Radiant MLHub

Marine Debris Archive (MARIDA)

Marine Debris Archive (MARIDA) is a marine debris-oriented dataset on Sentinel-2 satellite images. It also includes various sea features (clear & turbid water, waves, etc.) and floating materials (Sargassum macroalgae, ships, natural organic material, etc) that co-exist. MARIDA is primarily focused on the weakly supervised pixel-level semantic segmentation task.

Dataset ID

marida_v1

DOI

10.1371/journal.pone.0262247browse DOI

Creator

National Technical University of Athens

Contact

akikakh@central.ntua.gr

Documentation

Citation

Kikaki K, Kakogeorgiou I, Mikeli P, Raitsos DE, Karantzalos K (2022) MARIDA: A benchmark for Marine Debris detection from Sentinel-2 remote sensing data. PLoS ONE 17(1): e0262247. https://doi.org/10.1371/journal.pone.0262247

Python Client example

from radiant_mlhub import Dataset

ds = Dataset.fetch('marida_v1')
for c in ds.collections:
    print(c.id)

Python Client quick-start guide

Download Dataset

Source Imagery Collections

Description

MARIDA Sentinel-2 Marine Debris Imagery

License

CC-BY-4.0

Collection ID

marida_v1_source

Download

Labels Collections

Description

MARIDA Marine Debris Raster Labels

License

CC-BY-4.0

Collection ID

marida_v1_raster_labels

Download

Description

MARIDA Marine Debris Vector Labels

License

CC-BY-4.0

Collection ID

marida_v1_vector_labels

Download


Radiant Earth Foundation

© Radiant Earth Foundation