Volume IV-3
ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., IV-3, 149-152, 2018
https://doi.org/10.5194/isprs-annals-IV-3-149-2018
© Author(s) 2018. This work is distributed under
the Creative Commons Attribution 4.0 License.
ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., IV-3, 149-152, 2018
https://doi.org/10.5194/isprs-annals-IV-3-149-2018
© Author(s) 2018. This work is distributed under
the Creative Commons Attribution 4.0 License.

  23 Apr 2018

23 Apr 2018

CLOUD DETECTION BY FUSING MULTI-SCALE CONVOLUTIONAL FEATURES

Zhiwei Li1, Huanfeng Shen1,5, Yancong Wei2, Qing Cheng3, and Qiangqiang Yuan4,5 Zhiwei Li et al.
  • 1School of Resource and Environmental Sciences, Wuhan University, Wuhan, P. R. China
  • 2State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan, P. R. China
  • 3School of Urban Design of Wuhan University, Wuhan University, Wuhan, P. R. China
  • 4School of Geodesy and Geomatics, Wuhan University, Wuhan, P. R. China
  • 5Collaborative Innovation Center of Geospatial Technology, Wuhan, P. R. China

Keywords: Cloud detection, Deep learning, Convolutional feature fusion, Multi-scale, MSCN

Abstract. Clouds detection is an important pre-processing step for accurate application of optical satellite imagery. Recent studies indicate that deep learning achieves best performance in image segmentation tasks. Aiming at boosting the accuracy of cloud detection for multispectral imagery, especially for those that contain only visible and near infrared bands, in this paper, we proposed a deep learning based cloud detection method termed MSCN (multi-scale cloud net), which segments cloud by fusing multi-scale convolutional features. MSCN was trained on a global cloud cover validation collection, and was tested in more than ten types of optical images with different resolution. Experiment results show that MSCN has obvious advantages over the traditional multi-feature combined cloud detection method in accuracy, especially when in snow and other areas covered by bright non-cloud objects. Besides, MSCN produced more detailed cloud masks than the compared deep cloud detection convolution network. The effectiveness of MSCN make it promising for practical application in multiple kinds of optical imagery.