首页|期刊导航|Astronomical Techniques and Instruments|A nonrigid registration deep-learning model for solar photosphere images using a hybrid cross-attention mechanism

A nonrigid registration deep-learning model for solar photosphere images using a hybrid cross-attention mechanismOA

中文摘要

Image registration within a solar photosphere sequence is crucial for observational solar physics studies requiring high spatial and temporal resolutions.Previously,we identified residual large-scale nonrigid distortions in high-resolution solar photosphere images from ground-based telescopes after high-resolution reconstruction.Because these distortions are not eliminated by conventional sequence correlation alignment,they can affect the analysis of small-scale activity in the solar photosphere.Here,we implemented an image registration model using deep learning(HCAM-Net)to solve the problem.Within an encoder-decoder framework,we introduced a hybrid attention mechanism to improve context information capture and extract accurate deformation fields.Analyzing solar photosphere images acquired by the New Vacuum Solar Telescope,we demonstrated that the proposed model effectively achieved highly accurate nonrigid image registration.Evaluation metrics and visualization results indicated that our model outperformed current state-of-the-art models,such as VoxelMorph and TransMorph,for nonrigid registration of solar photosphere images,with a structural similarity index measure of 0.965 and a coefficient of determination of 0.976.

Mengwei Ban;Rui Wang;Zhi Xu;Zhongyan Liu;Xudong Nan

School of Electronics and Information,Xi’an Polytechnic University,Xi’an 710600,ChinaSchool of Electronics and Information,Xi’an Polytechnic University,Xi’an 710600,China Shaanxi Artificial Intelligence Joint Laboratory,Xi’an Polytechnic University,Xi’an 710600,ChinaYunnan Observatories,Chinese Academy of Sciences,Kunming 650216,ChinaSchool of Electronics and Information,Xi’an Polytechnic University,Xi’an 710600,ChinaSchool of Electronics and Information,Xi’an Polytechnic University,Xi’an 710600,China

天文与地球科学

Solar image registrationDeep learningUnsupervised learningHybrid attention mechanism

《Astronomical Techniques and Instruments》 2026 (2)

P.112-120,9

funded by the Strategic Priority Research Program of the Chinese Academy of Sciences(XDB0560000)the National Natural Science Foundation of China(12473054)the Basic Research on Fund Projects in Yunnan Province(2019FA001)the Yunnan Province Science Foundation Project(202105AC160085).

10.61977/ati2025043

评论