光学精密工程2024，Vol.32Issue(20)：3071-3084,14.DOI:10.37188/OPE.20243220.3071
变分近似解算KL散度红外可见光遥感图像配准
Infrared-visible remote sensing image registration method based on Kullback-Leibler divergence using variational approximation
摘要
Abstract
To solve the problem of poor robustness of distance-based metrics in multi-sensor remote sens-ing image registration methods,an image registration algorithm based on Kullback-Leibler divergence us-ing variational approximation was proposed.First,edge features were extracted from the infrared image and visible image,respectively.Second,the infrared image features were orthorectified using imaging pos-es,and Gaussian Mixture Models(GMMs)were constructed for the feature point sets of the infrared and visible images,respectively.Third,the Kullback-Leibler divergence between the two GMMs was calcu-lated using the variational approximation method,in which variational parameters were introduced and the Lagrange multiplier was utilized.Finally,the Particle Swarm Optimization(PSO)algorithm was applied to search for the optimal registration parameters.In the remote sensing image registration experiments,the proposed method's average Root Mean Square Error of registration parameters is 2.5,and the aver-age runtime is 1.5 seconds.Additionally,the proposed method still achieves correct registration when the variance of Gaussian noise and the salt-and-pepper noise coefficient is 0.07,respectively.These results validate the robustness and high computational efficiency of our method.关键词
变分近似法/KL散度/图像配准/遥感图像Key words
variational approximation/kullback-leibler divergence/image registration/remote sensing分类
计算机与自动化引用本文复制引用
王佳,吴昊,傅瑞罡,孔玲爽,左毅..变分近似解算KL散度红外可见光遥感图像配准[J].光学精密工程,2024,32(20):3071-3084,14.基金项目
国家自然科学基金项目(No.62201092) （No.62201092）
湖南省自然科学基金(No.2023JJ30085) （No.2023JJ30085）
湖南省教育厅基金(No.22A0599) （No.22A0599）
