基于前向-后向自校正扩散引导特征重建的图像融合
作者:
作者单位:

1. 上海电力大学 自动化工程学院,上海 200090;2. 上海交通大学 航空航天学院,上海 200240

作者简介:

通讯作者:

E-mail: liugang@shiep.edu.cn.

中图分类号:

TP391

基金项目:

国家自然科学基金项目(61673270,61203224);国家973计划项目(2014CB744903);上海浦江人才计划项目(16PJD028).


An image fusion method using forward-backward self-correcting diffusion guided feature reconstruction
Author:
Affiliation:

1. College of Automation Engineering,Shanghai University of Electric Power,Shanghai 200090,China;2. School of Aeronautics and Astronautics,Shanghai Jiao Tong University,Shanghai 200240,China

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    现有图像融合方法不同程度地存在边缘阶梯效应,导致一些空间伪影引入融合图像.鉴于此,提出一种新的解决图像融合过程中鲁棒性差的方法-----前向-后向自校正扩散引导特征重建(forward-backward self-correcting diffusion,FBSD),对分解后各特征之间的差异设计一种基于期望值最大算法和主成分分析的混杂融合策略.最后利用评价指标评估所提出算法的性能,验证了所提出方法在边缘阶梯效应的处理上优于现有的图像融合方法,同时验证了融合决策的有效性.

    Abstract:

    The existing image fusion methods have an edge ladder effect in varying degrees, which leads to some spatial artifacts introduced into the fused image. This paper proposes a new method to solve the poor robustness in the process of image fusion, that is, forward-backward self-correcting diffusion(FBSD) guided feature reconstruction. According to the differences between features after decomposition, a hybrid fusion strategy based on expectation-maximization algorithm and principal component analysis algorithm is designed. Finally, the evaluation index is used to evaluate the performance of the proposed algorithm, and it is verified that this method is better than the existing image fusion methods in dealing with the edge step effect, and the fusion decision is effective.

    参考文献
    相似文献
    引证文献
引用本文

张相博,刘刚,肖刚.基于前向-后向自校正扩散引导特征重建的图像融合[J].控制与决策,2022,37(8):2134-2140

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:
  • 最后修改日期:
  • 录用日期:
  • 在线发布日期: 2022-06-29
  • 出版日期: 2022-08-20