Article
Computer Science, Artificial Intelligence
Feiqiang Liu, Lihui Chen, Lu Lu, Gwanggil Jeon, Xiaomin Yang
Summary: The study introduces a method combining the rolling guidance filter and convolutional sparse representation for the fusion of infrared and visible images. Experimental results demonstrate the superiority of this method in both subjective and objective assessments.
JOURNAL OF INTELLIGENT & FUZZY SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Quanli Wang, Xin Jin, Qian Jiang, Liwen Wu, Yunchun Zhang, Wei Zhou
Summary: Remote sensing image fusion aims to combine high-resolution single-band panchromatic (PAN) image with spectrally informative multispectral (MS) image to generate a panchromatic sharpened image with high resolution and color information, known as pansharpening. Existing methods based on single convolutional neural network (CNN) or transformer have limitations in acquiring long-range features or difficulty in training, resulting in loss of spatial details and colors. In this work, a dual-branch hybrid CNN-Transformer network (DBCT-Net) is proposed to utilize the strengths of CNN and transformer to enhance the fusion results. The network consists of a multi-branch dense connected block (MDCB-4) for obtaining spectral and textural information, an encoder-decoder transformer for injecting local and global information, and an image reconstruction module for effective fusion of texture and spectral features. Experimental results on various datasets demonstrate that DBCT-Net outperforms other methods in spatial preservation and spectral feature recovery.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Lei Qu, Meng Wang, Kaixuan Guo, Wan Wan, Yu Liu, Jun Tang, Jun Wu, Peng Duan
Summary: This paper proposes a full-resolution biomedical image segmentation network that preserves the detailed information of images while maintaining sufficient semantic information and a large receptive field. By utilizing basic semantic features, non-destructive features, feature fusion, and multi-scale information extraction, the network demonstrates effectiveness and advancement in biomedical image segmentation tasks.
PATTERN RECOGNITION LETTERS
(2022)
Article
Computer Science, Artificial Intelligence
Qizhi Xu, Yuan Li, Jinyan Nie, Qingjie Liu, Mengyao Guo
Summary: This study proposes an iterative network based on spectral and textural loss constrained GAN for pansharpening. By generating mean difference images and using a coarse-to-fine fusion framework, as well as embedding loss functions for fidelity preservation, better fusion performance is achieved.
INFORMATION FUSION
(2023)
Article
Instruments & Instrumentation
Jianming Zhang, Wenxin Lei, Shuyang Li, Zongping Li, Xudong Li
Summary: This paper proposes a novel algorithm for infrared and visible image fusion. The algorithm decomposes the input image into different layers using a guided filter, and then fuses them using entropy-based fusion module, maximum absolute value rule, and a mask-guided deep convolutional neural network. Experimental results demonstrate that the algorithm achieves good performance in both subjective and objective evaluation.
INFRARED PHYSICS & TECHNOLOGY
(2023)
Article
Computer Science, Artificial Intelligence
G. Prema, S. Arivazhagan
Summary: This paper proposes a multi-scale multi-layer rolling guidance filter-based infrared and visible image fusion method, which can enhance target information while retaining texture details. By decomposing the source images into micro-scale, macro-scale, and base layers and combining them with unique fusion rules, a fused image with more significant features can be obtained.
PATTERN ANALYSIS AND APPLICATIONS
(2022)
Article
Chemistry, Analytical
Xiao Zhou, Yuanhang Mao, Miao Gu, Zhen Cheng
Summary: Researchers developed a microfluidic system embedded with a weakly supervised cell counting network (WSCNet) to generate microfluidic droplets, evaluate their quality, and accurately recognize the locations of encapsulated cells.
Article
Engineering, Electrical & Electronic
Wei Li, Zhongmin Li, Shiji Li
Summary: The main task of image fusion is to extract advantageous information from source images. Multiscale transform (MST) is commonly used but struggles to integrate detail and structural information. By extracting spatial information, edge preserving technology obtains more edge information than MST. Based on this advantage, this paper proposes an infrared and visible image fusion method using the rolling guidance filter (RGF) and weight map, which outperforms classic MST fusion algorithms and recent fusion methods in merging detail and structural information.
JOURNAL OF ELECTRONIC IMAGING
(2022)
Article
Computer Science, Artificial Intelligence
Xingyu Hu, Junjun Jiang, Xianming Liu, Jiayi Ma
Summary: Multi-focus image fusion (MFF) is a challenging task due to the difficulty in distinguishing different blur levels and the lack of real supervised data. In this study, we propose a novel deep learning-based framework named ZMFF, which captures the deep prior of the fused image and the focus map using deep image prior and deep mask prior networks, respectively. Our method achieves promising performance, generalization, and flexibility on both synthetic and real-world datasets without the need for extensive training data.
INFORMATION FUSION
(2023)
Article
Computer Science, Information Systems
Hongmei Wang, Lin Li, Chenkai Li, Xuanyu Lu
Summary: In this paper, a novel autoencoder-based image fusion network is proposed, which combines CNN and Transformer to simultaneously capture the local and global features of the source images. Additionally, contrast and gradient enhancement feature extraction blocks are designed for infrared and visible images respectively to maintain the information specific to each source. Experimental results demonstrate that the proposed network outperforms state-of-the-art methods in preserving both the clear target and detailed information of infrared and visible images.
Article
Automation & Control Systems
Huisi Wu, Baiming Zhang, Junquan Pan, Jing Qin
Summary: This paper proposes a novel biomedical image segmentation network MOG-Net, which introduces a new object-aware module (OAM) and a pyramid context encoder module (PCEM) to address the lack of global dependencies and semantic information dilution in existing models, achieving satisfactory segmentation performance by establishing global dependencies at multiple levels and compensating high-level semantic information dilution.
IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING
(2023)
Article
Chemistry, Analytical
Nagaraj Yamanakkanavar, Jae Young Choi, Bumshik Lee
Summary: In this paper, we propose an encoder-decoder architecture with wide and deep convolutional layers combined with different aggregation modules for medical image segmentation. The method achieves a rich representation of features spanning from low to high levels and from small to large scales using stacked kernels, and introduces feature-aggregation modules to better fuse information across network layers. The proposed method improves segmentation accuracy by combining feature-aggregation modules with guided skip connections.
Article
Engineering, Electrical & Electronic
He Li, Rencan Nie, Jinde Cao, Biaojian Jin, Yao Han
Summary: This article proposes a multilevel progressive enhancement fusion network to improve the fusion of remote sensing images. By employing a three-stage network structure, this method can fully fuse the spatial and spectral information of different resolution images and enhance the features through specific modules. Experimental results demonstrate that this method outperforms other methods on the IKONOS and WorldView-2 datasets.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2023)
Review
Agriculture, Multidisciplinary
Daoliang Li, Zhaoyang Song, Chaoqun Quan, Xianbao Xu, Chang Liu
Summary: This article discusses the importance of crop and livestock monitoring in agricultural production, as well as the application of image fusion technology in improving monitoring methods. It reviews the specific applications of image fusion in areas such as crop recognition, disease detection, and livestock health assessment, while also highlighting the challenges and future research directions in the field.
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2021)
Article
Computer Science, Information Systems
Armin Mehri, Parichehr Behjati, Angel Domingo Sappa
Summary: Image Super Resolution is a potential approach to improve the image quality of low-resolution optical sensors. This paper presents a dual stream Transformer-based method that uses a low-cost channel (visible image) as a guide to enhance the image quality of an expensive channel (infrared image).
Article
Engineering, Biomedical
Jun Fu, Weisheng Li, Jiao Du, Yuping Huang
Summary: In this study, a multiscale residual pyramid attention network (MSRPAN) for medical image fusion is proposed, which achieves better fusion results through feature extraction, reconstruction, and a feature fusion strategy. Compared to existing algorithms, the proposed MSRPAN network demonstrates superior performance in terms of both visual quality and objective metrics.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2021)
Article
Computer Science, Interdisciplinary Applications
Jun Fu, Baiqing He, Jie Yang, Jianpeng Liu, Aijia Ouyang, Ya Wang
Summary: In this paper, a cascaded dense residual network is proposed and used for grayscale and pseudocolor medical image fusion. Through the cascaded dense residual network, the fusion results have better performance in terms of edge strength, richer details, and objective indicators than the reference algorithms.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2023)