基于内生长机制和卷积稀疏表示的红外与可见光图像融合
作者:
作者单位:

重庆工商大学机械工程学院

作者简介:

通讯作者:

中图分类号:

TP391

基金项目:

国家自然科学基金项目(面上项目,重点项目,重大项目)


Infrared and Visible Light Image Fusion Based on Internal Generative Mechanism and Convolution Sparse Representation
Author:
Affiliation:

College of Mechanical Engineering,Chongqing Technology and Business University

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:

    为了提升红外与可见光图像融合视觉效果,克服融合结果的伪影效应,提出一种基于内生长机制结合卷积稀疏表示的图像融合方法。首先,采用符合人类大脑推理的内生长机制对源图像进行分解,获取预测层和细节层;然后对细节层采用卷积稀疏表示进行二次分解,获取二次细节层和基本层,并分别对其采用活动水平测度取大以及加权平均规则进行融合;针对预测层定义ISR混合算子融合规则并进行融合;最后,将融合后的预测层和细节层相加获取最终融合结果。实验中,本文采用三组具有代表性的红外与可见光图像进行算法测试,实验表明提出的方法具有较好的主观视觉效果,并且客观评价指标也更好,具有有效性。

    Abstract:

    In order to improve the visual effect of infrared and visible light image fusion and overcome the artifact effect of the fusion result, an image fusion method based on internal generative mechanism and convolution sparse representation is proposed. First, the source image is decomposed by internal generative mechanism that conforms to the reasoning of the human brain to obtain the prediction layer and the detail layer. Then the detail layer is decomposed using a convolution sparse representation to obtain the secondary detail layer and the basic layer, and adopts the activity level measurement to be larger and the weighted average rule for fusions separately; defines the ISR hybrid operator fusion rule for the prediction layer and fuse; finally, the fusion prediction layer and detail layer are added to obtain the final fusion result. In the experiment, this paper uses three representative infrared and visible light images for algorithm testing. The experiment shows that the proposed method has good subjective visual effects, and the objective evaluation indicators are also better and effective.□□□□□□□□□□□□□

    参考文献
    相似文献
    引证文献
引用本文
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:2020-08-05
  • 最后修改日期:2021-09-21
  • 录用日期:2020-11-05
  • 在线发布日期: 2020-12-02
  • 出版日期: