Infrared and Visible Image Fusion via L0 Decomposition and Intensity Mask

Image fusion integrates complex information about a target scene from multiple sensors into a single image. The fused image can further be utilized for human perception or different machine vision tasks. In the case of infrared and visible images, infrared images have the advantage of capturing ther...

Full description

Saved in:
Bibliographic Details
Main Authors: Lei Yan, Jie Cao, Yang Cheng, Saad Rizvi, Qun Hao
Format: Article
Language:English
Published: IEEE 2019-01-01
Series:IEEE Photonics Journal
Subjects:
Online Access:https://ieeexplore.ieee.org/document/8894856/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849417261569277952
author Lei Yan
Jie Cao
Yang Cheng
Saad Rizvi
Qun Hao
author_facet Lei Yan
Jie Cao
Yang Cheng
Saad Rizvi
Qun Hao
author_sort Lei Yan
collection DOAJ
description Image fusion integrates complex information about a target scene from multiple sensors into a single image. The fused image can further be utilized for human perception or different machine vision tasks. In the case of infrared and visible images, infrared images have the advantage of capturing thermal radiation intensity, whereas visible images are superior in gradient texture. In order to effectively fuse thermal intensity of infrared image and texture advantage of visible image, we propose a novel fusion method based on L0 decomposition and intensity mask. The proposed method first acquires base and detail layers of images (visible & infrared) using L0 decomposition. Next, an intensity mask is obtained using the basic global thresholding method on base layers of infrared image. The layers (base layers and detail layers) and visible images are divided images into three parts by the use of intensity mask, namely, mask-base layers, mask-detail layers, and texture-background. The first and second parts effectively achieve intensity blending, whereas the third part achieves the fused image with a clear gradient texture. The proposed method shows superior performance when compared with five state-of-the-art methods (on publicly available databases).
format Article
id doaj-art-7ef252637ea34ddcb083c9be66dcbb06
institution Kabale University
issn 1943-0655
language English
publishDate 2019-01-01
publisher IEEE
record_format Article
series IEEE Photonics Journal
spelling doaj-art-7ef252637ea34ddcb083c9be66dcbb062025-08-20T03:32:54ZengIEEEIEEE Photonics Journal1943-06552019-01-0111611110.1109/JPHOT.2019.29526548894856Infrared and Visible Image Fusion via L0 Decomposition and Intensity MaskLei Yan0https://orcid.org/0000-0002-7152-0519Jie Cao1https://orcid.org/0000-0001-8376-7669Yang Cheng2Saad Rizvi3https://orcid.org/0000-0003-3942-0857Qun Hao4https://orcid.org/0000-0003-2577-9391Key Laboratory of Biomimetic Robots and Systems, School of Optics and Photonics, Beijing Institute of Technology, Ministry of Education, Beijing, ChinaKey Laboratory of Biomimetic Robots and Systems, School of Optics and Photonics, Beijing Institute of Technology, Ministry of Education, Beijing, ChinaKey Laboratory of Biomimetic Robots and Systems, School of Optics and Photonics, Beijing Institute of Technology, Ministry of Education, Beijing, ChinaKey Laboratory of Biomimetic Robots and Systems, School of Optics and Photonics, Beijing Institute of Technology, Ministry of Education, Beijing, ChinaKey Laboratory of Biomimetic Robots and Systems, School of Optics and Photonics, Beijing Institute of Technology, Ministry of Education, Beijing, ChinaImage fusion integrates complex information about a target scene from multiple sensors into a single image. The fused image can further be utilized for human perception or different machine vision tasks. In the case of infrared and visible images, infrared images have the advantage of capturing thermal radiation intensity, whereas visible images are superior in gradient texture. In order to effectively fuse thermal intensity of infrared image and texture advantage of visible image, we propose a novel fusion method based on L0 decomposition and intensity mask. The proposed method first acquires base and detail layers of images (visible & infrared) using L0 decomposition. Next, an intensity mask is obtained using the basic global thresholding method on base layers of infrared image. The layers (base layers and detail layers) and visible images are divided images into three parts by the use of intensity mask, namely, mask-base layers, mask-detail layers, and texture-background. The first and second parts effectively achieve intensity blending, whereas the third part achieves the fused image with a clear gradient texture. The proposed method shows superior performance when compared with five state-of-the-art methods (on publicly available databases).https://ieeexplore.ieee.org/document/8894856/Image fusionL0 decompositionintensity maskmaximum gradient.
spellingShingle Lei Yan
Jie Cao
Yang Cheng
Saad Rizvi
Qun Hao
Infrared and Visible Image Fusion via L0 Decomposition and Intensity Mask
IEEE Photonics Journal
Image fusion
L0 decomposition
intensity mask
maximum gradient.
title Infrared and Visible Image Fusion via L0 Decomposition and Intensity Mask
title_full Infrared and Visible Image Fusion via L0 Decomposition and Intensity Mask
title_fullStr Infrared and Visible Image Fusion via L0 Decomposition and Intensity Mask
title_full_unstemmed Infrared and Visible Image Fusion via L0 Decomposition and Intensity Mask
title_short Infrared and Visible Image Fusion via L0 Decomposition and Intensity Mask
title_sort infrared and visible image fusion via l0 decomposition and intensity mask
topic Image fusion
L0 decomposition
intensity mask
maximum gradient.
url https://ieeexplore.ieee.org/document/8894856/
work_keys_str_mv AT leiyan infraredandvisibleimagefusionvial0decompositionandintensitymask
AT jiecao infraredandvisibleimagefusionvial0decompositionandintensitymask
AT yangcheng infraredandvisibleimagefusionvial0decompositionandintensitymask
AT saadrizvi infraredandvisibleimagefusionvial0decompositionandintensitymask
AT qunhao infraredandvisibleimagefusionvial0decompositionandintensitymask