Published May 13, 2024
| Version v1
Dataset
Open
Dataset for marine vessel detection from Sentinel 2 images in the Finnish coast
-
1.
Finnish Environment Institute
Contributors
Rights holder:
Description
This dataset contains annotated marine vessels from 15 different Sentinel-2 product, used for training object detection models for marine vessel detection. The vessels are annotated as bounding boxes, covering also some amount of the wake if present.
Source data
Individual products used to generate annotations are shown in the following table:
| Location | Product name |
| Archipelago sea | S2B_MSIL1C_20220619T100029_N0400_R122_T34VEM_20220619T104419 |
| S2A_MSIL1C_20220721T095041_N0400_R079_T34VEM_20220721T115325 | |
| S2A_MSIL1C_20220813T095601_N0400_R122_T34VEM_20220813T120233 | |
| Gulf of Finland | S2B_MSIL1C_20220606T095029_N0400_R079_T35VLG_20220606T105944 |
| S2B_MSIL1C_20220626T095039_N0400_R079_T35VLG_20220626T10432 | |
| S2A_MSIL1C_20220721T095041_N0400_R079_T35VLG_20220721T115325 | |
| Bothnian Bay | S2A_MSIL1C_20220627T100611_N0400_R022_T34WFT_20220627T134958 |
| S2B_MSIL1C_20220712T100559_N0400_R022_T34WFT_20220712T121613 | |
| S2B_MSIL1C_20220828T095549_N0400_R122_T34WFT_20220828T104748 | |
| Bothnian Sea | S2B_MSIL1C_20210714T100029_N0301_R122_T34VEN_20210714T121056 |
| S2A_MSIL1C_20220624T100041_N0400_R122_T34VEN_20220624T120211 | |
| S2A_MSIL1C_20220813T095601_N0400_R122_T34VEN_20220813T120233 | |
| Kvarken | S2A_MSIL1C_20220617T100611_N0400_R022_T34VER_20220617T135008 |
| S2B_MSIL1C_20220712T100559_N0400_R022_T34VER_20220712T121613 | |
| S2A_MSIL1C_20220826T100611_N0400_R022_T34VER_20220826T135136 |
Even though the reference data IDs are for L1C products, L2A products from the same acquisition dates can be used along with the annotations. However, Sen2Cor has been known to produce incorrect reflectance values for water bodies.
The raw products can be acquired from Copernicus Data Space Ecosystem.
Annotations
The annotations are bounding boxes drawn around marine vessels so that some amount of their wakes, if present, are also contained within the boxes. The data are distributed as geopackage files, so that one geopackage corresponds to a single Sentinel-2 tile, and each package has separate layers for individual products as shown below:
T34VEM|-20220619|-20220721|-20220813
All layers have a column id, which has the value boat for all annotations.
CRS is EPSG:32634 for all products except for the Gulf of Finland (35VLG), which is in EPSG:32635. This is done in order to have the bounding boxes to be aligned with the pixels in the imagery.
As tiles 34VEM and 34VEN have an overlap of 9.5x100 km, 34VEN is not annotated from the overlapping part to prevent data leakage between splits.
Annotation process
The minimum size for an object to be considered as a potential marine vessel was set to 2x2 pixels. Three separate acquisitions for each location were used to detect smallest objects, so that if an object was located at the same place in all images, then it was left unannotated. The data were annotated by two experts.| Product name | Number of annotations |
| S2B_MSIL1C_20220619T100029_N0400_R122_T34VEM_20220619T104419 | 591 |
| S2A_MSIL1C_20220721T095041_N0400_R079_T34VEM_20220721T115325 | 1518 |
| S2A_MSIL1C_20220813T095601_N0400_R122_T34VEM_20220813T120233 | 1368 |
| S2B_MSIL1C_20220606T095029_N0400_R079_T35VLG_20220606T105944 | 248 |
| S2B_MSIL1C_20220626T095039_N0400_R079_T35VLG_20220626T104321 | 1206 |
| S2A_MSIL1C_20220721T095041_N0400_R079_T35VLG_20220721T115325 | 971 |
| S2A_MSIL1C_20220627T100611_N0400_R022_T34WFT_20220627T134958 | 122 |
| S2B_MSIL1C_20220712T100559_N0400_R022_T34WFT_20220712T121613 | 162 |
| S2B_MSIL1C_20220828T095549_N0400_R122_T34WFT_20220828T104748 | 98 |
| S2B_MSIL1C_20210714T100029_N0301_R122_T34VEN_20210714T121056 | 450 |
| S2A_MSIL1C_20220624T100041_N0400_R122_T34VEN_20220624T120211 | 424 |
| S2A_MSIL1C_20220813T095601_N0400_R122_T34VEN_20220813T120233 | 399 |
| S2A_MSIL1C_20220617T100611_N0400_R022_T34VER_20220617T135008 | 83 |
| S2B_MSIL1C_20220712T100559_N0400_R022_T34VER_20220712T121613 | 183 |
| S2A_MSIL1C_20220826T100611_N0400_R022_T34VER_20220826T135136 | 88 |
Annotation statistics
Sentinel-2 images have spatial resolution of 10 m, so below statistics can be converted to pixel sizes by dividing them by 10 (diameter) pr 100 (area).
| mean | min | 25% | 50% | 75% | max | |
| Area (m²) | 5305.7 | 567.9 | 1629.9 | 2328.2 | 5176.3 | 414795.7 |
| Diameter (m) | 92.5 | 33.9 | 57.9 | 69.4 | 108.3 | 913.9 |
As most of the annotations cover also most of the wake of the marine vessel, the bounding boxes are significantly larger than a typical boat. There are a few annotations larger than 100 000 m², which are either cruise or cargo ships that are travelling along ordinal directions instead of cardinal directions, instead of e.g. smaller leisure boats.
Annotations typically have diameter less than 100 meters, and the largest diameters correspond to similar instances than the largest bounding box areas.
Train-test-split
We used tiles 34VEN and 34VER as the test dataset. The results acquired using RGB mosaics generated from L1C images are shown in the below table
| Model | Fold | Precision | Recall | mAP50 | mAP |
| yolov8n | 1 | 0,820806 | 0.838353 | 0.842 | 0.403 |
| yolov8s | 4 | 0.843822 | 0.860479 | 0.865 | 0.422 |
| yolov8m | 4 | 0.858263 | 0.874616 | 0.880 | 0.453 |
| yolov8l | 1 | 0.840311 | 0.863553 | 0.862 | 0.443 |
| yolov8x | 1 | 0.855134 | 0.859865 | 0.876 | 0.450 |
Before evaluating, the predictions for the test set are cleaned using the following steps:
1. All prediction whose centroid points are not located on water are discarded. The water mask used contains layers `jarvi` (Lakes), `meri` (Sea) and `virtavesialue` (Rivers as polygon geometry) from the Topographical database by the National Land Survey of Finland. Unfortunately this also discards all points not within the Finnish borders.
2. All predictions whose centroid points are located on water rock areas are discarded. The mask is the layer `vesikivikko` (Water rock areas) from the Topographical database.
3. All predictions that contain an above water rock within the bounding box are discarded. The mask contains classes `38511`, `38512`, `38513` from the layer `vesikivi` in the Topographical database.
4. All predictions that contain a lighthouse or a sector light within the bounding box are discarded. Lighthouses and sector lights come from Väylävirasto data, `ty_njr` class ids are 1, 2, 3, 4, 5, 8
5. All predictions that are wind turbines, found in Topographical database layer `tuulivoimalat`
6. All predictions that are obviously too large are discarded. The prediction is defined to be "too large" if either of its edges is longer than 750 meters.
Model checkpoints are available on Hugging Face platform: https://huggingface.co/mayrajeo/marine-vessel-detection-yolov8
To generate COCO format dataset run
Usage
The simplest way to chip the rasters into suitable format and convert the data to COCO or YOLO formats is to use geo2ml. First download the raw mosaics and convert them into GeoTiff files and then use the following to generate the datasets.from geo2ml.scripts import create_coco_dataset
raster_path = '<path_to_raster>'
outpath = '<path_to_save_the_dataset>'
poly_path = '<path_to_gpkg>'
layer = '<date_of_raster>'
create_coco_dataset(raster_path=raster_path, polygon_path=poly_path, target_column='id',
gpkg_layer=layer, outpath=outpath, save_grid=False,
dataset_name='<name_of_dataset>', gridsize_x=320, gridsize_y=320,
ann_format='box', min_bbox_area=0)To generate YOLO format dataset run
from geo2ml.scripts import create_yolo_dataset
raster_path = '<path_to_raster>'
outpath = '<path_to_save_the_dataset>'
poly_path = '<path_to_gpkg>'
layer = '<date_of_raster>'
create_yolo_dataset(raster_path=raster_path, polygon_path=poly_path, target_column='id',
gpkg_layer=layer, outpath=outpath, save_grid=False,
gridsize_x=320, gridsize_y=320, ann_format='box', min_bbox_area=0)Files
Files
(2.4 MB)
Additional details
Funding
- LIFE-IP BIODIVERSEA LIFE20 IPE/FI/000020
- European Commission