Single Image Cloud Detection via Multi-Image Fusion

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


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.

IGARSS 2020 Oral Paper

thumbnail thumbnail thumbnail thumbnail


  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)}},