Seatizen Atlas: a collaborative dataset of underwater and aerial marine imagery

Abstract

Citizen Science initiatives have a worldwide impact on environmental research by providing data at a global scale and high resolution. Mapping marine biodiversity remains a key challenge to which citizen initiatives can contribute. Here we describe a dataset made of both underwater and aerial imagery collected in shallow tropical coastal areas by using various low cost platforms operated either by citizens or researchers. This dataset is regularly updated and contains \textgreater1.6 M images from the Southwest Indian Ocean. Most of images are geolocated, and some are annotated with 51 distinct classes (e.g. fauna, and habitats) to train AI models. The quality of these photos taken by action cameras along the trajectories of different platforms, is highly heterogeneous (due to varying speed, depth, turbidity, and perspectives) and well reflects the challenges of underwater image recognition. Data discovery and access rely on DOI assignment while data interoperability and reuse is ensured by complying with widely used community standards. The open-source data workflow is provided to ease contributions from anyone collecting pictures.

DroneMegaDetector, A Generalised Model For Detecting Large Mammals In Aerial Imagery
C. C. Elchik, S. Longmore, D. Morris +5
bioRxiv12 Oct 2026PreprintCC BY-NC-NDFull textEcologybioRxiv
A 10-m National Agricultural Parcel Dataset of Ukraine Generated with an Enhanced Multi-Task Network and Sentinel-2 Imagery
Junbin Li, Hongwei Zeng, Hang Zhao +7
Scientific Data10 Jul 2026Peer-reviewedCC BY-NC-ND 4.0Full textEcologyPMC
AVID: A 5T fMRI Dataset for Benchmarking Auditory-induced Visual Mental Imagery Decoding
Shiqi Shen, Shurui Li, Xilin Zhang +1
arXiv2 Nov 2026PreprintCC BY 4.0Full textNeurosciencearXiv
Evaluating Pedestrian Crossing Safety: Implementing and Evaluating a Convolutional Neural Network Model Trained on Paired Aerial and Subjective Perspective Images (Vol 11, E42428, 2025)
Dylan Russon, Antoine Guennec, Juan Naredo-Turrado +5
Heliyon8 Oct 2026Peer-reviewedLicence not statedFull textGeneral biology Epidemiology & public healthHAL
Aerial Phenotyping of Coffee Flowering Using Deep Learning for Early Yield Prediction
Elias Horácio Zavala, Gabriel Araújo e Silva Ferraz, Felipe Andrés Obando Vega +5
Plants (Basel, Switzerland)1 Oct 2026Peer-reviewedCC BYFull textPlant biologyEurope PMC

Cite

BibTeX RIS

BibTeX

@article{contini2026seatizen,
  title = {{Seatizen Atlas: a collaborative dataset of underwater and aerial marine imagery}},
  author = {Matteo Contini and Victor Illien and Mohan Julien and Mervyn Ravitchandirane and Victor Russias and Arthur Lazennec and Thomas Chevrier and Cam Ly Rintz and Léanne Carpentier and Pierre Gogendeau and César Leblanc and Serge Bernard and Alexandre Boyer and Justine Talpaert Daudon and Sylvain Poulain and Julien Barde and Alexis Joly and Sylvain Bonhommeau},
  journal = {Scientific Data},
  year = {2026},
  month = sep,
  doi = {10.1038/s41597-024-04267-z},
  url = {https://hal.umontpellier.fr/hal-04918784v1},
  note = {CC BY-NC-ND 4.0},
}

RIS

TY  - JOUR
TI  - Seatizen Atlas: a collaborative dataset of underwater and aerial marine imagery
AU  - Matteo Contini
AU  - Victor Illien
AU  - Mohan Julien
AU  - Mervyn Ravitchandirane
AU  - Victor Russias
AU  - Arthur Lazennec
AU  - Thomas Chevrier
AU  - Cam Ly Rintz
AU  - Léanne Carpentier
AU  - Pierre Gogendeau
AU  - César Leblanc
AU  - Serge Bernard
AU  - Alexandre Boyer
AU  - Justine Talpaert Daudon
AU  - Sylvain Poulain
AU  - Julien Barde
AU  - Alexis Joly
AU  - Sylvain Bonhommeau
PY  - 2026
DA  - 2026/09/23
JO  - Scientific Data
DO  - 10.1038/s41597-024-04267-z
UR  - https://hal.umontpellier.fr/hal-04918784v1
AB  - Citizen Science initiatives have a worldwide impact on environmental research by providing data at a global scale and high resolution. Mapping marine biodiversity remains a key challenge to which citizen initiatives can contribute. Here we describe a dataset made of both underwater and aerial imagery collected in shallow tropical coastal areas by using various low cost platforms operated either by citizens or researchers. This dataset is regularly updated and contains \textgreater1.6 M images from the Southwest Indian Ocean. Most of images are geolocated, and some are annotated with 51 distinct classes (e.g. fauna, and habitats) to train AI models. The quality of these photos taken by action cameras along the trajectories of different platforms, is highly heterogeneous (due to varying speed, depth, turbidity, and perspectives) and well reflects the challenges of underwater image recognition. Data discovery and access rely on DOI assignment while data interoperability and reuse is ensured by complying with widely used community standards. The open-source data workflow is provided to ease contributions from anyone collecting pictures.
SN  - 2052-4463
ER  -

Abstract

Related

Cite