SSDFusion: A Semantic Segmentation Driven Framework for Infrared and Visible Image Fusion

Fusing infrared images with visible images facilitates obtaining more abundant and accurate information content. However, existing infrared and visible image fusion methods often lack attention to the semantic information and global context information in the original images. To address these issues...

Full description

Saved in:
Bibliographic Details
Main Authors: Qishen Lv, Rui Yang, Chengmin Zhang, Shuaihui Liu, Xinyan Fan, Zihao Luo
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11029297/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849421861835767808
author Qishen Lv
Rui Yang
Chengmin Zhang
Shuaihui Liu
Xinyan Fan
Zihao Luo
author_facet Qishen Lv
Rui Yang
Chengmin Zhang
Shuaihui Liu
Xinyan Fan
Zihao Luo
author_sort Qishen Lv
collection DOAJ
description Fusing infrared images with visible images facilitates obtaining more abundant and accurate information content. However, existing infrared and visible image fusion methods often lack attention to the semantic information and global context information in the original images. To address these issues, we propose a novel deep learning framework for infrared and visible image fusion, which is named Semantic Segmentation Driven Infrared and Visible Image Fusion Framework (SSDFusion). Within the fusion framework, the Local Global Feature Extraction Fusion Module is employed, complemented by the decoder. Furthermore, under the guidance of semantic segmentation, SSDFusion achieves a better understanding of complex scene region information, enhancing fusion task performance. Finally, an adaptive loss function is implemented throughout SSDFusion to fine-tune the balance between the semantic segmentation task and the image fusion task by adjusting their proportional contributions. This approach aids in more accurately preserving the semantic information in the image, thereby enhancing the performance of the fusion framework. We conducted comparative experiments on the MSRS dataset with existing advanced fusion methods. The experimental results show that SSDFusion performs best in both qualitative and quantitative metrics. Analysis of the public datasets indicates that our algorithm can improve the entropy (EN), spatial frequency (SF), standard deviation (SD), mutual information (MI), visual information fidelity (VIF), and edge-based similarity measure (Q<inline-formula> <tex-math notation="LaTeX">${}_{\text {AB/F}}$ </tex-math></inline-formula>) metrics with about 15.33%, 91.55%, 17.09%, 93.39%, 66.94%, and 122.56% gains, respectively. The ablation study further demonstrates that the local global feature fusion module, the adaptive fusion loss function, and the integration of semantic segmentation and image fusion have significant effects on improving the model performance. SSDFusion also exhibits excellent performance in terms of computational efficiency and parameter count. Furthermore, we have also verified the good generalization ability of SSDFusion on the RoadScene and M3FD datasets.
format Article
id doaj-art-01ee3303c7514c25a12f5bf928e63039
institution Kabale University
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-01ee3303c7514c25a12f5bf928e630392025-08-20T03:31:21ZengIEEEIEEE Access2169-35362025-01-011310235910237210.1109/ACCESS.2025.357847811029297SSDFusion: A Semantic Segmentation Driven Framework for Infrared and Visible Image FusionQishen Lv0https://orcid.org/0009-0001-1917-5033Rui Yang1https://orcid.org/0009-0006-8592-7375Chengmin Zhang2Shuaihui Liu3Xinyan Fan4Zihao Luo5School of Electronic Engineering, Jiangsu Ocean University, Lianyungang, Jiangsu, ChinaSchool of Electronic Engineering, Jiangsu Ocean University, Lianyungang, Jiangsu, ChinaSchool of Electronic Engineering, Jiangsu Ocean University, Lianyungang, Jiangsu, ChinaSchool of Electronic Engineering, Jiangsu Ocean University, Lianyungang, Jiangsu, ChinaSchool of Electronic Engineering, Jiangsu Ocean University, Lianyungang, Jiangsu, ChinaSchool of Electronic Engineering, Jiangsu Ocean University, Lianyungang, Jiangsu, ChinaFusing infrared images with visible images facilitates obtaining more abundant and accurate information content. However, existing infrared and visible image fusion methods often lack attention to the semantic information and global context information in the original images. To address these issues, we propose a novel deep learning framework for infrared and visible image fusion, which is named Semantic Segmentation Driven Infrared and Visible Image Fusion Framework (SSDFusion). Within the fusion framework, the Local Global Feature Extraction Fusion Module is employed, complemented by the decoder. Furthermore, under the guidance of semantic segmentation, SSDFusion achieves a better understanding of complex scene region information, enhancing fusion task performance. Finally, an adaptive loss function is implemented throughout SSDFusion to fine-tune the balance between the semantic segmentation task and the image fusion task by adjusting their proportional contributions. This approach aids in more accurately preserving the semantic information in the image, thereby enhancing the performance of the fusion framework. We conducted comparative experiments on the MSRS dataset with existing advanced fusion methods. The experimental results show that SSDFusion performs best in both qualitative and quantitative metrics. Analysis of the public datasets indicates that our algorithm can improve the entropy (EN), spatial frequency (SF), standard deviation (SD), mutual information (MI), visual information fidelity (VIF), and edge-based similarity measure (Q<inline-formula> <tex-math notation="LaTeX">${}_{\text {AB/F}}$ </tex-math></inline-formula>) metrics with about 15.33%, 91.55%, 17.09%, 93.39%, 66.94%, and 122.56% gains, respectively. The ablation study further demonstrates that the local global feature fusion module, the adaptive fusion loss function, and the integration of semantic segmentation and image fusion have significant effects on improving the model performance. SSDFusion also exhibits excellent performance in terms of computational efficiency and parameter count. Furthermore, we have also verified the good generalization ability of SSDFusion on the RoadScene and M3FD datasets.https://ieeexplore.ieee.org/document/11029297/Attention mechanismconvolutional neural networkimage fusionsemantic segmentationtransformer
spellingShingle Qishen Lv
Rui Yang
Chengmin Zhang
Shuaihui Liu
Xinyan Fan
Zihao Luo
SSDFusion: A Semantic Segmentation Driven Framework for Infrared and Visible Image Fusion
IEEE Access
Attention mechanism
convolutional neural network
image fusion
semantic segmentation
transformer
title SSDFusion: A Semantic Segmentation Driven Framework for Infrared and Visible Image Fusion
title_full SSDFusion: A Semantic Segmentation Driven Framework for Infrared and Visible Image Fusion
title_fullStr SSDFusion: A Semantic Segmentation Driven Framework for Infrared and Visible Image Fusion
title_full_unstemmed SSDFusion: A Semantic Segmentation Driven Framework for Infrared and Visible Image Fusion
title_short SSDFusion: A Semantic Segmentation Driven Framework for Infrared and Visible Image Fusion
title_sort ssdfusion a semantic segmentation driven framework for infrared and visible image fusion
topic Attention mechanism
convolutional neural network
image fusion
semantic segmentation
transformer
url https://ieeexplore.ieee.org/document/11029297/
work_keys_str_mv AT qishenlv ssdfusionasemanticsegmentationdrivenframeworkforinfraredandvisibleimagefusion
AT ruiyang ssdfusionasemanticsegmentationdrivenframeworkforinfraredandvisibleimagefusion
AT chengminzhang ssdfusionasemanticsegmentationdrivenframeworkforinfraredandvisibleimagefusion
AT shuaihuiliu ssdfusionasemanticsegmentationdrivenframeworkforinfraredandvisibleimagefusion
AT xinyanfan ssdfusionasemanticsegmentationdrivenframeworkforinfraredandvisibleimagefusion
AT zihaoluo ssdfusionasemanticsegmentationdrivenframeworkforinfraredandvisibleimagefusion