First dataset of wind turbine data created at national level with deep learning techniques from aerial orthophotographs with a spatial resolution of 0.5 m/pixel

Manso Callejo, Miguel Ángel and Cira, Calimanut-Ionut and Alcarria Garrido, Ramón Pablo and González Matesanz, Francisco Javier (2021). First dataset of wind turbine data created at national level with deep learning techniques from aerial orthophotographs with a spatial resolution of 0.5 m/pixel. "IEEE Journal of Selected Topics in Applied Earth Observations And Remote Sensing", v. 14 ; pp. 7968-7980. ISSN 1939-1404. https://doi.org/10.1109/JSTARS.2021.3101934.

Description

Title: First dataset of wind turbine data created at national level with deep learning techniques from aerial orthophotographs with a spatial resolution of 0.5 m/pixel
Author/s:
  • Manso Callejo, Miguel Ángel
  • Cira, Calimanut-Ionut
  • Alcarria Garrido, Ramón Pablo
  • González Matesanz, Francisco Javier
Item Type: Article
Título de Revista/Publicación: IEEE Journal of Selected Topics in Applied Earth Observations And Remote Sensing
Date: 4 August 2021
ISSN: 1939-1404
Volume: 14
Subjects:
Freetext Keywords: Feature extraction; Feature recognition; Image classification; Semantic segmentation; Wind turbines
Faculty: E.T.S.I. en Topografía, Geodesia y Cartografía (UPM)
Department: Ingeniería Topográfica y Cartografía
Creative Commons Licenses: Recognition - No derivative works - Non commercial

Full text

[img]
Preview
PDF - Requires a PDF viewer, such as GSview, Xpdf or Adobe Acrobat Reader
Download (2MB) | Preview

Abstract

Deep learning applied to feature extraction and mapping from high-resolution images is demonstrating the potential of this branch of data-intensive Artificial Intelligence to improve terrain mapping processes. The documented experiences have been applied on a small scale and there is a great expectation about its applicability on a country scale. For example, when extracting wind turbines using semantic segmentation models from a region of 28 km × 19 km containing unseen data, we obtained a commission rate of 1.4% and an omission rate of 0.38%. In this article, we present a methodology generated on the basis of two iterations. In these iterations, processing and post-processing time, energy consumption, and finally results have been optimised to map wind turbines for the first time throughout the Spanish peninsular territory. In addition to adding a binary classification neural network prior to the semantic segmentation that extracts the turbines, a third multiclass recognition network has been used to classify the turbines by their power capacity complementing the features extracted with attributes. The proposed methodology can be adapted in the vectorisation phase and applied to other types of features with linear or polygon representation to achieve a large-scale efficient extraction of geospatial elements using automated procedures

More information

Item ID: 68390
DC Identifier: https://oa.upm.es/68390/
OAI Identifier: oai:oa.upm.es:68390
DOI: 10.1109/JSTARS.2021.3101934
Official URL: https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9507327
Deposited by: Memoria Investigacion
Deposited on: 27 Jan 2022 16:42
Last Modified: 27 Jan 2022 16:42
  • Logo InvestigaM (UPM)
  • Logo GEOUP4
  • Logo Open Access
  • Open Access
  • Logo Sherpa/Romeo
    Check whether the anglo-saxon journal in which you have published an article allows you to also publish it under open access.
  • Logo Dulcinea
    Check whether the spanish journal in which you have published an article allows you to also publish it under open access.
  • Logo de Recolecta
  • Logo del Observatorio I+D+i UPM
  • Logo de OpenCourseWare UPM