Generalized Laplacian Pyramid Pan-Sharpening Gain Injection Prediction Based on CNN

Benzenati Tayeb; Kessentini Yousri; Kallel Abdelaziz; Hallabia Hind

首页> 外文期刊>IEEE Geoscience and Remote Sensing Letters >Generalized Laplacian Pyramid Pan-Sharpening Gain Injection Prediction Based on CNN

【24h】

Generalized Laplacian Pyramid Pan-Sharpening Gain Injection Prediction Based on CNN

机译：基于CNN的广义拉普拉斯金字塔泛尖锐化注入预测

获取原文

获取原文并翻译 | 示例

掌桥外文数据库（机构版） >>

开具论文收录证明 >>

文献代查 >>

页面导航

摘要
著录项
相似文献
相关主题

摘要

Pan-sharpening aims to fuse a low-spatial-resolution multispectral (MS) image with an associated higher resolution panchromatic image (PAN) in order to produce a high-resolution MS (HRMS) image to overcome physical limitation of satellite sensors. In this letter, we propose a new generalized Laplacian pyramid gain injection prediction based on convolutional neural networks (GIP-CNN) for pan-sharpening, which estimates the values of the injection gains for each MS band to complement it with spatial details extracted from the PAN image. The experimental results on images from different satellites show that GIP-CNN can achieve higher performances with respect to the state-of-the-art and new CNN-based methods in both spatial and spectral qualities.

机译：PAN锐化旨在使具有相关的更高分辨率的Panchromic图像（PAN）熔断低空间分辨率的多光谱（MS）图像，以便产生高分辨率MS（HRMS）图像以克服卫星传感器的物理限制。在这封信中，我们提出了一种基于卷积神经网络（GIP-CNN）的新的广义拉普拉斯金字塔注入预测，用于削减泛锐，估计每个MS频带的注射增益的值与从中提取的空间细节互补平底锅图像。来自不同卫星图像的实验结果表明，GIP-CNN可以在空间和光谱素质中相对于最先进的基于CNN的方法实现更高的性能。

著录项

来源
《IEEE Geoscience and Remote Sensing Letters》 |2020年第4期|651-655|共5页
作者
Benzenati Tayeb; Kessentini Yousri; Kallel Abdelaziz; Hallabia Hind;
展开▼
作者单位

Digital Res Ctr Sfax Sfax 3021 Tunisia|Univ Sfax Adv Technol Image & Signal Proc Sfax Tunisia;

Digital Res Ctr Sfax Sfax 3021 Tunisia|Univ Sfax MIRACL Lab Sfax Tunisia;

Digital Res Ctr Sfax Sfax 3021 Tunisia|Univ Sfax Adv Technol Image & Signal Proc Sfax Tunisia;

Digital Res Ctr Sfax Sfax 3021 Tunisia|Univ Sfax Adv Technol Image & Signal Proc Sfax Tunisia;

展开▼
收录信息
原文格式 PDF
正文语种 eng
中图分类
关键词
Spatial resolution; Training; Satellites; Image sensors; Sensors; Convolutional neural networks; Convolutional neural network (CNN); details injection; multi-resolution analysis (MRA); pan-sharpening;

机译：空间分辨率;训练;卫星;图像传感器;传感器;卷积神经网络;卷积神经网络（CNN）;细节注射;多分辨率分析（MRA）;泛锐;

相似文献

外文文献
中文文献
专利

1. Pansharpening: Context-Based Generalized Laplacian Pyramids by Robust Regression [J] . Vivone Gemine, Marano Stefano, Chanussot Jocelyn IEEE Transactions on Geoscience and Remote Sensing . 2020,第9期

机译：Pansharpening：基于背景的广义Laplacian金字塔，由强大的回归
2. Resolution Enhancement by Prediction of the High-Frequency Image Based on the Laplacian Pyramid [J] . Bo-Won Jeon, Rae-Hong Park, Seungjoon Yang EURASIP journal on applied signal processing . 2006,第10期

机译：通过拉普拉斯金字塔预测高频图像提高分辨率
3. Resolution Enhancement by Prediction of the High-Frequency Image Based on the Laplacian Pyramid [J] . Bo-Won Jeon, Rae-Hong Park, Seungjoon Yang EURASIP journal on advances in signal processing . 2006,第1期

机译：通过拉普拉斯金字塔预测高频图像提高分辨率
4. Multiresolution adaptive filtering of signal-dependent noise based on a generalized Laplacian pyramid [C] . Aiazzi, B., Baronti, Image Processing, 1997. Proceedings., International Conference on . 1997

机译：基于广义拉普拉斯金字塔的信号相关噪声的多分辨率自适应滤波
5. Holder regularity of solutions of generalized p-Laplacian type parabolic equations [D] . Hwang, Sukjung. 2012

机译：广义p-Laplacian型抛物型方程解的Holder正则性
6. pcPromoter-CNN: A CNN-Based Prediction and Classification of Promoters [O] . Muhammad Shujaat, Abdul Wahab, Hilal Tayara, 2020

机译：PCPROMoter-CNN：基于CNN的预测和启动子分类
7. We develop a model of scientific creativity and test it in the field of rare diseases. Our model is based on the results of an in-depth case study of the Rett syndrome. Archival analysis, bibliometric techniques and expert surveys are combined with network analysis to identify the most creative scientists. First, alternative measures of generative and combinatorial creativity are compared. Then, we generalize our results and present a stochastic model of socio-semantic network evolution. The model predictions are tested with multiple networks of rare disease specialties. We find that new scientific collaborations among experts in a field enhance combinatorial creativity. Instead, high entry rates of novices are negatively related to generative creativity. By extending the set of useful concepts, creative scientists gain in centrality. At the same time, by increasing their centrality in the scientific community, scientists can replicate and generalize their results, thus contributing to a scientific paradigm. [O] . Massimo Riccaboni, Maria Laura Frigotto 100

机译：我们开发了一种科学创造力模型，并在稀有疾病领域进行测试。我们的模型基于对Rett综合征的深入案例研究的结果。档案分析，文献计量技术和专家调查与网络分析相结合，以确定最具创造力的科学家。首先，比较生成和组合创造力的替代措施。然后，我们推广了我们的结果，并提出了社会语义网络演化的随机模型。模型预测用多个罕见疾病专业网络进行测试。我们发现，一个领域的专家之间的新的科学合作增强了组合创造力。相反，新手的高入门率与生成创造力负相关。通过扩展这组有用的概念，创造性的科学家获得了中心地位。同时，通过增加科学界的中心地位，科学家们可以复制和推广他们的结果，从而促进科学范式的发展。
8. Analysis of Interstellar Cloud Properties with Laplacian Pyramid Transforms: I. IRAS Maps [R] . Langer, William D. 1995

机译：用拉普拉斯金字塔变换分析星际云性质：I。IRas图

Generalized Laplacian Pyramid Pan-Sharpening Gain Injection Prediction Based on CNN

摘要

著录项

相似文献

相关主题

期刊订阅