结合邻域特征与IDCSCM的红外与可见光图像融合
DOI:
作者:
作者单位:

作者简介:

通讯作者:

中图分类号:

基金项目:

国家自然科学基金项目(No.61775180)资助


Infrared and visible image fusion combining neighborhood features with IDCSCM
Author:
Affiliation:

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:

    提出了一种结合邻域特征与改进双通道脉冲发放皮层模型(Improved Dual-Channel Spiking Cortical Model,IDCSCM)的红外与可见光图像融合算法。针对传统的脉冲发放皮层模型对于图像较暗区域的处理存在不足,采用双通道脉冲发放皮层模型进行图像融合,并对其进行改进。结合非下采样剪切波对源图像进行分解,同时选用子带图像合适的邻域特征作为IDCSCM的输入激励进行融合。通过实验验证,该方法可以在保留可见背景信息的同时有效地提取红外图像的目标信息,与其他几种方法进行对比,在标准差、信息熵,以及互信息等方面有明显的提高。

    Abstract:

    An infrared and visible image fusion algorithm combining neighborhood features and Improved Dual-Channel Spiking Cortical Model (IDCSCM) is proposed.In view of the insufficiency of the traditional pulsed cortical model for the treatment of darker areas of the image,a two-channel spiking cortical model is used for image fusion and improved.The source image is decomposed with the non-subsampled shear wave,and the appropriate neighborhood features of the sub-band image are selected as the input excitation of the IDCSCM for fusion.The experimental results show that the method can extract the target information of the infrared image while retaining the visible background information.Compared with other methods,the method has obvious improvement in standard deviation,information entropy,and mutual information.

    参考文献
    相似文献
    引证文献
引用本文

巩稼民,刘爱萍,马豆豆,杨红蕊,张凯泽,赵梦凯.结合邻域特征与IDCSCM的红外与可见光图像融合[J].激光与红外,2020,50(7):889~896

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: 2020-08-05
  • 出版日期: