Cite as:
Dr&ouml;nner, J.; Korfhage, N.; Egli, S.; M&uuml;hling, M.; Thies, B.; Bendix, J.; Freisleben, B. &amp; Seeger, B. (2018): <b>Fast Cloud Segmentation Using Convolutional Neural Networks</b>. <i>remote sensing</i> <b>10</b>(11), 1782-.

Resource Description

Title: Fast Cloud Segmentation Using Convolutional Neural Networks
FOR816dw ID: 323
Publication Date: 2018-11-10
License and Usage Rights: Department of Mathmatics and Computer Science, University of Marburg
Resource Owner(s):
Individual: Johannes Drönner
Individual: Nikolaus Korfhage
Individual: Sebastian Egli
Individual: Markus Mühling
Individual: Boris Thies
Individual: Jörg Bendix
Individual: Bernd Freisleben
Individual: Bernhard Seeger
Information about clouds is important for observing and predicting weather and climate as well as for generating and distributing solar power. Most existing approaches extract cloud information from satellite data by classifying individual pixels instead of using closely integrated spatial information, ignoring the fact that clouds are highly dynamic, spatially continuous entities. This paper proposes a novel cloud classification method based on deep learning. Relying on a Convolutional Neural Network (CNN) architecture for image segmentation, the presented Cloud Segmentation CNN (CS-CNN), classifies all pixels of a scene simultaneously rather than individually.<br/> We show that CS-CNN can successfully process multispectral satellite data to classify continuous phenomena such as highly dynamic clouds. The proposed approach produces excellent results on Meteosat Second Generation (MSG) satellite data in terms of quality, robustness, and runtime compared to other machine learning methods such as random forests. In particular, comparing CS-CNN with the CLAAS-2 cloud mask derived from MSG data shows high accuracy (0.94) and Heidke Skill Score (0.90) values. In contrast to a random forest, CS-CNN produces robust results and is insensitive to challenges created by coast lines and bright (sand) surface areas. Using GPU acceleration, CS-CNN requires only 25 ms of computation time for classification of images of Europe with 508 508 pixels.
| Meteosat Second Generation | Convolutional Neuronal Networks | Cloud Mask |
Literature type specific fields:
Journal: remote sensing
Volume: 10
Issue: 11
Page Range: 1782-
Metadata Provider:
Individual: Maik Dobbermann
Online Distribution:
Download File:

Quick search

  • Publications:
  • Datasets: