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...

Täydet tiedot

Tallennettuna:
Bibliografiset tiedot
Päätekijät: Kamal Gopikrishnan Nambiar, Veniamin I. Morgenshtern, Philipp Hochreuther, Thorsten Seehaus, Matthias Holger Braun
Aineistotyyppi: Artigo
Kieli:Inglês
Julkaistu: MDPI AG 2022-04-01
Sarja:Remote Sensing
Aiheet:
deep learning
semi-supervised learning
semantic segmentation
self-training
automatic cloud screening
Fmask
Linkit:https://www.mdpi.com/2072-4292/14/8/1825
Tagit: Lisää tagi
Ei tageja, Lisää ensimmäinen tagi!

Samankaltaisia teoksia