Fusion of Infrared and Visible Images based on visual contrast in Human Vision Space

Rao Yang, Lingjuan Miao, Zhiqiang Zhou, Saijia Cui, Yusen Lin

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

The purpose of infrared and visible image fusion is to merge the complementary information of source images. However, most fusion algorithms just consider the preservation of information, while overlook the visual effect of the fused image. In this paper, we propose a method of infrared and visible image fusion based on the adaptation of human visual system. The source images are firstly been decomposed into band-pass and low-pass images of different frequencies by the guided filter. Then the local adaptation process is applied to acquire the visual contrast which is in the space of human vision. After that, the fusion schemes based on the visual saliency are used to merge the contrast coefficients. At last, image reconstruction is implemented to obtain the final fused image. Experimental results of objective and subjective assessments prove the effective and excellent performance of the proposed method.

Original languageEnglish
Title of host publicationProceedings of the 40th Chinese Control Conference, CCC 2021
EditorsChen Peng, Jian Sun
PublisherIEEE Computer Society
Pages2969-2974
Number of pages6
ISBN (Electronic)9789881563804
DOIs
Publication statusPublished - 26 Jul 2021
Event40th Chinese Control Conference, CCC 2021 - Shanghai, China
Duration: 26 Jul 202128 Jul 2021

Publication series

NameChinese Control Conference, CCC
Volume2021-July
ISSN (Print)1934-1768
ISSN (Electronic)2161-2927

Conference

Conference40th Chinese Control Conference, CCC 2021
Country/TerritoryChina
CityShanghai
Period26/07/2128/07/21

Keywords

  • Image fusion
  • adaptation
  • guided filter
  • human vision space
  • visual contrast

Fingerprint

Dive into the research topics of 'Fusion of Infrared and Visible Images based on visual contrast in Human Vision Space'. Together they form a unique fingerprint.

Cite this