Paper
18 December 2023 Image super-resolution reconstruction for EAST TiO band (7057Å) solar images
Zhimao Du, Zhiyong Wang, Xuejun Rao
Author Affiliations +
Abstract
The Educational Adaptive-optics Solar Telescope is the most advanced solar telescope available for scientific education currently. However, in some situations, strong atmospheric turbulence or equipment failure cause the solar adaptive optics system to fail, resulting in high-resolution imaging systems only being able to record open loop solar images with low quality and a lack of detailed texture information. Traditional image interpolation algorithms have limited expressive capabilities, however deep-learning methods can be trained for generating high-quality images from paired data sets. Our research is based on Real-ESRGAN, a powerful deep neural network that is utilized to solve real-world single image super-resolution reconstruction problems. We select 130 close loop TiO band (7057Å) images recorded on 2022 August 4 and another 203 on 2022 September 22 as the training datasets. For two representative examples, we evaluate the effect of image reconstruction from open loop images, and the peak signal-to-noise ratio and the structural similarity index measurement values of the reconstructed images generated by Real-ESRGAN are higher than those obtained using open loop data. As a result, some reconstruction image generated by Real-ESRGAN from the open loop solar image can be used some supplementary data.
© (2023) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Zhimao Du, Zhiyong Wang, and Xuejun Rao "Image super-resolution reconstruction for EAST TiO band (7057Å) solar images", Proc. SPIE 12965, AOPC 2023: Novel Technologies and Instruments for Astronomical Imaging and Spectroscopy, 1296503 (18 December 2023); https://doi.org/10.1117/12.2692232
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Image quality

Image restoration

Adaptive optics

Imaging systems

Data modeling

Image processing

Reconstruction algorithms

Back to Top