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.
@article{arxiv.2007.15144,
title = {Single Image Cloud Detection via Multi-Image Fusion},
author = {Scott Workman and M. Usman Rafique and Hunter Blanton and Connor Greenwell and Nathan Jacobs},
journal= {arXiv preprint arXiv:2007.15144},
year = {2020}
}
Comments
IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2020