Improving the Performance of Infrared and Visible Image Fusion Based on Latent Low-Rank Representation Nested With Rolling Guided Image Filtering

The fusion quality of infrared and visible image is very important for subsequent human understanding of image information and target processing. The fusion quality of the existing infrared and visible image fusion methods still has room for improvement in terms of image contrast, sharpness and rich...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Ce Gao, Congcong Song, Yanchao Zhang, Donghao Qi, Yi Yu
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	Image fusion rolling guided image filtering latent low-rank representation detail-enhanced layer Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/62fc5228386c462e8438e072e0ddb046
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:62fc5228386c462e8438e072e0ddb046
record_format	dspace
spelling	oai:doaj.org-article:62fc5228386c462e8438e072e0ddb0462021-11-19T00:07:02ZImproving the Performance of Infrared and Visible Image Fusion Based on Latent Low-Rank Representation Nested With Rolling Guided Image Filtering2169-353610.1109/ACCESS.2021.3090436https://doaj.org/article/62fc5228386c462e8438e072e0ddb0462021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9459693/https://doaj.org/toc/2169-3536The fusion quality of infrared and visible image is very important for subsequent human understanding of image information and target processing. The fusion quality of the existing infrared and visible image fusion methods still has room for improvement in terms of image contrast, sharpness and richness of detailed information. To obtain better fusion performance, an infrared and visible image fusion algorithm based on latent low-rank representation (LatLRR) nested with rolling guided image filtering (RGIF) is proposed that is a novel solution that integrates two-level decomposition and three-layer fusion. First, infrared and visible images are decomposed using LatLRR to obtain the low-rank sublayers, saliency sublayers, and sparse noise sublayers. Then, RGIF is used to perform further multiscale decomposition of the low-rank sublayers to extract multiple detail layers, which are fused using convolutional neural network (CNN)-based fusion rules to obtain the detail-enhanced layer. Next, an algorithm based on improved visual saliency mapping with weighted guided image filtering (IVSM-GIF) is used to fuse the low-rank sublayers, and an algorithm for adaptive weighting of regional energy features based on Laplacian pyramid decomposition is used to fuse the saliency sublayers. Finally, the fused low-rank sublayer, saliency sublayer, and detail-enhanced layer are used to reconstruct the final image. The experimental results show that the proposed method outperforms other state-of-the-art fusion methods in terms of visual quality and objective evaluation, achieving the highest average values in six objective evaluation metrics.Ce GaoCongcong SongYanchao ZhangDonghao QiYi YuIEEEarticleImage fusionrolling guided image filteringlatent low-rank representationdetail-enhanced layerElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 91462-91475 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Image fusion rolling guided image filtering latent low-rank representation detail-enhanced layer Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Image fusion rolling guided image filtering latent low-rank representation detail-enhanced layer Electrical engineering. Electronics. Nuclear engineering TK1-9971 Ce Gao Congcong Song Yanchao Zhang Donghao Qi Yi Yu Improving the Performance of Infrared and Visible Image Fusion Based on Latent Low-Rank Representation Nested With Rolling Guided Image Filtering
description	The fusion quality of infrared and visible image is very important for subsequent human understanding of image information and target processing. The fusion quality of the existing infrared and visible image fusion methods still has room for improvement in terms of image contrast, sharpness and richness of detailed information. To obtain better fusion performance, an infrared and visible image fusion algorithm based on latent low-rank representation (LatLRR) nested with rolling guided image filtering (RGIF) is proposed that is a novel solution that integrates two-level decomposition and three-layer fusion. First, infrared and visible images are decomposed using LatLRR to obtain the low-rank sublayers, saliency sublayers, and sparse noise sublayers. Then, RGIF is used to perform further multiscale decomposition of the low-rank sublayers to extract multiple detail layers, which are fused using convolutional neural network (CNN)-based fusion rules to obtain the detail-enhanced layer. Next, an algorithm based on improved visual saliency mapping with weighted guided image filtering (IVSM-GIF) is used to fuse the low-rank sublayers, and an algorithm for adaptive weighting of regional energy features based on Laplacian pyramid decomposition is used to fuse the saliency sublayers. Finally, the fused low-rank sublayer, saliency sublayer, and detail-enhanced layer are used to reconstruct the final image. The experimental results show that the proposed method outperforms other state-of-the-art fusion methods in terms of visual quality and objective evaluation, achieving the highest average values in six objective evaluation metrics.
format	article
author	Ce Gao Congcong Song Yanchao Zhang Donghao Qi Yi Yu
author_facet	Ce Gao Congcong Song Yanchao Zhang Donghao Qi Yi Yu
author_sort	Ce Gao
title	Improving the Performance of Infrared and Visible Image Fusion Based on Latent Low-Rank Representation Nested With Rolling Guided Image Filtering
title_short	Improving the Performance of Infrared and Visible Image Fusion Based on Latent Low-Rank Representation Nested With Rolling Guided Image Filtering
title_full	Improving the Performance of Infrared and Visible Image Fusion Based on Latent Low-Rank Representation Nested With Rolling Guided Image Filtering
title_fullStr	Improving the Performance of Infrared and Visible Image Fusion Based on Latent Low-Rank Representation Nested With Rolling Guided Image Filtering
title_full_unstemmed	Improving the Performance of Infrared and Visible Image Fusion Based on Latent Low-Rank Representation Nested With Rolling Guided Image Filtering
title_sort	improving the performance of infrared and visible image fusion based on latent low-rank representation nested with rolling guided image filtering
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/62fc5228386c462e8438e072e0ddb046
work_keys_str_mv	AT cegao improvingtheperformanceofinfraredandvisibleimagefusionbasedonlatentlowrankrepresentationnestedwithrollingguidedimagefiltering AT congcongsong improvingtheperformanceofinfraredandvisibleimagefusionbasedonlatentlowrankrepresentationnestedwithrollingguidedimagefiltering AT yanchaozhang improvingtheperformanceofinfraredandvisibleimagefusionbasedonlatentlowrankrepresentationnestedwithrollingguidedimagefiltering AT donghaoqi improvingtheperformanceofinfraredandvisibleimagefusionbasedonlatentlowrankrepresentationnestedwithrollingguidedimagefiltering AT yiyu improvingtheperformanceofinfraredandvisibleimagefusionbasedonlatentlowrankrepresentationnestedwithrollingguidedimagefiltering
_version_	1718420612104323072

Improving the Performance of Infrared and Visible Image Fusion Based on Latent Low-Rank Representation Nested With Rolling Guided Image Filtering

Ejemplares similares