检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

65 篇 会议
2 篇 期刊文献

馆藏范围

67 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

21 篇 工学
- 15 篇 计算机科学与技术...
- 15 篇 软件工程
- 6 篇 电子科学与技术（可...
- 4 篇 光学工程
- 4 篇 信息与通信工程
- 2 篇 安全科学与工程
- 1 篇 力学（可授工学、理...
- 1 篇 机械工程
- 1 篇 仪器科学与技术
- 1 篇 电气工程
- 1 篇 建筑学
- 1 篇 水利工程
- 1 篇 化学工程与技术
- 1 篇 生物医学工程（可授...
13 篇 理学
- 7 篇 物理学
- 5 篇 数学
- 2 篇 统计学（可授理学、...
- 1 篇 化学
- 1 篇 地球物理学
3 篇 管理学
- 3 篇 图书情报与档案管...
1 篇 医学
- 1 篇 临床医学

主题

27 篇 cellular neural ...
18 篇 image processing
14 篇 computer archite...
11 篇 partial differen...
10 篇 field programmab...
9 篇 computational mo...
8 篇 laboratories
8 篇 very large scale...
7 篇 application soft...
7 篇 analog computers
7 篇 equations
6 篇 automation
6 篇 image segmentati...
6 篇 cameras
6 篇 mathematical mod...
6 篇 computer network...
5 篇 image coding
5 篇 biomedical imagi...
5 篇 motion detection
4 篇 motion estimatio...

机构

13 篇 department of im...
11 篇 department of im...
6 篇 analogical and n...
5 篇 department of im...
5 篇 cellular sensory...
4 篇 department of im...
3 篇 computer and aut...
3 篇 department image...
3 篇 analogic and neu...
3 篇 department of im...
2 篇 university of ve...
2 篇 electronics depa...
2 篇 analogic and neu...
2 篇 department of im...
2 篇 analogical & neu...
2 篇 department of ma...
2 篇 department infor...
2 篇 analogic and neu...
2 篇 faculty of infor...
2 篇 analogical compu...

作者

18 篇 p. szolgay
13 篇 t. sziranyi
10 篇 zoltan nagy
10 篇 peter szolgay
7 篇 szirányi tamás
7 篇 z. nagy
6 篇 l. czuni
5 篇 p. kozma
4 篇 czúni lászló
4 篇 i. kopilovic
4 篇 zsolt voroshazi
4 篇 andras kiss
4 篇 szolgay péter
4 篇 sandor kocsardi
3 篇 p. sonkoly
3 篇 a. licsar
3 篇 laszlo czuni
3 篇 licsár attila
3 篇 arpad csik
2 篇 akos utasi

语言

66 篇 英文
1 篇 中文

检索条件"机构=Department of Image Processing and Neurocomputing"

共 67 条记录，以下是21-30 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

Behavior and event detection for annotation and surveillance

Behavior and event detection for annotation and surveillance

引用

International Workshop on Content-Based Multimedia Indexing, CBMI

作者： Zoltan Szlavik Levente Kovacs Laszlo Havasi Csaba Benedek Istvan Petras Akos Utasi Attila Licsar Laszlo Czuni Tamas Sziranyi MTA-SZTAKI Hungary Department of Image Processing and Neurocomputing University of Pannonia Veszprem Hungary

Visual surveillance and activity analysis is an active research field of computer vision. As a result, there are several different algorithms produced for this purpose. To obtain more robust systems it is desirable to integrate the different algorithms. To achieve this goal, the paper presents results in automatic event detection in surveillance videos, and a distributed application framework for supporting these methods. Results in motion analysis for static and moving cameras, automatic fight detection, shadow segmentation, discovery of unusual motion patterns, indexing and retrieval will be presented. These applications perform real time, and are suitable for real life applications.

关键词： Event detection Surveillance Motion analysis Computer vision Robustness Videos Application software Cameras Motion detection Indexing

来源：评论

学校读者我要写书评

暂无评论

HMM-based unusual motion detection without tracking

HMM-based unusual motion detection without tracking

引用

International Conference on Pattern Recognition

作者： Akos Utasi Laszlo Czuni MTA-SZTAKI Budapest Hungary Department of Image Processing and Neurocomputing University of Pannonia Veszprem Hungary

ISBN: (纸本)9781424421749

We propose novel pixel dense modeling of motion of urban traffic in noisy environments with the help of multidimensional Gaussian Mixture Models (GMMs) and Hidden Markov Models (HMMs). In our approach there is no need for object tracking in order to detect anomalous motion or to model and visualize the fluctuation of traffic. We propose a new scaling method introduced into the HMM to get a robust tool for the analysis of hundreds of motion vector samples at a time. We show the use of our model with a photorealistic video synthetized from real life recordings.

关键词： Motion detection Tracking Hidden Markov models Traffic control Gaussian noise Working environment noise Multidimensional systems Object detection Visualization Fluctuations

来源：评论

学校读者我要写书评

暂无评论

Elastic wave propagation modeling on emulated digital CNN-UM architecture

Elastic wave propagation modeling on emulated digital CNN-UM...

引用

IEEE International Workshop on Cellular Nanoscale Networks and their Applications, (CNNA)

作者： P. Kozma P. Sonkoly P. Szolgay Department of Image Processing and Neurocomputing University of Veszprém Veszprem Hungary Department of Image Processing and Neurocomputing University of Veszprém Hungary Analogic and Neural Computing Laboratory Computer and Automation Research Institute Hungarian Academy of Sciences Budapest Hungary

The synthetic seismogram has seen many years of widespread and successful application in geophysical prospecting. It is used to simulate the normal incidence reflectivity of a heterogeneous medium and has been employed more recently to obtain the responses of subsurface structural and stratigraphic configurations. The propagation of seismic waves has to be modeled to create synthetic seismograms. The solution of the partial differential equations of motion describing the propagation of stress waves in an elastic medium requires enormous computation power. In this paper a solution of seismic wave propagation will be presented on CNN-UM architecture. Unfortunately the space-dependent equations and the low computational precision do not make it possible to utilize the huge computing power of the analog CNN-UM chips so the Falcon emulated digital CNN-UM architecture is used to implement our solution.

关键词： Partial differential equations Computer architecture Cellular neural networks Geophysics computing Seismic waves Stress Analog computers image processing Very large scale integration Numerical models

来源：评论

学校读者我要写书评

暂无评论

Non-linear scale-selection for image compression improvement obtained by perceptual distortion criteria

Non-linear scale-selection for image compression improvement...

引用

International Conference on image Analysis and processing

作者： I. Kopilovic T. Sziranyi Department of Image Processing and Neurocomputing University of Veszprém Veszprem Hungary Analogical and Neural Computing Laboratory Computer & Automation Institute Hungarian Academy of Sciences (ATOMKI) Budapest Hungary Department of Image Processing and Neurocomputing University of Veszprém Hungary

The effect of linear and nonlinear diffusions prior to the Joint Photographic Experts Group (JPEG) standard baseline compression is analysed and compared. We shall show that anisotropic diffusion acts as an adaptive filtering that extracts and preserves the important visual information, and it will be shown how it can be used as a preprocessing method for compression artefact reduction. The selection of the appropriate preprocessing parameters at a specified bit-rate greatly reduces the compression artefacts. The selection criteria were determined using a perceptual error metric based on a model of the human visual system.

关键词： image coding Nonlinear distortion Adaptive filters Data mining image processing Transform coding Smoothing methods Nonlinear equations Noise shaping Filtering

来源：评论

学校读者我要写书评

暂无评论

Picture segmentation with introducing an anisotropic preliminary step to an MRF model with cellular neural networks

Picture segmentation with introducing an anisotropic prelimi...

引用

13th International Conference on Pattern Recognition, ICPR 1996

作者： Szirányi, Tamás Czúni, László Department of Image Processing and Neurocomputing University of Veszprém 8200 Veszprém Egyetem út 10. Hungary Analogical and Neural Computing Laboratory Computer and Automation Institute Hungarian Academy of Sciences Kende u. 13-17 H- 1111 Budapest Hungary

ISBN: (纸本)081867282X

Due to the large computation power needed for Markovian random field (MRF) based image processing, new variations of the basic MRF model are implemented. The transportation of the model to the very fast cellular neural networks (CNN) gave new tasks and opportunities to improve the technique, since the CNN has a special local architecture. This CNN architecture can be implemented in real VLSI circuits of superior speed in image processing. A type of MRF image segmentation with modified metropolis dynamics (MMD) can be well implemented in the CNN architecture. In this paper we address the improvement of this existing CNN method by introducing anisotropic diffusion as the smoothing process in the model. We suggest that this new feature with the MRF representation will give a new approach to solving early vision problems in the future. © 1996 IEEE.

关键词： Cellular neural networks

来源：评论

学校读者我要写书评

暂无评论

Morphological and wave segmentation by cellular neural networks

Morphological and wave segmentation by cellular neural netwo...

引用

Seminar on Neural Network Applications in Electrical Engineering

作者： T. Szabo P. Szolgay Neurocomputing and Image Processing Department University of Veszprém Veszprem Hungary Analogical and Neural Computing Laboratory Hungarian Academy of Sciences Hungary

This paper aims to carry out region-based segmentation in medical images. The main goal is to separate regions with the image features of a stroke, and moreover to develop algorithms for a special type of neural netwo... 详细信息

关键词： Cellular neural networks image segmentation Smoothing methods Biomedical imaging Analog computers Computer networks Concurrent computing Neural networks Anatomical structure Gaussian processes

来源：评论

学校读者我要写书评

暂无评论

Emulated digital CNN solution for two dimensional compressible flows

Emulated digital CNN solution for two dimensional compressib...

引用

European Conference on Circuit Theory and Design, ECCTD

作者： Sandor Kocsardi Zoltan Nagy Peter Szolgay Department of Image Processing and Neurocomputing University of Pannonia Veszprem Hungary Computer and Automation Research Institute Hungarian Academy of Sciences (ATOMKI) Budapest Hungary

In the area of mechanical, aerospace, chemical and civil engineering the solution of partial differential equations (PDEs) has been one of the most important problems of mathematics for a long time. Inside that one of the most exciting fields is the simulation of fluid flow, which involves for example problems of air, sea and land vehicle motion. In this paper a CNN-UM based solver of 2D inviscid, isothermal, compressible fluids will be presented. Unfortunately the necessity of the coupled multi-layered computational structure with non-linear, space-variant templates does not make it possible to utilize the huge computing power of the analog CNN-UM chips. To improve the performance of our solution an emulated digital CNN-UM has been used.

关键词： Cellular neural networks Analog computers Aerospace engineering Chemical engineering Civil engineering Partial differential equations Mathematics Computational modeling Fluid flow Land vehicles

来源：评论

学校读者我要写书评

暂无评论

Seismic wave propagation modelling on emulated digital CNN-UM architecture

Seismic wave propagation modelling on emulated digital CNN-U...

引用

作者： Kozma, Péter Nagy, Zoltán Szolgay, Péter Department of Image Processing and Neurocomputing University of Veszprém Egyetem u. 10 H-8200 Veszprém Hungary Analogic and Neural Computing Laboratory Computer and Automation Institute HAS Kende u. 13-17 H-1111 Budapest Hungary

The synthetic seismogram has seen many years of widespread and successful application in geophysical prospecting. It is used to simulate the normal incidence reflectivity of a horizontally stratified medium and has been employed more recently to obtain the responses of subsurface structural and stratigraphie configurations. The solution of the partial differential equations of motion describing the propagation of stress waves in an elastic medium requires enormous computation power. In this paper a solution of seismic wave propagation will be presented on CNN-UM architecture. Unfortunately the space-dependent equations and the low computational precision do not make it possible to utilize the huge computing power of the analog CNN-UM chips so the Falcon emulated digital CNN-UM architecture is used to improve the performance of our solution.

关键词： Electromagnetic wave propagation

来源：评论

学校读者我要写书评

暂无评论

Implementation of Nonlinear Template Runner Emulated Digital CNN-UM on FPGA

Implementation of Nonlinear Template Runner Emulated Digital...

引用

IEEE International Workshop on Cellular Nanoscale Networks and their Applications, (CNNA)

作者： Z. Kincses Z. Nagy P. Szolgay Department of Image Processing and Neurocomputing University of Pannonia Veszprém Hungary Analogic and Neural Computing Laboratory Computer and Automation Institute of HAS Budapest Hungary

In the original CNN paradigm template values are defined as constants but several complex tasks can be efficiently solved by using nonlinear weights between the CNN cells. Unfortunately programmable nonlinear weights can not be implemented by using present day analog VLSI technology. In this paper a new emulated digital CNN-UM architecture will be presented which makes it possible to use zero and first order nonlinear templates during emulation. The new architecture is based on the Falcon emulated digital CNN-UM architecture and implemented on FPGAs. The computing precision of the architecture is configurable and the area/speed/accuracy tradeoffs are investigated

关键词： Field programmable gate arrays Cellular neural networks Gray-scale Very large scale integration Computer architecture image processing Detectors Emulation Hamming distance Application software

来源：评论

学校读者我要写书评

暂无评论

Acoustic wvave propagation modeling on 3D CNN-UM architecture

Acoustic wvave propagation modeling on 3D CNN-UM architectur...

引用

IEEE International Workshop on Cellular Nanoscale Networks and their Applications, (CNNA)

作者： P. Sonkoly P. Kozma Z. Nagy P. Szolgay Department of Image Processing and Neurocomputing University of Pannonia Veszprém Hungary Analogic and Neural Computing Laboratory Computer and Automation Institute of HAS Budapest Hungary

Solution of partial differential equations (PDE) has long been one of the most important fields of mathematics. Several previous studies proved the effectiveness of the CNN-UM solution for partial differential equations in two dimensions. This paper works with the 3D acoustic wave equation which describes the pressure wave propagation in fluid medium. This three-dimensional PDE can be solved also with 3D CNN-UM and multilayer 2D CNN-UM architecture. Unfortunately the huge number of space-dependent equations and the low computational precision do not make it possible to utilize the huge computing power of the analogue CNN-UM chips so the Falcon emulated digital CNN-UM architecture is used to implement our solution

关键词： Acoustic propagation Partial differential equations Acoustic waves Electronic mail Computer networks Computer architecture Analog computers Very large scale integration Differential equations Cellular neural networks

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共7页 << < 1 2 3 4 5 6 7 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：