DDFNet-A: Attention-Based Dual-Branch Feature Decomposition Fusion Network for Infrared and Visible Image Fusion

Author:

Wei Qiancheng1,Liu Ying1,Jiang Xiaoping1,Zhang Ben1,Su Qiya2,Yu Muyao2

Affiliation:

1. University of Chinese Academy of Sciences, Beijing 101408, China

2. Beijing Institute of Remote Sensing Equipment, Beijing 100005, China

Abstract

The fusion of infrared and visible images aims to leverage the strengths of both modalities, thereby generating fused images with enhanced visible perception and discrimination capabilities. However, current image fusion methods frequently treat common features between modalities (modality-commonality) and unique features from each modality (modality-distinctiveness) equally during processing, neglecting their distinct characteristics. Therefore, we propose a DDFNet-A for infrared and visible image fusion. DDFNet-A addresses this limitation by decomposing infrared and visible input images into low-frequency features depicting modality-commonality and high-frequency features representing modality-distinctiveness. The extracted low and high features were then fused using distinct methods. In particular, we propose a hybrid attention block (HAB) to improve high-frequency feature extraction ability and a base feature fusion (BFF) module to enhance low-frequency feature fusion ability. Experiments were conducted on public infrared and visible image fusion datasets MSRS, TNO, and VIFB to validate the performance of the proposed network. DDFNet-A achieved competitive results on three datasets, with EN, MI, VIFF, QAB/F, FMI, and Qs metrics reaching the best performance on the TNO dataset, achieving 7.1217, 2.1620, 0.7739, 0.5426, 0.8129, and 0.9079, respectively. These values are 2.06%, 11.95%, 21.04%, 21.52%, 1.04%, and 0.09% higher than those of the second-best methods, respectively. The experimental results confirm that our DDFNet-A achieves better fusion performance than state-of-the-art (SOTA) methods.

Funder

National Natural Science Foundation of China

Fundamental Research Funds for the Central Universities

Publisher

MDPI AG

Reference79 articles.

1. An Adaptive Fusion Algorithm for Visible and Infrared Videos Based on Entropy and the Cumulative Distribution of Gray Levels;Hu;IEEE Trans. Multimedia,2017

2. Multisensor Image Fusion and Enhancement in Spectral Total Variation Domain;Zhao;IEEE Trans. Multimed.,2018

3. Feature Level Image Fusion of Optical Imagery and Synthetic Aperture Radar (SAR) for Invasive Alien Plant Species Detection and Mapping;Rajah;Remote Sens. Appl. Soc. Environ.,2018

4. A Dual-Domain Super-Resolution Image Fusion Method with SIRV and GALCA Model for PolSAR and Panchromatic Images;Liu;IEEE Trans. Geosci. Remote Sens.,2022

5. Zhang, X., Ye, P., Qiao, D., Zhao, J., Peng, S., and Xiao, G. (2019, January 2–5). Object Fusion Tracking Based on Visible and Infrared Images Using Fully Convolutional Siamese Networks. Proceedings of the 2019 22th International Conference on Information Fusion (FUSION), Ottawa, ON, Canada.

Cited by 1 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3