Fast Accurate Supervised Cloud Annotation

C. WILLIAMS; T. DAGOBERT; C. DE FRANCHIS; J.-M. MOREL; C. HESSEL

doi:10.1109/IGARSS47720.2021.9554213

Fast Accurate Supervised Cloud Annotation

C. WILLIAMS^*
, T. DAGOBERT^*
, C. DE FRANCHIS^*
, J.-M. MOREL^*
, C. HESSEL^*

^*Corresponding author for this work

Research output: Book Chapters | Papers in Conference Proceedings › Conference paper (refereed) › Research › peer-review

1 Citation (Scopus)

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.

Original language	English
Title of host publication	IGARSS 2021: 2021 IEEE International Geoscience and Remote Sensing Symposium, Proceedings
Publisher	IEEE
Pages	3237-3240
Number of pages	4
ISBN (Electronic)	9781665403696
ISBN (Print)	9781665447621
DOIs	https://doi.org/10.1109/IGARSS47720.2021.9554213
Publication status	Published - 2021
Externally published	Yes
Event	2021 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2021 - Brussels, Belgium Duration: 12 Jul 2021 → 16 Jul 2021

Conference

Conference	2021 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2021
Country/Territory	Belgium
City	Brussels
Period	12/07/21 → 16/07/21

Bibliographical note

Publisher Copyright:
© 2021 IEEE

Keywords

classification
cloud detection
Optical satellite images
segmentation
supervised learning

Access to Document

10.1109/IGARSS47720.2021.9554213

Cite this

@inproceedings{1f1e1c72434441e1979292830438b369,

title = "Fast Accurate Supervised Cloud Annotation",

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.",

keywords = "classification, cloud detection, Optical satellite images, segmentation, supervised learning",

author = "C. WILLIAMS and T. DAGOBERT and \{DE FRANCHIS\}, C. and J.-M. MOREL and C. HESSEL",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE; 2021 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2021 ; Conference date: 12-07-2021 Through 16-07-2021",

year = "2021",

doi = "10.1109/IGARSS47720.2021.9554213",

language = "English",

isbn = "9781665447621",

pages = "3237--3240",

booktitle = "IGARSS 2021: 2021 IEEE International Geoscience and Remote Sensing Symposium, Proceedings",

publisher = "IEEE",

}

WILLIAMS, C, DAGOBERT, T, DE FRANCHIS, C, MOREL, J-M & HESSEL, C 2021, Fast Accurate Supervised Cloud Annotation. in IGARSS 2021: 2021 IEEE International Geoscience and Remote Sensing Symposium, Proceedings . IEEE, pp. 3237-3240, 2021 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2021, Brussels, Belgium, 12/07/21. https://doi.org/10.1109/IGARSS47720.2021.9554213

TY - GEN

T1 - Fast Accurate Supervised Cloud Annotation

AU - WILLIAMS, C.

AU - DAGOBERT, T.

AU - DE FRANCHIS, C.

AU - MOREL, J.-M.

AU - HESSEL, C.

PY - 2021

Y1 - 2021

N2 - 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.

AB - 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.

KW - classification

KW - cloud detection

KW - Optical satellite images

KW - segmentation

KW - supervised learning

UR - https://www.scopus.com/pages/publications/85129823775

U2 - 10.1109/IGARSS47720.2021.9554213

DO - 10.1109/IGARSS47720.2021.9554213

M3 - Conference paper (refereed)

AN - SCOPUS:85129823775

SN - 9781665447621

SP - 3237

EP - 3240

BT - IGARSS 2021: 2021 IEEE International Geoscience and Remote Sensing Symposium, Proceedings

PB - IEEE

T2 - 2021 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2021

Y2 - 12 July 2021 through 16 July 2021

ER -

Fast Accurate Supervised Cloud Annotation

Abstract

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this