Thin and Thick Cloud Removal on Remote Sensing Image by Conditional Generative Adversarial Network
- Resource Type
- Conference
- Authors
- Wang, Xiaoke; Xu, Guangluan; Wang, Yang; Lin, Daoyu; Li, Peiguang; Lin, Xiujing
- Source
- IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium Geoscience and Remote Sensing Symposium, IGARSS 2019 - 2019 IEEE International. :1426-1429 Jul, 2019
- Subject
- Aerospace
Geoscience
Signal Processing and Analysis
Remote sensing
Generators
Generative adversarial networks
Linear programming
Task analysis
Image reconstruction
Indexes
Conditional generative adversarial network
remote sensing image
cloud removal
- Language
- ISSN
- 2153-7003
Cloud removal is an essential step to enhance the quality of cloud-covered remote sensing image. In recent years, conditional Generative Adversarial Network (cGAN) yields promising improvement in plentiful image-to-image translation tasks. In this paper, we propose a novel objective function to upgrade the structural similarity index based on cGAN. We discover that ImageGAN is effective to focus on global information for thick cloud-covered images and Patch-GAN has fewer parameters while maintaining outstanding performance for thin cloud-covered remote sensing images in the experiments. Experimental results demonstrate that our method achieves remarkable performance in both PSNR, SSIM and visual effect on cloud-covered remote sensing images especially thin cloud-covered images.