SD4EO - Physically Based Rendering images of human settlements (Sentinel-2 B2B3B4B8)

This dataset contains part of the results of the SD4EO project, including images corresponding to the use case of human settlement monitoring. The dataset contains images that have been simulated corresponding to different sensors of the Sentinel 2 satellites. Each image in the dataset includes pixel-level labels for each element present in the image, ensuring perfect accuracy due to the synthetic nature of the images. This eliminates common errors in manual or semi-automatic labeling processes.

Multispectral images includedSentinel 2: Images from bands 2, 3, 4 and 8.

Image labeling

(Open Street Map color code)

Element

R

G

B

Road

255

255

255

Building

196

182

171

Highway

232

146

162

Industrial zone

234

203

228

Parking

238

238

238

Railway

112

112

112

Residential zone

224

223

223

Vegetation

174

223

163

Water

170

211

223

(Building Masks)

Green - Non residential

Red - Residential

Image name convention

The name convention follows the next schema of fields, separated by the character “_”

-          ID number

-          Meters per pixel resolution

-          Type of image (Sentinel 2 bands, labels or buildings masks): B2B3B4, B8, labels, buildings

Image formats

PNG format is used to display each band in normalized values [0..1].

TIFF format is used to save each band with floating point precision in the original range of the satellite images.

Type of data

PNG range

TIFF range

B2

0 - 255

0 - 2000

B3

0 - 255

0 - 2500

B4

0 - 255

0 - 3000

B8

0 - 255

1180 - 5736

Creation and funding

All the images have been generated using a tool developed in Unity. This tool will be soon available to enable the generation of new datasets.

This research work has been funded by the European Space Agency (ESA) under the FutureEO program and the SD4EO project (Contract No.: 4000142334/23/I-DT), supervised by the ESA Φ-lab.

License and attribution

This dataset is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0).

When using the images from this dataset, please attribute them as follows: "Synthetic images created by the research group ARTEC - IRTIC - University of Valencia".