Automatic Cloud Detection Method Based on Generative Adversarial Networks in Remote Sensing Images

Jun Li, Zhaocong Wu, Zhongwen Hu, Yi Zhang, Matthieu Molinier

Research output: Contribution to journalArticle in a proceedings journalScientificpeer-review

2 Citations (Scopus)
88 Downloads (Pure)


Clouds in optical remote sensing images seriously affect the visibility of background pixels and greatly reduce the availability of images. It is necessary to detect clouds before processing images. In this paper, a novel cloud detection method based on attentive generative adversarial network (Auto-GAN) is proposed for cloud detection. Our main idea is to inject visual attention into the domain transformation to detect clouds automatically. First, we use a discriminator (D) to distinguish between cloudy and cloud free images. Then, a segmentation network is used to detect the difference between cloudy and cloud-free images (i.e. clouds). Last, a generator (G) is used to fill in the different regions in cloud image in order to confuse the discriminator. Auto-GAN only requires images and their labels (1 for a cloud-free image, 0 for a cloudy image) in the training phase which is more time-saving to acquire than existing methods based on CNNs that require pixel-level labels. Auto-GAN is applied to cloud detection in Sentinel-2A Level 1C imagery. The results indicate that Auto-GAN method performs well in cloud detection over different land surfaces.
Original languageEnglish
Pages (from-to)885-892
JournalISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Issue number2
Publication statusPublished - 3 Aug 2020
MoE publication typeA4 Article in a conference publication
Event24th ISPRS Congress on Technical Commission II: Online - Virtual, Nice, France
Duration: 31 Aug 20202 Sept 2020


  • Attention mechanism
  • Auto-GAN
  • Cloud detection
  • Deep learning
  • Generative adversarial networks (GANs)


Dive into the research topics of 'Automatic Cloud Detection Method Based on Generative Adversarial Networks in Remote Sensing Images'. Together they form a unique fingerprint.

Cite this