 3396 DSM raster patches for S2 and SPOT-6. Additionally, it contains 533 annotated raster patches for seabed habitat and type, facilitating supervised pixel-based classification. Each patch covers 180x180m, represented by 18x18 pixels in S2 imagery, 30x30 pixels in SPOT-6 imagery and 720x720 pixels in airborne imagery. 

For the implementation code and pre-trained models visit our project page: https://www.magicbathy.eu/magicbathynet.html 

 

Citation

If you use the code in this repository or the dataset please cite our paper:

P. Agrafiotis, L. Janowski, D. Skarlatos, and B. Demir, "MagicBathyNet: A Multimodal Remote Sensing Dataset for Bathymetry Prediction and Pixel-based Classification in Shallow Waters", arXiv:2405.15477, 2024.

or 

P. Agrafiotis, Ł. Janowski, D. Skarlatos and B. Demir, "MAGICBATHYNET: A Multimodal Remote Sensing Dataset for Bathymetry Prediction and Pixel-Based Classification in Shallow Waters," IGARSS 2024 - 2024 IEEE International Geoscience and Remote Sensing Symposium, Athens, Greece, 2024, pp. 249-253, doi: 10.1109/IGARSS53475.2024.10641355.

Folder structure

┗ 📂 magicbathynet/
  ┣ 📂 agia_napa/
  ┃ ┣ 📂 img/
  ┃ ┃ ┣ 📂 aerial/
  ┃ ┃ ┃ ┣ 📜 img_339.tif
  ┃ ┃ ┃ ┣ 📜 ...
  ┃ ┃ ┣ 📂 s2/
  ┃ ┃ ┃ ┣ 📜 img_339.tif
  ┃ ┃ ┃ ┣ 📜 ...
  ┃ ┃ ┣ 📂 spot6/
  ┃ ┃ ┃ ┣ 📜 img_339.tif
  ┃ ┃ ┃ ┣ 📜 ...
  ┃ ┣ 📂 depth/
  ┃ ┃ ┣ 📂 aerial/
  ┃ ┃ ┃ ┣ 📜 depth_339.tif
  ┃ ┃ ┃ ┣ 📜 ...
  ┃ ┃ ┣ 📂 s2/
  ┃ ┃ ┃ ┣ 📜 depth_339.tif
  ┃ ┃ ┃ ┣ 📜 ...
  ┃ ┃ ┣ 📂 spot6/
  ┃ ┃ ┃ ┣ 📜 depth_339.tif
  ┃ ┃ ┃ ┣ 📜 ...
  ┃ ┣ 📂 gts/
  ┃ ┃ ┣ 📂 aerial/
  ┃ ┃ ┃ ┣ 📜 gts_339.tif
  ┃ ┃ ┃ ┣ 📜 ...
  ┃ ┃ ┣ 📂 s2/
  ┃ ┃ ┃ ┣ 📜 gts_339.tif
  ┃ ┃ ┃ ┣ 📜 ...
  ┃ ┃ ┣ 📂 spot6/
  ┃ ┃ ┃ ┣ 📜 gts_339.tif
  ┃ ┃ ┃ ┣ 📜 ...
  ┃ ┣ 📜 [modality]_split_bathymetry.txt
  ┃ ┣ 📜 [modality]_split_pixel_class.txt
  ┃ ┣ 📜 norm_param_[modality]_an.txt
  ┃
  ┣ 📂 puck_lagoon/
  ┃ ┣ 📂 img/
  ┃ ┃ ┣ 📜 ...
  ┃ ┣ 📂 depth/
  ┃ ┃ ┣ 📜 ...
  ┃ ┣ 📂 gts/
  ┃ ┃ ┣ 📜 ...
  ┃ ┣ 📜 [modality]_split_bathymetry.txt
  ┃ ┣ 📜 [modality]_split_pixel_class.txt
  ┃ ┣ 📜 norm_param_[modality]_pl.txt

 

Package for benchmarking MagicBathyNet dataset

Donwload the package for benchmarking MagicBathyNet dataset in learning-based bathymetry and pixel-based classification here:

https://github.com/pagraf/MagicBathyNet

 

Version history

v1.0.0 - First release

 

License

Dataset: Creative Commons Attribution Non Commercial 4.0 International

Code: Attribution-NonCommercial-ShareAlike 4.0 International License

Copyright (c) 2024 The MagicBathyNet Authors

 

Acknowledgments

This work was part of the project MagicBathy which is a research project funded by the European Commission for the period 2023-2025. It is funded under the HORIZON Europe MSCA Postdoctoral Fellowships - European Fellowships (GA 101063294).

European Space Agency (ESA) is also acknowledged for providing the SPOT-6 images within its TPM programme in the frame of proposal PP0092443 and Airbus for being the provider of the original SPOT-6 images. The Dep. of Land and Surveys of Cyprus is acknowledged for providing the LiDAR reference data for Cyprus.

Files

MagicBathyNet.zip

Files (5.9 GB)

Name Size Download all
md5:f7d5bf1873b846a96de00c722b7a1fd5
5.9 GB Preview Download

Additional details

Related works

Is published in
Publication: 10.48550/arXiv.2405.15477 (DOI)
Publication: 10.1109/IGARSS53475.2024.10641355 (DOI)

Funding

MagicBathy – Multimodal multitAsk learninG for MultIsCale BATHYmetric mapping in shallow waters 101063294
European Commission

Dates

Accepted
2024-03-15
IGARSS 2024

Software

Repository URL
https://github.com/pagraf/MagicBathyNet
Programming language
Python
Development Status
Active