Two-Stream Edge-Aware Network for Infrared and Visible Image Fusion with Multi-Level Wavelet Decomposition

Infrared and visible image fusion (IVIF) aims to generate a fused image with both salient target and rich textures from two different complementary modality images. To better integrate valuable edge information into the fused image, we first propose a novel two-stream network based on Auto-Encoder (...

Full description

Saved in:
Bibliographic Details
Published in:IEEE access 2024-01, Vol.12, p.1-1
Main Authors: Wang, Haozhe, Shu, Chang, Li, Xiaofeng, Fu, Yu, Fu, Zhizhong, Yin, Xiaofeng
Format: Article
Language:English
Subjects:
Computer vision
Decomposition
Discrete wavelet transforms
edge information
Feature extraction
Feature maps
Fuses
Image edge detection
Image fusion
Infrared imagery
Infrared imaging
Low-pass filters
multi-scale analysis
Streaming media
Visual perception
wavelet decomposition
Wavelet transforms
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Infrared and visible image fusion (IVIF) aims to generate a fused image with both salient target and rich textures from two different complementary modality images. To better integrate valuable edge information into the fused image, we first propose a novel two-stream network based on Auto-Encoder (AE) framework, which extracts deep hierarchical detail information at coarse scale from base stream by multi-level wavelet decomposition progressively and incorporates them into detail stream for information compensation. The aggregation of edge information ranging from coarse to fine facilitates a more comprehensive representation of contours and textures. Then, we propose a new feature fusion strategy, termed as Structural Feature Map Decomposition (SFMD). The first step is to decompose local patches of feature map with each modality into three independent components by Structural Patch Decomposition (SPD). In the second step, appropriate fusion rules are carefully designed for each component and the fused patch can be derived by inverse SPD. Our extensive experiments on several benchmark datasets show that our method outperforms seven compared state-of-the-art methods, especially in human visual perception.
ISSN:2169-3536
2169-3536
DOI:10.1109/ACCESS.2024.3364050