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

Abstract

Abstract. 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.

Cloud detection algorithm based on point by point refinement

“…Thanks to the rapid development of computer hardware devices and artificial intelligence algorithms, cloud detection algorithms based on convolutional neural networks have gradually become the mainstream of cloud detection tasks, achieving breakthroughs in both accuracy and speed. Li et al [4] proposed a cloud detection method based on generative adversarial networks, using discriminators to distinguish between cloudy and cloud-free images and segmentation networks to detect the differences between cloudy and cloud-free images. Ji et al [5] proposed an F-CNN remote sensing image cloud detection method based on a fully convolutional neural network model, which can achieve cloud segmentation in large scale, high resolution, multi-channel remote sensing images, but the method is difficult to distinguish between clouds and snow.…”