EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Detection of forest roads in Sentinel-2 images using U-Net

Øivind Trier, Arnt-Børre Salberg, Ragnvald Larsen, Ole Torbjørn Nyvoll

Proceedings of the Northern Lights Deep Learning Workshop · 2022

DOI: 10.7557/18.6246 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the Northern Lights Deep Learning Workshop, 2022. Verfasst von Øivind Trier und 3 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper presents a new method for semi-automatic detection of nature interventions inSentinel-2 satellite images with 10 m spatial resolution. The Norwegian Environment Agency ismaintaining a map of undisturbed nature in Norway. U-Net was used for automated detection ofnew roads, as these are often the cause whenever the area of undisturbed nature is reduced. Themethod was able to detect many new roads, but with some false positives and possibly some falsenegatives (i.e., missing new roads). In conclusion, we have demonstrated that automated detection ofnew roads, for the purpose of updating the map of undisturbed nature, is possible. We have alsosuggested several improvements of the method to improve its usefulness.

Zitieren

APA

Trier, Ø., Salberg, A., Larsen, R., & Nyvoll, O. T. (2022). Detection of forest roads in Sentinel-2 images using U-Net. Proceedings of the Northern Lights Deep Learning Workshop. https://doi.org/10.7557/18.6246

Vancouver

Trier Ø, Salberg A, Larsen R, Nyvoll OT. Detection of forest roads in Sentinel-2 images using U-Net. Proceedings of the Northern Lights Deep Learning Workshop. 2022. doi:10.7557/18.6246

BibTeX
@article{Trier2022,
  author = {Trier, Øivind and Salberg, Arnt-Børre and Larsen, Ragnvald and Nyvoll, Ole Torbjørn},
  title = {Detection of forest roads in Sentinel-2 images using U-Net},
  journal = {Proceedings of the Northern Lights Deep Learning Workshop},
  year = {2022},
  doi = {10.7557/18.6246}
}
Kostenlos starten →