A Self-Trained Model for Cloud, Shadow and Snow Detection in Sentinel-2 Images of Snow- and Ice-Covered Regions

Screening clouds, shadows, and snow is a critical pre-processing step in many remote-sensing data processing pipelines that operate on satellite image data from polar and high mountain regions. We observe that the results of the state-of-the-art Fmask algorithm are not very accurate in polar and hig...

Descrizione completa

Salvato in:
Dettagli Bibliografici
Autori principali: Kamal Gopikrishnan Nambiar, Veniamin I. Morgenshtern, Philipp Hochreuther, Thorsten Seehaus, Matthias Holger Braun
Natura: Artigo
Lingua:Inglês
Pubblicazione: MDPI AG 2022-04-01
Serie:Remote Sensing
Soggetti:
deep learning
semi-supervised learning
semantic segmentation
self-training
automatic cloud screening
Fmask
Accesso online:https://www.mdpi.com/2072-4292/14/8/1825
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne! !

Documenti analoghi