Skip to main navigation Skip to search Skip to main content

FAST ACCURATE SUPERVISED CLOUD ANNOTATION

  • C. Williams
  • , T. Dagobert
  • , C. de Franchis
  • , J.-M. Morel
  • , C. Hessel

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review

Abstract

Using optical satellite images requires detecting accurately all clouds in any image. For many applications, automatic cloud detection methods are not accurate enough. We describe here a fast machine learning based annotation system and demonstrate on Sentinel-2 images its efficacy to reach in four clicks or less a more than 95% accurate cloud detector. To obtain these statistics, we constructed an eclectic database of partially cloudy images and its ground truth, and evaluated its accuracy to be larger than 98%. We then show that our fast supervised annotation is far more accurate than recent sophisticated cloud detectors. © 2021 IEEE
Original languageEnglish
Title of host publicationIGARSS 2021 - 2021 IEEE International Geoscience and Remote Sensing Symposium
Subtitle of host publicationProceedings
PublisherIEEE
Pages3237-3240
ISBN (Electronic)978-1-6654-0369-6
ISBN (Print)978-1-6654-4762-1
DOIs
Publication statusPublished - 2021
Externally publishedYes
Event2021 IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2021) - Virtual, Brussels, Belgium
Duration: 11 Jul 202116 Jul 2021

Publication series

Name
ISSN (Print)2153-6996
ISSN (Electronic)2153-7003

Conference

Conference2021 IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2021)
PlaceBelgium
CityBrussels
Period11/07/2116/07/21

Research Keywords

  • classification
  • cloud detection
  • Optical satellite images
  • segmentation
  • supervised learning

Fingerprint

Dive into the research topics of 'FAST ACCURATE SUPERVISED CLOUD ANNOTATION'. Together they form a unique fingerprint.

Cite this