检索结果-内蒙古大学图书馆

A case study on homogeneous and heterogeneous reservoir porous media reconstruction by using generative adversarial networks

引用

Energy Procedia 2019年 158卷 6164-6169页

作者： Siyan Liu Zhi Zhong Ali Takbiri-Borujeni Mohammad Kazemi Qinwen Fu Yuhao Yang The University of Kansas Department of Chemical & Petroleum Engineering Lawrence Kansas USA 66045 Bureau of Economic Geology The University of Texas at Austin Texas USA 78713 West Virginia University Department of Petroleum and Natural Gas Engineering Slippery Rock University Department of Petroleum and Natural Gas Engineering

The advancing of modern X-ray computer tomography technology provides a powerful tool for us to illustrate the details inside the reservoir rock in three-dimensional space. Pore-scale rock characterization, modeling, and related fluid flow simulation can be challenging due to the high complexity of various rock samples. Conventional pore scale structure modeling methods such as various stochastic methods were developed for reservoir rock 3D microscopic structure reconstruction in order to generate representative realizations for numerical simulations and property upscaling approaches. In this work, generative adversarial networks (GANs) is used for generating the synthetic micro representations of porous rock by acquiring non-linear statistical information from the real 3D rock images in an unsupervised learning scheme. The related 3D image pre-processing, network training and adjusting as well as data post-processing procedures are addressed. The network prediction results from a homogeneous Berea sandstone and a heterogeneous Estaillades carbonate demonstrated the capability of GANs for high-resolution porous rock image representations reconstruction, generated and real images are compared via various visualizations and inspections. The study also illustrated the importance of the training image preprocessing, which indicating the data augmentation techniques can be one of the promising improvements in terms of capturing the sparsely distributed features from heterogenous 3D images and reconstructing the synthetic realizations, meanwhile, the robustness of the model during training process is enhanced when limited real data is available.

关键词： porous media image reconstruction generative adversarial networks neural networks

来源：评论

学校读者我要写书评

暂无评论

A Hybrid DCT-CLAHE Approach for Brightness Enhancement of Uneven-illumination Underwater images 18

A Hybrid DCT-CLAHE Approach for Brightness Enhancement of Un...

引用

2nd International conference on Video and image processing (ICVIP)

作者： Ge, Meng Hong, Qingqing Zhang, Lifeng Kyushu Inst Technol Dept Elect & Elect Engn Fukuoka Fukuoka Japan

ISBN: (纸本)9781450366137

Underwater images have been drawing sufficient attentions, as more and more researchers and companies are committed to ocean engineering, underwater archaeology, mining etc in recent years. Underwater images often suffer from unbalanced illumination, which bring image analysis and processing challenges. This paper introduces a novel approach for underwater image enhancement based on the DCT coefficient and CLAHE algorithm. image changes with operations on the statistical model of the image DCT coefficients. The proposed methods firstly perform brightness equalization of the image, which optimize the underexposed and overexposed regions by regulating the low-frequency part of the image DCT coefficients. Afterwards CLAHE is applied to achieve image contrast enhancement. Finally experiments shows the better image enhancement performance compared to other algorithms.

关键词： Underwater image Brightness Equalization image Enhancement DCT Coefficient CLAHE

来源：评论

学校读者我要写书评

暂无评论

AUTOMATIC EXPOSURE COMPENSATION FOR MULTI-EXPOSURE image FUSION 25

AUTOMATIC EXPOSURE COMPENSATION FOR MULTI-EXPOSURE IMAGE FUS...

引用

25th IEEE International conference on image processing (ICIP)

作者： Kinoshita, Yuma Shiota, Sayaka Kiya, Hitoshi Tokyo Metropolitan Univ Tokyo Japan

ISBN: (纸本)9781479970612

This paper proposes a novel luminance adjustment method based on automatic exposure compensation for multi-exposure image fusion. Multi-exposure image fusion is a method to produce images without saturation regions, by using photos with different exposures. In conventional works, it has been pointed out that the quality of those multi-exposure images can be improved by adjusting the luminance of them. However, how to determine the degree of adjustment has never been discussed. This paper therefore proposes a way to automatically determines the degree on the basis of the luminance distribution of input multi-exposure images. Moreover, new weights, called "simple weights", for image fusion are also considered for the proposed luminance adjustment method. Experimental results show that the multi-exposure images adjusted by the proposed method have better quality than the input multi-exposure ones in terms of the well-exposedness. It is also confirmed that the proposed simple weights provide the highest score of statistical naturalness and discrete entropy in all fusion methods.

关键词： Multi-exposure fusion luminance adjustment image enhancement automatic exposure compensation

来源：评论

学校读者我要写书评

暂无评论

Ultra-wideband Passive radars Fundamental Theory and Applications 17

Ultra-wideband Passive radars Fundamental Theory and Applica...

引用

17th IEEE International conference on Mathematical methods in Electromagnetic Theory (MMET)

作者： Pavlikov, V. V. Volosyuk, V. K. Zhyla, S. S. Natl Aerosp Univ Kharkiv Aviat Inst Aerosp Radio Elect Syst Dept Kharkov Ukraine

ISBN: (纸本)9781538654385

Passive radars are such radars that record and process signals of the objects own radiation within the radio wave band. They are used to solve a wide range of remote sensing problems. The observations registered by such radars are a mixture of stochastic signals of the investigated and interfering objects, as well as the internal noise of the receiver. Signals and noise are completely random, and their statistical characteristics are the same. Another feature of the transmitting radio thermal signals is that their emission spectrum is ultra-wideband (UWB) (except for polyatomic gases, which are characterized by discrete absorption and emission lines). Therefore, it is expedient to provide wide-or UWB for the passive radars operating frequencies band. Transition to UWB signal processing requires the improvement of the passive UWB radars theory. This theory should be able to synthesize new algorithms for signal processing and reveal the physical essence of parameter estimates at the output of the radar. This will allow solving the inverse problems of estimating the parameters and characteristics of the objects. Results of many years of research are summarized in this paper, a logical connection is formed between the key elements of the microwave radiation theory, the mathematical apparatus for processing UWB signals and the fundamentals of the optimal signal processing algorithms synthesis. Examples of the signal processing algorithm synthesis in a single-and a multichannel passive radar are also given.

关键词： Passive radars optimal signal processing optimum algorithm stochastic signals radio thermal signals

来源：评论

学校读者我要写书评

暂无评论

Crop Classification Maps Filtration Based on Deep Learning methods 2

Crop Classification Maps Filtration Based on Deep Learning M...

引用

IEEE 2nd Ukraine conference on Electrical and Computer Engineering (UKRCON)

作者： Lavreniuk, Mykola Natl Tech Univ Ukraine Igor Sikorsky Kiev Polytech Inst Space Res Inst NASU SSAU Kiev Ukraine

ISBN: (纸本)9781728138824

In this paper we proposed filtration methods for land cover and land use classification maps, that obtained based on high resolution satellite images. The main idea is to adapt and utilize state-of-the-art deep learning fully convolutional and U-net architectures, that previously have been used for image segmentation, for classification map filtration task and to compare them with traditional rule-based approach. The most complicated tasks in the filtering such maps are to preserve edges, boundaries between different fields and automatically take into account not only single object or its neighbors, but also consider whole surrounded situation. The proposed U-net architecture allows us to overcome these issues and to provide more accurate and precise filtration in terms of accuracies per class. Also, McNemar statistical test has been conducted to prove the statistically significant gain of utilizing proposed filtration methodology compare to initial classification map. In addition, it shows advantages comparing to rule-based method in successfully dealing with big objects of noise in large fields and at the same time prevent significant changes in small farmer fields that grouped near villages or towns.

关键词： crop classification post processing filtration deep learning U-net fully convolutional network

来源：评论

学校读者我要写书评

暂无评论

Long-term Persistence and Cross-Wavelet Transform Analysis of Solar Filament Activity 10

Long-term Persistence and Cross-Wavelet Transform Analysis o...

引用

10th International conference on Digital image processing (ICDIP)

作者： An, Jianmei Cai, Yunfang Qi, Yi Zuo, Yongyan Wang, Xianping Chongqing Univ Arts & Sci Sch Software Engn Chongqing 402160 Peoples R China Chinese Acad Sci Yunnan Observ Kunming 650216 Yunnan Peoples R China

ISBN: (数字)9781510622005

ISBN: (纸本)9781510622005

Solar time series analysis is one of the most important topics in statistical astrophysics, which aims at revealing the complex dynamical behavior of long-term solar magnetic activity. In this work, several statistical analysis techniques are combined to study the long-term persistence and phase relationship of monthly filament activity between the low latitudes and the high latitudes during the time period from 1957 April to 2010 June. Based on these advanced analysis approaches, the following remarkable results are found: (1) solar filament activity at the low latitudes lags behind that at the high latitudes with a phase shift of 40 months, and the largest positive coefficient is found to be 0.35;(2) solar filament activity at both the low and the high latitudes exhibits a strong long-term persistence behavior, that is, their nonlinear dynamical behavior could not be regarded as stochastic phenomenon;(3) the relative phase relationships between the low latitudes and the high latitudes are not in phase for the studied periodic scales, but they are coherent in the periods of 10-14 years. To sum up, the analysis results could give more useful information on our understanding the solar and the stellar dynamo theory, and also provide some crucial roles of solar magnetic activity variations.

关键词： Time-frequency signal analysis statistical signal processing wavelet transform correlation analysis

来源：评论

学校读者我要写书评

暂无评论

image Compressed Sensing Based on Dictionary Learning via Bilinear Generalized Approximate Message Passing 10

Image Compressed Sensing Based on Dictionary Learning via Bi...

引用

10th International conference on Digital image processing (ICDIP)

作者： Si, Jingjing Wang, Jiaoyun Cheng, Yinbo Yanshan Univ Sch Informat Engn Qinhuangdao Peoples R China Hebei Agr Univ Ocean Coll Qinhuangdao Peoples R China Hebei Key Lab Informat Transmiss & Signal Proc Qinhuangdao Peoples R China

ISBN: (数字)9781510622005

ISBN: (纸本)9781510622005

Sparse representation matrix is of great significance for compressed sensing (CS). When dictionaries learned from training data are used instead of predefined dictionaries, signal reconstruction accuracy would be improved. In this paper, we learn dictionaries for compressed image reconstruction based on bilinear generalized approximate message passing (BiGAMP). stochastic mapping is performed on the training data which are composed of image blocks, to conform to the statistical model of BiGAMP methodology. Square dictionary and overcomplete dictionary are learned respectively for blocked image sparse representation, and are applied to image CS reconstruction. Simulation results show that our learned dictionaries lead to improved image CS reconstruction performance in comparison to predefined dictionaries and dictionaries learned with K-SVD method.

关键词： compressed sensing bilinear generalized approximate message passing (BiGAMP) dictionary learning

来源：评论

学校读者我要写书评

暂无评论

An Object-Based Method Based on a Novel statistical Distance for SAR image Change Detection 3

An Object-Based Method Based on a Novel Statistical Distance...

引用

IEEE 3rd International conference on Signal and image processing (ICSIP)

作者： Wan, Ling Zhang, Tao You, Hongjian Key Lab Technol Geospatial Informat Proc & Applic Beijing 100190 Peoples R China Chinese Acad Sci Inst Elect Beijing 100190 Peoples R China Univ Chinese Acad Sci Beijing 100039 Peoples R China

ISBN: (纸本)9781538663967

This paper introduces an object-based method based on a new statistical distance for SAR image change detection. Firstly, multi-temporal segmentation is carried out to segment two temporal SAR images simultaneously. It considers the homogeneity in two temporal images, and could generate homogeneous objects in spectral, spatial and temporal. In addition, through setting different segmentation parameters, the multi-temporal images can be segmented in a set of scales. This process exploits the advantages of OBIA that could effectively reduce spurious changes, and considers the scale of change detection task. Secondly, a multiplicative noise model called Nakagami-Rayleigh distribution is employed to describe SAR data, and then applied to Bayesian formulation. Thus, a new statistical distance that is insensitive to speckles is derived to measure the distances between pairs of parcels. Then, cluster ensemble algorithm is utilized to improve accuracy of individual result in each scale to obtain the final change detection map. Finally, multi-temporal Radarsat-2 images are employed to verify the effectiveness of the proposed method compared with other four methods.

关键词： synthetic aperture radar (SAR) change detection object-based image analysis multi-scale analysis

来源：评论

学校读者我要写书评

暂无评论

statistical Optimality of stochastic Gradient Descent on Hard Learning Problems through Multiple Passes 32

Statistical Optimality of Stochastic Gradient Descent on Har...

引用

32nd conference on Neural Information processing Systems (NIPS)

作者： Pillaud-Vivien, Loucas Rudi, Alessandro Bach, Francis PSL Res Univ Ecole Normale Super INRIA Paris France

We consider stochastic gradient descent (SGD) for least-squares regression with potentially several passes over the data. While several passes have been widely reported to perform practically better in terms of predictive performance on unseen data, the existing theoretical analysis of SGD suggests that a single pass is statistically optimal. While this is true for low-dimensional easy problems, we show that for hard problems, multiple passes lead to statistically optimal predictions while single pass does not;we also show that in these hard models, the optimal number of passes over the data increases with sample size. In order to define the notion of hardness and show that our predictive performances are optimal, we consider potentially infinite-dimensional models and notions typically associated to kernel methods, namely, the decay of eigenvalues of the covariance matrix of the features and the complexity of the optimal predictor as measured through the covariance matrix. We illustrate our results on synthetic experiments with non-linear kernel methods and on a classical benchmark with a linear model.

关键词： Covariance matrix

来源：评论

学校读者我要写书评

暂无评论

A Local Block Coordinate Descent Algorithm for the CSC Model

A Local Block Coordinate Descent Algorithm for the CSC Model

引用

IEEE/CVF conference on Computer Vision and Pattern Recognition

作者： Ev Zisselman Jeremias Sulam Michael Elad Technion Israel Institute of Technology Johns Hopkins University

ISBN: (纸本)9781728132945

The Convolutional Sparse Coding (CSC) model has recently gained considerable traction in the signal and image processing communities. By providing a global, yet tractable, model that operates on the whole image, the CSC was shown to overcome several limitations of the patch-based sparse model while achieving superior performance in various applications. Contemporary methods for pursuit and learning the CSC dictionary often rely on the Alternating Direction Method of Multipliers (ADMM) in the Fourier domain for the computational convenience of convolutions, while ignoring the local characterizations of the image. In this work we propose a new and simple approach that adopts a localized strategy, based on the Block Coordinate Descent algorithm. The proposed method, termed Local Block Coordinate Descent (LoBCoD), operates locally on image patches. Furthermore, we introduce a novel stochastic gradient descent version of LoBCoD for training the convolutional filters. This stochastic-LoBCoD leverages the benefits of online learning, while being applicable even to a single training image. We demonstrate the advantages of the proposed algorithms for image inpainting and multi-focus image fusion, achieving state-of-the-art results.

关键词： imagery (Psychotherapy) images descent Coordinates e-learning image fusion image algorithms Convolution

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：