A General Perceptual Infrared and Visible Image Fusion Framework Based on Linear Filter and Side Window Filtering Technology

Huibin Yan,Zhongmin Li

doi:10.1109/access.2019.2961626

Huibin Yan, Zhongmin Li

Open Access

PDF Available

https://doi.org/10.1109/access.2019.2961626

Copy DOI

Export

Save

Cite

Journal: IEEE Access	Publication Date: Jan 1, 2020
Citations: 5	License type: CC BY 4.0

Affiliation: Nanchang Hangkong University

Abstract
Highlights/Summary
Full-Text PDF
Similar Papers

Abstract

Listen

Recently, edge-preserving filters have achieved great success in infrared (IR) and visible (VI) image fusion field. However, most edge-preserving filters are complex. In this paper, with the side window filtering technology by which most filters can improve their edge-preserving capabilities, we propose a general perceptual IR and VI image fusion framework with simple linear filter. Firstly, the source images are decomposed into edge feature components, hybrid components and base components by using linear filter and its side window version. Then, these components are combined by max-absolute fusion rule and improved max-absolute fusion rule. Finally, the fused image is reconstructed by adding all the fused components. In our experiments, two popular linear filters, i.e., box filter and Gaussian filter, are used to verify the effectiveness of the proposed framework. Experimental results show that the proposed fusion framework can obtain better perceptual fusion results than compared methods.

Highlights

Visible (VI) images can reflect clear details and background scenery, which can lead to better situation awareness
We demonstrate that just using linear filter can obtain perceptual fusion results for IR and VI images with the side window filtering (SWF) technology
(2) We propose a general perceptual IR and VI image fusion framework based on linear filter and SWF technology to achieve visually satisfactory fusion

Summary

Introduction

Visible (VI) images can reflect clear details and background scenery, which can lead to better situation awareness. Infrared (IR) images can present obvious thermal object information, which are conducive to object detection and recognition. Infrared (IR) and visible (VI) image fusion is an important part of multi-sensor informa-tion fusion, which benefits many applications [1]. Taking advantage of all the information of the source image is the main core of image fusion. As for IR and VI image fusion, integrating all the information of IR and VI images will make the fusion results visually unpleasing because they are two different phenomena of the same scene. Many IR and VI image fusion methods have been proposed, and we divide them into three categories, i.e., multi-scale transform (MST)-based methods, deep learning (DL)-based methods, and other methods.

Objectives

Methods

Results

Conclusion