Dataset containing orthoimages tagged with road information covering approximately 8650 km2 of the Spanish territory (SROADEX)

Miguel-Ángel Manso-Callejo; Calimanut-Ionut Cira; Alicia González-Jiménez; José-Javier Querol-Pascual

doi:10.1016/j.dib.2022.108316

Dataset containing orthoimages tagged with road information covering approximately 8650 km² of the Spanish territory (SROADEX)

Data Brief. 2022 May 28:42:108316. doi: 10.1016/j.dib.2022.108316. eCollection 2022 Jun.

Authors

Miguel-Ángel Manso-Callejo¹, Calimanut-Ionut Cira¹, Alicia González-Jiménez², José-Javier Querol-Pascual¹

Affiliations

¹ Departamento de Ingeniería Topográfica y Cartografía, Escuela Técnica Superior de Ingenieros en Topografía, Geodesia y Cartografía, Universidad Politécnica de Madrid, Madrid 28031, Spain.
² Subdirección General de Cartografía y Observación del Territorio, Instituto Geográfico Nacional, Madrid 28003, Spain.

Abstract

In this data paper, we propose an open dataset (named SROADEX) containing more than 527,000 image tiles of 256 × 256 pixels stored in the lossless PNG format, tagged at pixel level with road information. The dataset covers approximately 8650 km² of the Spanish territory, is divided in train, validation and test sets and can be used by researchers and professionals for training other extraction solutions and benchmarking additional models. The SROADEX dataset is available under a CC-BY 4.0 licence and can be freely downloaded from the Zenodo repository.

Keywords: Binary classification; Highways; Main roads; Paths; RGB images; Road recognition; Road surface area extraction; Secondary roads.