The fusion of infrared and visible images of the same scene aims to generate a composite image which can provide a more comprehensive description of the scene. In this paper, we propose an infrared and visible image fusion method based on convolutional neural networks (CNNs). In particular, a siamese convolutional network is applied to obtain a weight map which integrates the pixel activity information from two source images. This CNN-based approach can deal with two vital issues in image fusion as a whole, namely, activity level measurement and weight assignment. Considering the different imaging modalities of infrared and visible images, the merging procedure is conducted in a multi-scale manner via image pyramids and a local similarity-based strategy is adopted to adaptively adjust the fusion mode for the decomposed coefficients. Experimental results demonstrate that the proposed method can achieve state-of-the-art results in terms of both visual quality and objective assessment.

Yu Liu

Xun Chen

Juan Cheng

Hu Peng

Zengfu Wang

International Journal of Wavelets Multiresolution and Information Processing

INTERNATIONAL JOURNAL OF WAVELETS, MULTIRESOLUTION AND INFORMATION PROCESSING（以下简称 IJWMIP）是关于小波分析、多分辨率和信息处理当前最新成果的理论和应用论文的双月刊。 IJWMIP 主题特别征集，包括理论、方法、算法和新兴应用。 IJWMIP 感兴趣的主题包括但不限于：1。小波：小波与算子理论框架与应用时频分析与应用稀疏表示与逼近采样理论与压缩感知基于小波的算法与应用2．多分辨率：多分辨率分析多尺度逼近多分辨率图像处理和信号处理多分辨率表示深度学习和神经网络机器学习理论、算法和应用高维数据分析3．信息处理：数据科学大数据与应用信息论信息系统与技术信息安全信息学习与处理人工智能与模式识别图像/信号处理。

The International Journal of Wavelets, Multiresolution and Information Processing (IJWMIP) is a bi-monthly journal dedicated to the latest theoretical and applied research in wavelet analysis, multiresolution, and information processing. IJWMIP invites submissions on topics including, but not limited to: 1. Wavelets: Wavelet and operator theory frameworks, time-frequency analysis and applications, sparse representation and approximation, sampling theory and compressed sensing, wavelet-based algorithms and applications; 2. Multiresolution: Multiresolution analysis, multiscale approximation, multiresolution image and signal processing, multiresolution representation, deep learning and neural networks, theories, algorithms, and applications of machine learning, high-dimensional data analysis; 3. Information Processing: Data science, big data and applications, information theory, information systems and technology, information security, information learning and processing, artificial intelligence and pattern recognition, image/signal processing.

《International Journal of Wavelets, Multiresolution and Information Processing》（以下简称 IJWMIP）是一本双月刊，专注于小波分析、多分辨率和信息处理领域的最新理论与应用研究。IJWMIP 特别征集与以下主题相关的论文：1. 小波：小波与算子理论框架、时频分析及其应用、稀疏表示与逼近、采样理论与压缩感知、基于小波的算法与应用；2. 多分辨率：多分辨率分析、多尺度逼近、多分辨率图像处理与信号处理、多分辨率表示、深度学习与神经网络、机器学习的理论、算法与应用、高维数据分析；3. 信息处理：数据科学、大数据与应用、信息论、信息系统与技术、信息安全、信息学习与处理、人工智能与模式识别、图像/信号处理。

International Journal of Wavelets, Multiresolution and Information Processing

Int. J. Wavelets Multiresolut Inf. Process.

Infrared and visible image fusion with convolutional neural networks

This paper proposes an infrared fusion image that combines infrared and visible images of the same scene to generate a composite image which can provide a more comprehensive description of the scene.

Category	Quartile
计算机科学	4
计算机科学, 计算机软件工程	4
计算机科学, 数学跨学科应用	4

Infrared and visible image fusion with convolutional neural networks

ivySCI AI Smartly Parses PDF, Answers Researchers' Questions, and Helps You Understand Papers in Seconds

Journal Info

Category	Quartile
MATHEMATICS, INTERDISCIPLINARY APPLICATIONS	4