A Deep Learning-Based Solution for Large-Scale Extraction of the Secondary Road Network from High-Resolution Aerial Orthoimagery

Cira, Calimanut-Ionut and Alcarria Garrido, Ramon Pablo and Manso Callejo, Miguel Angel and Serradilla Garcia, Francisco (2020). A Deep Learning-Based Solution for Large-Scale Extraction of the Secondary Road Network from High-Resolution Aerial Orthoimagery. "Machine Learning and Remote Sensing for Automatic Map Creation and Update", v. 10 (n. 20); pp. 1-18. ISSN 2076-3417. https://doi.org/10.3390/app10207272.

Description

Title: A Deep Learning-Based Solution for Large-Scale Extraction of the Secondary Road Network from High-Resolution Aerial Orthoimagery
Author/s:
  • Cira, Calimanut-Ionut
  • Alcarria Garrido, Ramon Pablo
  • Manso Callejo, Miguel Angel
  • Serradilla Garcia, Francisco
Item Type: Article
Título de Revista/Publicación: Machine Learning and Remote Sensing for Automatic Map Creation and Update
Date: 17 October 2020
ISSN: 2076-3417
Volume: 10
Subjects:
Freetext Keywords: Aerial orthoimagery; Deep learning; Remote sensing; Road extraction; Semantic segmentation; Web-based segmentation solution
Faculty: E.T.S.I. en Topografía, Geodesia y Cartografía (UPM)
Department: Ingeniería Cartográfica y Topografía
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 (3MB) | Preview

Abstract

Secondary roads represent the largest part of the road network. However, due to the absence of clearly defined edges, presence of occlusions, and differences in widths, monitoring and mapping them represents a great effort for public administration. We believe that recent advancements in machine vision allow the extraction of these types of roads from high-resolution remotely sensed imagery and can enable the automation of the mapping operation. In this work, we leverage these advances and propose a deep learning-based solution capable of efficiently extracting the surface area of secondary roads at a large scale. The solution is based on hybrid segmentation models trained with high-resolution remote sensing imagery divided in tiles of 256 × 256 pixels and their correspondent segmentation masks, resulting in increases in performance metrics of 2.7?3.5% when compared to the original architectures. The best performing model achieved Intersection over Union and F1 scores of maximum 0.5790 and 0.7120, respectively, with a minimum loss of 0.4985 and was integrated on a web platform which handles the evaluation of large areas, the association of the semantic predictions with geographical coordinates, the conversion of the tiles? format and the generation of geotiff results compatible with geospatial databases.

More information

Item ID: 65086
DC Identifier: http://oa.upm.es/65086/
OAI Identifier: oai:oa.upm.es:65086
DOI: 10.3390/app10207272
Official URL: https://www.mdpi.com/2076-3417/10/20/7272
Deposited by: Memoria Investigacion
Deposited on: 08 Feb 2021 17:58
Last Modified: 10 Feb 2021 14:58
  • 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