Single Image Cloud Detection via Multi-Image Fusion

Scott Workman, M. Usman Rafique, Hunter Blanton, Connor Greenwell, Nathan Jacobs

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Scopus citations


Artifacts in imagery captured by remote sensing, such as clouds, snow, and shadows, present challenges for various tasks, including semantic segmentation and object detection. A primary challenge in developing algorithms for identifying such artifacts is the cost of collecting annotated training data. In this work, we explore how recent advances in multi-image fusion can be leveraged to bootstrap single image cloud detection. We demonstrate that a network optimized to estimate image quality also implicitly learns to detect clouds. To support the training and evaluation of our approach, we collect a large dataset of Sentinel-2 images along with a per-pixel semantic labelling for land cover. Through various experiments, we demonstrate that our method reduces the need for annotated training data and improves cloud detection performance.

Original languageEnglish
Title of host publication2020 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2020 - Proceedings
Number of pages4
ISBN (Electronic)9781728163741
StatePublished - Sep 26 2020
Event2020 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2020 - Virtual, Waikoloa, United States
Duration: Sep 26 2020Oct 2 2020

Publication series

NameInternational Geoscience and Remote Sensing Symposium (IGARSS)


Conference2020 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2020
Country/TerritoryUnited States
CityVirtual, Waikoloa

Bibliographical note

Publisher Copyright:
© 2020 IEEE.


  • clouds
  • multi-image fusion
  • segmentation
  • weakly-supervised learning

ASJC Scopus subject areas

  • Computer Science Applications
  • General Earth and Planetary Sciences


Dive into the research topics of 'Single Image Cloud Detection via Multi-Image Fusion'. Together they form a unique fingerprint.

Cite this