Single Image Cloud Detection via Multi-Image Fusion

Published in IEEE International Geosciences and Remote Sensing Symposium (IGARSS), 2020

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

              [Paper][Project Page]

Overview

overview

Abstract

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.

@inproceedings{workman2020single,
  author={Scott Workman and M. Usman Rafique and Hunter Blanton and Connor Greenwell and Nathan Jacobs},
  title={Single Image Cloud Detection via Multi-Image Fusion},
  booktitle={IEEE International Geoscience and Remote Sensing Symposium (IGARSS)},
  year=2020
}