YOLO11 model checkpoint for marine vessel detection in Sentinel-2 L1C-TCI imagery

Model details

Model Description

These model weights are meant for detecting marine vessels from L1C-TCI Sentinel-2 imagery.

The models are trained and validated on human-annotated marine vessel data. These annotations, information of which Sentinel-2 product they correspond to, and instructions on how to convert them into COCO or YOLO format datasets are available as GeoPackage files on Zenodo portal: https://doi.org/10.5281/zenodo.10046341.

Model type: Instance segmentation
License: aGPL3
Finetuned from model: Ultralytics pretrained yolo11 models

Uses

Direct Use

Models are trained to process 320x320 pixel patches of Sentinel-2 L1C-TCI images with 10m resolution and detect marine vessels which are upsampled into 640x640 pixels during training and inference. The models will detect targets from outside of the water areas, but those detections can be eliminated by using external datasets such as land masks.

Out-of-Scope Use

This model is not suitable for other purposes than for detecting potential marine vessels from satellite imagery. Also, as the model is trained on the data from the Finnish coast, it might not work in other geographical areas.

Recommendations

The models are most accurate on more closed water areas such as denser archipelagos and close to the coast instead of open sea. Especially during windy conditions the models incorrectly detect some wakes and glint as marine vessels.

How to Get Started with the Model

[https://github.com/mayrajeo/ship-detection] provides examples on how to use the models.

Compute Infrastructure

Hardware

NVIDIA V100 GPU with 32GB of memory, hosted on computing nodes of Puhti supercomputer by CSC - IT Center for Science, Finland.

Software

Models were trained as Slurm batch jobs in Puhti.

Citation

Manuscript has been accepted for publication, and citation will be added when the article is available.

Model Card Contact

Janne Mäyrä