Towards Robust Cloud Detection in Satellite Images Using U-Nets
Authors:
- 11 July 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 4099-4102
Abstract
Cloud detection is an important pre-processing step that allows us to significantly reduce the amount of satellite imagery which should undergo further processing. In this paper, we investigate the impact of training set selection on the abilities of fully-convolutional neural networks for this task. Our experiments, performed over a range of Landsat-8 satellite images, show that the performance of deep models can substantially vary for different training samples, especially in the case of challenging scenes, such as those capturing snowy areas.Keywords
Funding Information
- European Space Agency (BEETLES)
- Polish National Centre for Research and Development (POIR.01.01.01-00-0356/17)
- SUT
This publication has 7 references indexed in Scilit:
- Cloud detection methodologies: variants and development—a reviewComplex & Intelligent Systems, 2019
- A cloud detection algorithm for satellite imagery based on deep learningRemote Sensing of Environment, 2019
- Deep Convolutional Networks for Cloud Detection Using Resourcesat-2 Data2019
- Cloud-Net: An End-To-End Cloud Detection Algorithm for Landsat 8 Imagery2019
- A Cloud Detection Algorithm for Remote Sensing Images Using Fully Convolutional Neural Networks2018
- Cloud detection machine learning algorithms for PROBA-V2017
- Cloud detection algorithm comparison and validation for operational Landsat data productsRemote Sensing of Environment, 2017