检索结果-内蒙古大学图书馆

Conference on image reconstruction from incomplete data vii

作者： Zhang, Ni Millane, Rick P. Enevoldson, Einar Murray, James E. Univ Canterbury Dept Elect & Comp Engn Computat Imaging Grp Christchurch 1 New Zealand NASA Dryden Flight Res Ctr Edwardsville IL 93523 USA

ISBN: (纸本)9780819492173

The problem of estimating wind velocities from limited flight data recordings is considered, with application to sailplane flights in high-altitude atmospheric mountain waves. Sailplane flight recorders routinely measure only GPS position and the problem is highly underdetermined. The nature of this problem is studied and a maximum a posteriori estimator is developed using prior information on the wind velocity and the sailplane airspeed and heading. The method is tested by simulation and by application to sailplane flight data.

关键词： Maximum a posteriori wind velocity aircraft sailplane mountain wave atmospheric wave

来源：评论

学校读者我要写书评

暂无评论

NEURAL NETWORKS FOR LINEAR INVERSE PROBLEMS WITH incomplete data ESPECIALLY IN APPLICATIONS TO SIGNAL AND image-reconstruction

引用

NEUROCOMPUTING 1995年第1期8卷 7-41页

作者： CICHOCKI, A UNBEHAUEN, R LENDL, M WEINZIERL, K Lehrstuhl für Allgemeine und Theoretische Elektrotechnik University Erlangen-Nürnberg Cauerstrasse 7 D-91058. Erlangen Germany

In this paper a generalized minimum norm principle and/or a maximum entropy principle are used as general criteria, e.g. for reconstructing images or signals from noisy and incomplete projection data. The linear inverse problem is reformulated as an optimization problem and solved by a unified analog neural network. Moreover, in order to reduce the network complexity a new approach is proposed which makes it possible to construct simply and effectively a neural network containing only one single artificial neuron with an on chip adaptive learning algorithm. The correctness and performance of the proposed neural network architectures are illustrated by extensive computer simulation experiments.

关键词： OPTIMIZATION HOPFIELD RECURRENT NEURAL NETWORKS REAL-TIME NEUROCOMPUTING INVERSE PROBLEMS MAXIMUM ENTROPY MINIMUM L(P)-NORM CRITERIA

来源：评论

学校读者我要写书评

暂无评论

Deep image Prior-Based PET reconstruction from Partial data

引用

IEEE TRANSACTIONS ON RADIATION AND PLASMA MEDICAL SCIENCES 2024年第4期8卷 416-425页

作者： Shan, Qianxue Wang, Junwu Liu, Dong Univ Sci & Technol China Sch Phys Sci Hefei 230026 Peoples R China Univ Sci & Technol China Sch Math Sci Hefei 230026 Peoples R China Univ Sci & Technol China Div Life Sci & Med CAS Key Lab Microscale Magnet Resonance Hefei 230026 Peoples R China Univ Sci & Technol China Synerget Innovat Ctr Quantum Informat & Quantum Ph Hefei 230026 Peoples R China Univ Sci & Technol China Sch Biomed Engn Suzhou 215123 Peoples R China Univ Sci & Technol China Suzhou Inst Adv Res Suzhou 215123 Peoples R China

In this article, we propose an unsupervised deep learning method for positron emission tomography (PET) reconstruction from incomplete data. This method utilizes the so-called deep image prior (DIP) as an untrained deep convolutional neural network (CNN) to generate object reconstructions. The main idea is to reparameterize the image reconstruction problem as a neural network optimization problem. We show that the proposed method effectively addresses the incomplete data reconstruction problem, which otherwise degrades the image resolution and quality of standard reconstruction algorithms. Meanwhile, the proposed method does not require any pretraining procedures, i.e., it is not biased toward any particular dataset. Hence, it has the potential to be used in clinical situations, where training data would be infeasible or prohibitively expensive. The performance of the proposed approach is evaluated with noisy synthetic data based on the Shepp-Logan and brainweb phantoms, and clinical naive rat data. In addition, robustness studies of the approach with respect to regularization parameters are also carried out. We showcase that the proposed method considerably outperforms the state-of-the-art methods, leading to flexible reconstruction from incomplete PET data.

关键词： Contourlet transform deep image prior (DIP) incomplete data positron emission tomography (PET) unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Feature constrained compressed sensing CT image reconstruction from incomplete data via robust principal component analysis of the database

引用

PHYSICS IN MEDICINE AND BIOLOGY 2013年第12期58卷 4047-4070页

作者： Wu, Dufan Li, Liang Zhang, Li Tsinghua Univ Dept Engn Phys Beijing 100084 Peoples R China Tsinghua Univ Minist Educ Key Lab Particle & Radiat Imaging Beijing 100084 Peoples R China

In computed tomography (CT), incomplete data problems such as limited angle projections often cause artifacts in the reconstruction results. Additional prior knowledge of the image has shown the potential for better results, such as a prior image constrained compressed sensing algorithm. While a pre-full-scan of the same patient is not always available, massive well-reconstructed images of different patients can be easily obtained from clinical multi-slice helical CTs. In this paper, a feature constrained compressed sensing (FCCS) image reconstruction algorithm was proposed to improve the image quality by using the prior knowledge extracted from the clinical database. The database consists of instances which are similar to the target image but not necessarily the same. Robust principal component analysis is employed to retrieve features of the training images to sparsify the target image. The features form a low-dimensional linear space and a constraint on the distance between the image and the space is used. A bi-criterion convex program which combines the feature constraint and total variation constraint is proposed for the reconstruction procedure and a flexible method is adopted for a good solution. Numerical simulations on both the phantom and real clinical patient images were taken to validate our algorithm. Promising results are shown for limited angle problems.

关键词： Compressed sensing

来源：评论

学校读者我要写书评

暂无评论

Siamese Cooperative Learning for Unsupervised image reconstruction from incomplete Measurements

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2024年第7期46卷 4866-4879页

作者： Quan, Yuhui Qin, Xinran Pang, Tongyao Ji, Hui South China Univ Technol Sch Comp Sci & Engn Guangzhou 510000 Peoples R China Natl Univ Singapore Dept Math Singapore 119076 Singapore

image reconstruction from incomplete measurements is one basic task in imaging. While supervised deep learning has emerged as a powerful tool for image reconstruction in recent years, its applicability is limited by its prerequisite on a large number of latent images for model training. To extend the application of deep learning to the imaging tasks where acquisition of latent images is challenging, this article proposes an unsupervised deep learning method that trains a deep model for image reconstruction with the access limited to measurement data. We develop a Siamese network whose twin sub-networks perform reconstruction cooperatively on a pair of complementary spaces: the null space of the measurement matrix and the range space of its pseudo inverse. The Siamese network is trained by a self-supervised loss with three terms: a data consistency loss over available measurements in the range space, a data consistency loss between intermediate results in the null space, and a mutual consistency loss on the predictions of the twin sub-networks in the full space. The proposed method is applied to four imaging tasks from different applications, and extensive experiments have shown its advantages over existing unsupervised solutions.

关键词： image reconstruction Training Noise measurement Loss measurement Deep learning Imaging Task analysis image reconstruction siamese neural networks unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

ALMA chemical survey of disk-outflow sources in Taurus (ALMA-DOT) vii: The layered molecular outflow from HL Tau and its relationship with the ringed disk

arXiv

引用

arXiv 2025年

作者： Bacciotti, F. Nony, T. Podio, L. Dougados, C. Garufi, A. Cabrit, S. Codella, C. Zimniak, N. Ferreira, J. INAF - Osservatorio Astrofisico di Arcetri Largo E. Fermi 5 Firenze50125 Italy Univ. Grenoble Alpes CNRS IPAG Grenoble38000 France INAF - Istituto di Radioastronomia Via P. Gobetti 101 Bologna40129 Italy Max-Planck-Institut für Astronomie Königstuhl 17 Heidelberg69117 Germany PSL University Sorbonne Université Observatoire de Paris LERMA CNRS UMR 8112 Paris75014 France

Context. The ALMA image of the ringed disk around HL Tau stands out as the iconic signature of planet formation, but the origin of the observed substructures is still debated. The HL Tau system also drives a powerful bipolar wind, detected in atomic and molecular lines, that may have important feedback on the process. Aims. The outermost component of the wind traced by CO emission is analyzed in detail to determine its relationship with the disk and its substructures. Methods. A spectro-imaging investigation is conducted using ALMA observations of the 12CO (2-1) line at 1.3 mm, with 0.2 km s−1 and ∼ 0′′.28 spectral and angular resolution, in the framework of the ALMA-DOT project. Relevant wind parameters are derived, allowing a tomographic reconstruction of the morphology and kinematics of the red-shifted lobe of the outflow, to compare with theoretical models. Results. The data channel maps and position-velocity diagrams show a rich substructure of concatenated bubble- and arc-shaped features, whose size and distance from the source continuously increase with velocity. The superposition of such features generates the apparent conical shape. The spatio-kinematical properties suggest that the flow presents distinct nested shells with increasing velocity and faster acceleration going toward the axis, and rotating in the same sense of the disk. The wind parameters are compared with the predictions of magnetohydrodynamic (MHD) disk winds. Under this hypothesis, the launch radii of the three outermost shells are found to be at 55, 67 and 86 au from the star, coincident with regions of enhanced gas density in the disk. We derive a magnetic lever arm λ ∼ 4 − 5, higher than that commonly adopted in models of MHD winds from the outer disk. Interpretations are discussed. Conclusions. The properties of the CO outflow from HL Tau appear to be compatible with magnetized disk winds with launch radii in the region at 50-90 au from the source. As such, the wind may be capable of re

关键词： Magnetohydrodynamics

来源：评论

学校读者我要写书评

暂无评论

Performance of Sparse Recovery Algorithms for the reconstruction of Radar images from incomplete RCS data

引用

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS 2015年第4期12卷 860-864页

作者： Bae, Ji-Hoon Kang, Byung-Soo Kim, Kyung-Tae Yang, Eunjung Pohang Univ Sci & Technol Dept Elect Engn Pohang 790784 South Korea Agcy Def Dev Taejon 305152 South Korea

In this letter, we compare the performances of sparse recovery algorithms (SRAs) for the reconstruction of a 2-D inverse synthetic aperture radar (ISAR) image from incomplete radar-cross-section (RCS) data. The three methods considered for the SRA include the basis pursuit (BP), the BP denoising, and the orthogonal matching pursuit methods. The performances of the methods in terms of the reconstruction accuracy of the ISAR image are compared using the incomplete RCS data. In addition, traditional interpolation methods such as nearest-neighbor interpolation, linear interpolation, and spline interpolation are applied to the incomplete RCS data to reconstruct ISAR images, and their performances are compared to that of the SRAs.

关键词： Basis pursuit (BP) BP denoising (BPDN) interpolation inverse synthetic aperture radar (ISAR) image orthogonal matching pursuit (OMP) radar sparse recovery algorithm (SRA)

来源：评论

学校读者我要写书评

暂无评论

Study of optical micro-scanning reconstruction

Study of optical micro-scanning reconstruction

引用

Conference on image reconstruction from incomplete data vii

作者： Zhao, Xunjie Li, Chengjin Soochow Univ Sch Phys Sci & Technol Suzhou 215006 Peoples R China Sci & Technol ElectOpt Secur Lab Sanhe 065201 Peoples R China

ISBN: (纸本)9780819492173

Infrared images provide valuable information for many applications. However, compared to a visible image, the image quality is poor and its spatial resolution is limited due to the focal plane arrays cannot be made dense enough to yield a sufficiently high spatial sampling frequency, which consequently leads to image blurring. Optical micro-scanning technique has been proven to be an effective method to increase the resolution of images. This technique is able to produce high resolution (HR) images from a set of optically shifted images of low-resolution (LR). Over the last decade, optical micro-scanning technique has become one of the active topics of research, among this, the super-resolution (SR) reconstruction algorithms are the focus. This paper starts with the basic principle of SR reconstruction. Then several methods of high-precision movement registration algorithm and SR reconstruction algorithms were introduced. This study particularly focuses on the more recent development in motion estimation methods. Furthermore, an algorithm based on sub-pixel image registration that estimates the displacements of the LR image is presented. The critical steps in image registration are collecting feature points and estimating a spatial transformation especially when outliers are present. In this paper, the Harris corner detector is used to find the feature points and then the point feature is described by the neighborhood difference in order to reduce the sensitivity to illumination variations. Moreover, the Random Sample Consensus(RANSAC) algorithm is employed to build a transformation model. Simulation results demonstrate that the method can estimate the displacements accurately.

关键词： super-resolution reconstruction optical micro-scanning sub-pixel registration Harris corner detector RANSAC image interpolation feature matching

来源：评论

学校读者我要写书评

暂无评论

A Convex Variational Model for Learning Convolutional image Atoms from incomplete data

引用

JOURNAL OF MATHEMATICAL IMAGING AND VISION 2020年第3期62卷 417-444页

作者： Chambolle, A. Holler, M. Pock, T. Ecole Polytech Ctr Math Appl Paris France Karl Franzens Univ Graz Inst Math & Sci Comp Graz Austria Graz Univ Technol Inst Comp Graph & Vis Graz Austria

A variational model for learning convolutional image atoms from corrupted and/or incomplete data is introduced and analyzed both in function space and numerically. Building on lifting and relaxation strategies, the proposed approach is convex and allows for simultaneous image reconstruction and atom learning in a general, inverse problems context. Further, motivated by an improved numerical performance, also a semi-convex variant is included in the analysis and the experiments of the paper. For both settings, fundamental analytical properties allowing in particular to ensure well-posedness and stability results for inverse problems are proven in a continuous setting. Exploiting convexity, globally optimal solutions are further computed numerically for applications with incomplete, noisy and blurry data and numerical results are shown.

关键词： Variational methods Learning approaches Inverse problems Functional lifting Convex relaxation Convolutional Lasso Machine learning Texture reconstruction

来源：评论

学校读者我要写书评

暂无评论

Maximum subarray algorithms for use in optical and radio astronomy

Maximum subarray algorithms for use in optical and radio ast...

引用

Conference on image reconstruction from incomplete data vii

作者： Weddell, S. J. Takaoka, T. Read, T. Candy, R. Univ Canterbury Dept Elect & Comp Engn Christchurch 1 New Zealand Univ Canterbury Dept Comp Sci & Software Engn Christchurch 1 New Zealand

ISBN: (纸本)9780819492173

The maximum sub-array algorithm has been implemented within a field programmable gate array as an efficient centroiding method for wavefront slope estimation. However, a convenient platform for this work is a graphics processor unit (GPU). Translation of the maximum subarray algorithm to a GPU has been performed and shows significant performance gains compared to a single-core CPU. Recently, this algorithm has been applied to radio telescope images acquired for the Australian square kilometer array pathfinder project. This paper provides an overview of the maximum subarray algorithm and shows how this can be utilized for optical and radio telescope applications

关键词： graphics processing unit maximum subarray problem astronomical image 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：