检索结果-内蒙古大学图书馆

European conference on Antennas and Propagation, EuCAP

作者： Vincent Lee Yahya Rahmat-Samii University of California Los Angeles Electrical and Computer Engineering UCLA Los Angeles USA

ISBN: (数字)9788831299107

ISBN: (纸本)9798350366327

Unmanned aerial vehicles (UAVs) have gained attention in antenna near-field measurements for outdoor large antennas due to their ability to reduce the amount of required test equipment. The most promising UAV-based setup for these outdoor measurements is an amplitude-only approach as amplitude-only measurements are robust against positioning errors which is an inherent problem facing UAVs. Current implementations of UAV amplitude-only near-field scans utilize matrix solvers and equivalent currents to account for the non-uniform data collection when performing phase reconstruction. In this paper, the conjugate gradient non-uniform fast Fourier transform (CG-NUFFT) algorithm is utilized for phase reconstruction from non-uniform two planar amplitude-only measurements. The system is tested through simulations of a dipole-element phased array antenna with various tapering and steering angles, aiming to reconstruct the far-field patterns. UAV non-uniform positioning is also simulated by introducing deviations to the targeted uniform waypoints. Simulation results demonstrate that the CG-NUFFT algorithm accurately reconstructs far-field patterns.

关键词： Antenna measurements Phased arrays Phase measurement Transmission line matrix methods Fast Fourier transforms Current measurement Measurement uncertainty Position measurement Autonomous aerial vehicles image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Tomographic image reconstruction from incomplete View data by Convex Projections and Direct Fourier Inversion

引用

IEEE Transactions on Medical Imaging 1984年第2期3卷 91-98页

作者： Sezan, M. Ibrahim Stark, Henry Eastman Kodak Research Labs Rochester NY 14650 United States Rensselaer Polytechnic Institute Department of Electrical Computer and Systems Engineering Troy NY 12181 United States

We consider the problem of reconstructing CAT imagery by the direct Fourier method (DFM) when not all view data are available. To restore the missing information we use the method of projections onto convex sets (POCS). POCS is a recursive image restoration technique that finds a solution consistent with the measured data and a priori known constraints in both the space and Fourier domain. Because DFM reconstruction is a frequency-domain technique it is ideally matched to POCS restoration when, for one reason or another, we are forced to generate an image from a less than complete set of view data. We design and apply an algorithm (PRDF) which interpolates/extrap-olates the missing Fourier domain information by POCS and reconstructs an image by DFM. A simulated human thorax cross section is restored and reconstructed. The restorations using POCS are compared with the Gerchberg-Papoulis extrapolation method and shown to be superior. Applications of PRDF to other types of medical imaging modalities are discussed. © 1984 IEEE

关键词： Tomography image reconstruction image restoration Design for manufacture image generation Algorithm design and analysis Medical simulation Humans Thorax Extrapolation

来源：评论

学校读者我要写书评

暂无评论

Near-Field Focusing Operators for Planar Multi-Static Microwave Imaging Using Back-Projection in the Spatial Domain

Near-Field Focusing Operators for Planar Multi-Static Microw...

引用

European conference on Antennas and Propagation, EuCAP

作者： Matthias M. Saurer Marius Brinkmann Han Na Quanfeng Wang Thomas F. Eibert Department of Electrical Engineering School of Computation Information and Technology Technical University of Munich Munich Germany Rohde & Schwarz GmbH & Co. KG Munich Germany

ISBN: (数字)9788831299107

ISBN: (纸本)9798350366327

Based on a plane-wave expansion of the observation data in quasi-planar multi-static scattering scenarios, an improved formalism for image creation utilizing back-projection in the spatial domain is derived. The underlying integral expressions for different focusing operators are derived analytically leading to magnitude correction factors, which are mostly relevant for reconstructing microwave images when the distance from the scattering object to the aperture plane is small. It is shown that the derived imaging procedure is superior to the traditional back-projection only compensating the phase delay of the measurement signals and validate our findings based on simulated as well as measured data. Since the derived focusing operators correspond to a low-pass filtering of the spatial images, the resulting modified multi-static back-projection algorithms effectively suppress imaging artifacts as well.

关键词： Microwave measurement Phase measurement Filtering Focusing Scattering Spatial databases Microwave filters image reconstruction Microwave imaging Microwave propagation

来源：评论

学校读者我要写书评

暂无评论

image reconstruction from incomplete data V

Image Reconstruction from Incomplete Data V

引用

image reconstruction from incomplete data V

ISBN: (纸本)9780819472960

The proceedings contain 21 papers. The topics discussed include: spectral image estimation for coded aperture snapshot spectral imagers;exploiting image sparsity in parallel magnetic resonance imaging (pMRI);spatio-temporal sampling for video;multi-spectral intensity diffraction tomography;inversion of strongly scattered data: shape and permittivity recovery;evaluation of surrogate data quality in sinogram-based CT metal-artifact reduction;an EM-like optimization scheme for diffuse optical tomography;advances in ptychographical coherent diffractive imaging;image reconstruction by phase retrieval with transverse translation diversity;turbulence profiling for long range surveillance imaging;superresolution in dewraped in anisoplanatic images;and self-tuning Kalman filter estimation at atmospheric wrap.

关键词：

来源：评论

学校读者我要写书评

暂无评论

多阶段重建内容协同优化的图像修复算法

引用

信号处理 2025年第2期41卷 325-337页

作者：秦佳白慧慧王梦丽翟双姣晋赞霞秦品乐曾建潮中北大学计算机科学与技术学院山西太原030051 北京交通大学信息科学研究所北京100044 现代信息科学与网络技术北京市重点实验室北京100044

随着数字图像技术的快速发展,图像已经成为日常生活学习中信息传递的重要载体之一。然而,由于错误传输、不当存储或者关键信息被遮挡等情况造成的图像信息丢失,往往影响人们对图像信息的理解和分析。近几年,大量渐进式图像修复算法被提... 详细信息

随着数字图像技术的快速发展,图像已经成为日常生活学习中信息传递的重要载体之一。然而,由于错误传输、不当存储或者关键信息被遮挡等情况造成的图像信息丢失,往往影响人们对图像信息的理解和分析。近几年,大量渐进式图像修复算法被提出,通过由粗到精的修复方式逐步生成受损图像的缺失信息,使修复后的图像在视觉和内容上接近原始图像。然而,在这种渐进式图像修复的结构中,低渐进层的错误往往容易传递到高渐进层中,造成修复结果在图像内容上有误,难以达到人眼视觉要求。针对这一问题,本文提出了一种多阶段重建内容协同优化的图像修复算法(image inpainting algorithm based on multi-stage reconstruction collaborative optimization,MSNet),在渐进修复中融入并行结构,通过对三阶段渐进层内容的协同优化,提高修复结果的准确性。具体来说,在该网络的初步修复阶段后,提出了一种并行的图像内容精细化修复模块(Parallel image content refinement module,PCRM),通过基于自注意力的U-Net和增强的残差网络两个分支并行地修复图像结构和细节信息。其中,基于自注意力的U-Net倾向于对图像的结构特征进行抽象提取,并通过Multi-Head自注意力机制进行全局恢复。而增强残差网络结构则通过优化特征值区分度的方式,提升重要细节信息的表征能力,使残差网络能够更关注于重要细节的恢复。在PCRM后,为了融合第二阶段所得的多个修复重建信息,细节-结构融合模块被提出来,将细节信息合理嵌入到结构中,提高多渐进层特征在空间表征上的兼容性,减少纹理与结构不统一所造成的图像视觉不连续问题,以生成更加符合客观现实的修复结果。实验结果表明,与现有的修复算法对比,本文提出的算法可以生成纹理更加清晰,视觉上更加逼真的结果。

关键词：图像修复特征融合渐进式图像修复图像复原

来源：评论

学校读者我要写书评

暂无评论

BiLSTM-Based VAE-GAN for Predicting Future Road States in Autonomous Driving

BiLSTM-Based VAE-GAN for Predicting Future Road States in Au...

引用

International conference on Artificial Intelligence in Information and Communication (ICAIIC)

作者： Donghyun Kim Jaerock Kwon Haewoon Nam Division of Electrical Engineering Hanyang University Ansan South Korea Electrical and Computer Engineering University of Michigan-Dearborn Dearborn United States of America

ISBN: (数字)9798331507022

ISBN: (纸本)9798331507039

The ability to accurately predict future road conditions is essential for the advancement of autonomous driving systems. This study introduces a BiLSTM-based VAE-GAN framework that leverages both temporal and spatial information to generate high-quality future road images. The proposed architecture combines the reconstruction capabilities of Variational Auto-Encoders (VAEs) with the adversarial training of Generative Adversarial Networks (GANs), while incorporating Bidirectional Long Short-Term Memory (BiLSTM) to effectively capture temporal dependencies in sequential driving data. To train the model, diverse datasets were collected from the CARLA simulation environment, encompassing various road conditions and vehicle states. The training process minimizes reconstruction loss, KL divergence, and adversarial loss, enabling the generation of visually consistent and semantically accurate future road images. Quantitative evaluations using PSNR and MSE metrics demonstrate the model's ability to outperform conventional VAE-based approaches, achieving high structural similarity and low reconstruction errors. The results highlight the potential of the proposed framework to enhance decision-making and lane-keeping performance in autonomous vehicles. By predicting future road states with high fidelity, the BiLSTM-based VAE-GAN framework lays the groundwork for integrating generative models into real-world autonomous driving applications, contributing to safer and more reliable driving systems.

关键词： Training Measurement Roads Reinforcement learning Predictive models Generative adversarial networks Safety Reliability Autonomous vehicles image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Comparative Assessment of Modern Approaches for 3D reconstruction

Comparative Assessment of Modern Approaches for 3D Reconstru...

引用

International conference on Radioelektronika

作者： Oleh Kryvoshei Patrik Kamencay Roberta Hlavata Adam Stech Miroslav Benco Department of Multimedia and Information-Communication Technologies University of Zilina Zilina Slovakia

ISBN: (数字)9798331544478

ISBN: (纸本)9798331544485

This paper explores and evaluates the strengths and weaknesses of neural and Gaussian-based approaches in 3D reconstruction. While neural radiance fields (NRFs) methods are increasingly favored for their adaptability and excellent outcomes, Gaussian techniques stand out for their analytical efficiency and robustness. This study systematically evaluates these both paradigms by comparing their performance in terms of accuracy, computational complexity, scalability, and real-world feasibility. In this paper, we analyze their effectiveness in reconstructing diverse 3D environments, considering factors such as noise resilience, data requirements, and rendering quality. Through experimental comparisons and benchmarking against standard datasets, our aim is to identify the strengths and limitations of each method and determine their suitability for specific applications in computer vision and graphics. By offering insights into the trade-offs between neural and Gaussian-based approaches, this paper contributes to the ongoing development of efficient and high-fidelity 3D reconstruction techniques. The findings will aid researchers and practitioners in selecting appropriate methods for different use cases, ultimately advancing the state of the art in 3D vision and computational graphics. Furthermore, the paper highlights the potential integration of NeRF in medical imaging, where it offers significant promise for generating 3D reconstructions from standard 2D medical scans. These reconstructions could revolutionize diagnostic accuracy, enhance surgical planning, and improve medical education.

关键词： Three-dimensional displays Accuracy Neural networks Surgery Neural radiance field Rendering (computer graphics) Real-time systems Planning image reconstruction Standards

来源：评论

学校读者我要写书评

暂无评论

EvaSR: Rethinking Efficient Visual Attention Design for image Super-Resolution

EvaSR: Rethinking Efficient Visual Attention Design for Imag...

引用

International conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Zhijian Wu Chenhan Zhang Dingjiang Huang School of Data Science and Engineering East China Normal University China Trenton Collegiate Institute Canada

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Due to the advantages of long-range modeling via the self-attention mechanism, Transformer has taken various vision tasks by storm, including image super-resolution (SR). In this study, we reveal that the convolutional neural network (CNN) with proper visual attention is a more simple and effective paradigm than Transformer in image SR tasks. We reexamine the successful SR models and discover several key characteristics that contribute to accurate image reconstruction. Built on this recipe, we propose a pure CNN-based SR network using efficient visual attention, dubbed EvaSR. Benefiting from the carefully designed visual attention, our EvaSR can favorably capture both local structure and long-range dependencies, and achieve adaptivity in spatial and channel dimensions while retaining the simplicity and efficiency of CNNs. The experimental results demonstrate that our EvaSR achieves state-of-the-art performance among the existing efficient SR methods. Especially, the tiny version of EvaSR needs 21.4% and 15.2% parameters of IMDN and SMSR with better performance.

关键词： Performance evaluation Visualization Storms Computational modeling Superresolution Transformers Convolutional neural networks Speech processing Spatial resolution Signal resolution

来源：评论

学校读者我要写书评

暂无评论

image reconstruction from incomplete data and its applications in experimental mechanics

Image reconstruction from incomplete data and its applicatio...

引用

作者： Huang, Y.H. Hung, Y.Y. He, X.Y. Liu, L. Department of Manufacturing Engineering and Engineering Management City University of Hong Kong Hong Kong Hong Kong Southeast University China

In the field of experimental mechanics, there exist some circumstances when only data at the boundary can be obtained while the internal data are unavailable, or when some data are missed due to shadow, illumination saturation and other reasons. Thus it would be helpful if a reasonable estimation of the unavailable or missed data can be obtained. In this study, an algorithm is developed to reconstruct the missed data from the existing ones by generating a series of equations about the missed data and solving for an optimal solution using least-squares approach. Results based on both simulation data and real incomplete experimental data obtained by shearography and fringe projection show the usefulness and potential of the algorithm for experimental mechanics applications.

关键词： image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Stacking U-Nets in U-shape: Redesigning the Information Flow in Model-based Networks for MRI reconstruction

Stacking U-Nets in U-shape: Redesigning the Information Flow...

引用

International conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Xiaoyu Qiao Weisheng Li Bin Xiao Yuping Huang Lijian Yang Chongqing Key Laboratory of Image Cognition Chongqing University of Posts and Telecommunications Chongqing China Key Laboratory of Cyberspace Big Data Intelligent Security Chongqing University of Posts and Telecommunications Ministry of Education Chongqing China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Model-based networks have shown convincing performance in MRI reconstruction. However, the unrolled cascades within the networks are constrained to solely obtain information from the preceding counterpart, resulting in potential error accumulation. Moreover, the linear structure fails to address the challenge of recovering fine-grained details. To tackle these problems, we propose to redesign the information flow in model-based networks. Our method features a large U-shaped network, where the nodes are built with unrolled cascades and U-Net-based regularizers. We design an input-level integration module to help the cascades acquire information from adjacent and skip-connected counterparts, building robust mappings to the target. We further design a coarse-to-fine feature-level integration module, aiming at guiding the network to progressively recover fine details. Intermediate reconstructions produced by subnetworks of different scales are integrated, enabling the extraction of complementary information to enhance the final performance. Compared with cutting-edge methods on different datasets, our method exhibits superior performances.

关键词： Magnetic resonance imaging Stacking Buildings Signal processing Feature extraction Acoustics Sensors data mining Speech processing

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：