Modified OMP based sparse representation for multi-sensor images fusion

Fuyu Huang, Changfan Zou, Gang Li, Yuanbo Wang, Shuai Zhang

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

Abstract

In this paper, a novel fusion method is proposed combining the sparse representation and nonsubsampled contourlet transform (NSCT). The fusion framework consists of two parts: low-frequency components fusion and high-frequency sub-bands fusion. Firstly, the original images are divided into low-frequency component and high-frequency components using the NSCT transformation. Secondly, a modified OMP is proposed for the sparse representation of low-frequency images and the weight fusion rule is designed for sparse coefficients fusion. Then, the high-frequency sub-bands images are fused using the Max-L1 way. Finally, the fusion image can be obtained by inverse NSCT transformation of two images from different fusion parts.

Original languageEnglish
Title of host publicationSixth Symposium on Novel Optoelectronic Detection Technology and Applications
EditorsJunhao Chu, Huilin Jiang
PublisherSPIE
ISBN (Electronic)9781510637047
DOIs
Publication statusPublished - 2020
Externally publishedYes
Event6th Symposium on Novel Optoelectronic Detection Technology and Applications - Beijing, China
Duration: 3 Dec 20195 Dec 2019

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume11455
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Conference

Conference6th Symposium on Novel Optoelectronic Detection Technology and Applications
Country/TerritoryChina
CityBeijing
Period3/12/195/12/19

Keywords

  • Image fusion
  • Modified OMP
  • Multi-sensor image
  • Nonsubsampled contourlet transform
  • Sparse representation

Fingerprint

Dive into the research topics of 'Modified OMP based sparse representation for multi-sensor images fusion'. Together they form a unique fingerprint.

Cite this