Removing cloud shadows from ground-based solar imagery

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Chaoui, Amal, Morgan, Jay Paul, Paiement, Adeline, Aboudarham, Jean
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917726790877184
author Chaoui, Amal
Morgan, Jay Paul
Paiement, Adeline
Aboudarham, Jean
author_facet Chaoui, Amal
Morgan, Jay Paul
Paiement, Adeline
Aboudarham, Jean
contents The study and prediction of space weather entails the analysis of solar images showing structures of the Sun's atmosphere. When imaged from the Earth's ground, images may be polluted by terrestrial clouds which hinder the detection of solar structures. We propose a new method to remove cloud shadows, based on a U-Net architecture, and compare classical supervision with conditional GAN. We evaluate our method on two different imaging modalities, using both real images and a new dataset of synthetic clouds. Quantitative assessments are obtained through image quality indices (RMSE, PSNR, SSIM, and FID). We demonstrate improved results with regards to the traditional cloud removal technique and a sparse coding baseline, on different cloud types and textures.
format Preprint
id arxiv_https___arxiv_org_abs_2407_13379
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Removing cloud shadows from ground-based solar imagery
Chaoui, Amal
Morgan, Jay Paul
Paiement, Adeline
Aboudarham, Jean
Computer Vision and Pattern Recognition
Image and Video Processing
The study and prediction of space weather entails the analysis of solar images showing structures of the Sun's atmosphere. When imaged from the Earth's ground, images may be polluted by terrestrial clouds which hinder the detection of solar structures. We propose a new method to remove cloud shadows, based on a U-Net architecture, and compare classical supervision with conditional GAN. We evaluate our method on two different imaging modalities, using both real images and a new dataset of synthetic clouds. Quantitative assessments are obtained through image quality indices (RMSE, PSNR, SSIM, and FID). We demonstrate improved results with regards to the traditional cloud removal technique and a sparse coding baseline, on different cloud types and textures.
title Removing cloud shadows from ground-based solar imagery
topic Computer Vision and Pattern Recognition
Image and Video Processing
url https://arxiv.org/abs/2407.13379