Algorithm development of cloud removal from solar images based on pix2pix network

TY - JOUR

T1 - Algorithm development of cloud removal from solar images based on pix2pix network

AU - Wu, Xian

AU - Song, Wei

AU - Zhang, Xukun

AU - Lin, Ganghua

AU - Wang, Haimin

AU - Deng, Yuanyong

N1 - Publisher Copyright: © 2022 Tech Science Press. All rights reserved.

PY - 2022

Y1 - 2022

N2 - Sky clouds affect solar observations significantly. Their shadows obscure the details of solar features in observed images. Cloud-covered solar images are difficult to be used for further research without pre-processing. In this paper, the solar image cloud removing problem is converted to an image-to-image translation problem, with a used algorithm of the Pixel to Pixel Network (Pix2Pix), which generates a cloudless solar image without relying on the physical scattering model. Pix2Pix is consists of a generator and a discriminator. The generator is a well-designed U-Net. The discriminator uses PatchGAN structure to improve the details of the generated solar image, which guides the generator to create a pseudo realistic solar image. The image generation model and the training process are optimized, and the generator is jointly trained with the discriminator. So the generation model which can stably generate cloudless solar image is obtained. Extensive experiment results onHuairou Solar Observing Station, National Astronomical Observatories, and Chinese Academy of Sciences (HSOS, NAOC and CAS) datasets show that Pix2Pix is superior to the traditional methods based on physical prior knowledge in peak signal-to-noise ratio, structural similarity, perceptual index, and subjective visual effect. The result of the PSNR, SSIM and PI are 27.2121 dB, 0.8601 and 3.3341.

AB - Sky clouds affect solar observations significantly. Their shadows obscure the details of solar features in observed images. Cloud-covered solar images are difficult to be used for further research without pre-processing. In this paper, the solar image cloud removing problem is converted to an image-to-image translation problem, with a used algorithm of the Pixel to Pixel Network (Pix2Pix), which generates a cloudless solar image without relying on the physical scattering model. Pix2Pix is consists of a generator and a discriminator. The generator is a well-designed U-Net. The discriminator uses PatchGAN structure to improve the details of the generated solar image, which guides the generator to create a pseudo realistic solar image. The image generation model and the training process are optimized, and the generator is jointly trained with the discriminator. So the generation model which can stably generate cloudless solar image is obtained. Extensive experiment results onHuairou Solar Observing Station, National Astronomical Observatories, and Chinese Academy of Sciences (HSOS, NAOC and CAS) datasets show that Pix2Pix is superior to the traditional methods based on physical prior knowledge in peak signal-to-noise ratio, structural similarity, perceptual index, and subjective visual effect. The result of the PSNR, SSIM and PI are 27.2121 dB, 0.8601 and 3.3341.

KW - Cloud removal

KW - Pix2Pix

KW - Solar image

UR - http://www.scopus.com/inward/record.url?scp=85120801245&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85120801245&partnerID=8YFLogxK

U2 - 10.32604/cmc.2022.022325

DO - 10.32604/cmc.2022.022325

M3 - Article

SN - 1546-2218

VL - 71

SP - 3497

EP - 3512

JO - Computers, Materials and Continua

JF - Computers, Materials and Continua

IS - 2

ER -