检索结果-内蒙古大学图书馆

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

作者： L. Czuni T. Sziranyi Department of Image Processing and Neurocomputing University of Veszpém Veszprem Hungary Analogical and Neural Computing Laboratory Computer and Automation Institute Hungarian Academy of Sciences Budapest Hungary

We have developed a high-level set of cellular neural net (CNN) functions for finding the segment-borders of moving objects through spatio-temporal relaxation optimization. They are analogic algorithms based on simple CNN instructions considering their implementability in analogic VLSI chips. Motion information extraction from video series is very power consuming. Most computing effort is devoted to motion vector field estimation, object definition and boundary determination. Finding interrelations among small segments, obtained by oversegmentation, involves optimization through merging or separation. In our algorithm the process starts from an oversegmented image, then the segments are merged using information from spatial and temporal auxiliary data: motion fields and motion history. This grouping process is based on neighboring segment similarity in color, speed and time-depth. There is also a feedback to accept or refuse the cancellation of a segment-border. Our parallel approach is independent of the number of segments or objects. We use simple VLSI functions. We develop grouping by stochastic optimization. This relaxation-based motion segmentation can be a basic step of the effective coding of image-series and other automatic motion tracking systems. The proposed system is planned to implement in a cellular nonlinear network chip-set architecture.

关键词： Motion segmentation Computer vision Tracking image segmentation Cellular neural networks Very large scale integration Neural networks Data mining Motion estimation Merging

来源：评论

学校读者我要写书评

暂无评论

Application of panoramic annular lens for motion analysis tasks: surveillance and smoke detection

Application of panoramic annular lens for motion analysis ta...

引用

International Conference on Pattern Recognition

作者： I. Kopilovic B. Vagvolgyi T. Sziranyi Department of Image Processing and Neurocomputing University of Veszprém Veszprem Hungary Analogical and Neural Computing Laboratory Comp. and Aut. Institute Hungarian Academy of Sciences Budapest Hungary

ISBN: (纸本)0769507506

In this paper some applications of motion analysis are investigated for a compact panoramic optical system (panoramic annular lens). Panoramic image acquisition makes multiple or mechanically controlled camera systems needless for many applications. Panoramic annular lens' main advantage to other omnidirectional monitoring systems is that it is a cheap, small, compact device with no external hyperboloidal, spherical, conical or paraboloidal reflecting surface as in other panoramic optical devices. By converting the annular image captured with an NTSC camera to a rectangular one, we get a low-resolution (2.8 pixels/degrees horizontally and 3 pixels/degree vertically) image. We developed algorithms which can analyze this low-resolution image to yield motion information for surveillance and smoke detection.

关键词： Lenses Motion analysis Cameras Pixel Control systems Monitoring Optical devices image converters image analysis image motion analysis

来源：评论

学校读者我要写书评

暂无评论

Spatio-temporal segmentation with edge relaxation and optimization using fully parallel methods

Spatio-temporal segmentation with edge relaxation and optimi...

引用

International Conference on Pattern Recognition

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

ISBN: (纸本)0769507506

In this paper we outline a fully parallel and locally connected computation model for the spatio-temporal segmentation of motion events in video sequences. We are searching for a new algorithm, which can be easily implemented in one-pixel/one-processor cell-array VLSI architectures at high-speed. Our proposed algorithm starts from an oversegmented image, then the segments are merged by applying the information coming from the spatial and temporal auxiliary data: motion fields and motion history, which is calculated from consecutive image frames. This grouping process is defined through a similarity measure of neighboring segments, which is based on the values of intensity, speed and the time-depth of motion history. As for checking the merging process there is a feedback implemented, by that we can accept or refuse the cancellation of a segment-border. Our parallel approach is independent of the number of segments and objects, since instead of graph representation and serial processing of these components, image features are defined on the pixel-level. We use simple functions, easily realizable in VLSI, like arithmetic and logical operators, local memory transfers and convolution.

关键词： image segmentation Very large scale integration History Concurrent computing Computational modeling Video sequences Computer architecture Motion measurement Velocity measurement Merging

来源：评论

学校读者我要写书评

暂无评论

A comparison of the different CNN implementations in solving the problem of spatiotemporal dynamics in mechanical systems

A comparison of the different CNN implementations in solving...

引用

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

作者： P. Szolgay T. Hidvegi Z. Szolgay P. Kozma Analogical and Neural Computing Laboratory Computer and Automation Institute Hungarian Academy of Sciences (ATOMKI) Budapest Hungary Department of Mechanics Technical University of Budapest Budapest Hungary Image processing and Neurocomputing University of Veszprém Veszprem Hungary

The large computing power of cellular neural networks (CNNs) is used to compute the transient response of a mechanical vibrating system. A basic question is how an inhomogeneous mechanical system can be computed by using different CNNUM (cellular neural net Universal Machine ) implementations. How complexity to time transformations were used in different CNNUM implementations, namely in software, in emulated digital CNN chips and in analog chips is discussed.

关键词： Cellular neural networks Spatiotemporal phenomena Mechanical systems Computer networks Equations Damping Boundary conditions Laboratories Automation Transient response

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

10th International Conference on image Analysis and processing, ICIAP 1999

作者： Kopilovic, Iván Szirányi, Tamás University of Veszprém Department of Image Processing and Neurocomputing Egyetem u. 10. H-8200 Veszprém Hungary University of Veszprém Department of Image Processing and Neurocomputing Hungarian Academy of Sciences Kende u. 13-17. H-1111 Budapest Hungary

ISBN: (纸本)0769500404

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. © 1999 IEEE.

关键词： Adaptive filtering

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

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

Object oriented motion-segmentation for video-compression in the CNN-UM

引用

Journal of VLSI Signal processing Systems for Signal, image, and Video Technology 1999年第2期23卷 479-496页

作者： Szirányi, Tamás László, Károly Czúni, László Ziliani, Francesco Analogical and Neural Comp. Lab. Comp. and Automation Inst. Hungarian Academy of Sciences H-1111 Budapest Kende u. 13-17 Hungary Dept. Image Proc. and Neurocomputing University of Veszprém H-8200 Veszprém Egyetem u. 10 Hungary Signal Processing Laboratory Swiss Fed. Institute of Technology CH-1015 Lausanne Switzerland

Object-oriented motion segmentation is a basic step of the effective coding of image-series. Following the MPEG-4 standard we should define such objects. In this paper, a fully parallel and locally connected computation model is described for segmenting frames of image sequences based on spatial and motion information. The first type of the algorithm is called early segmentation. It is based on spatial information only and aims at providing an over segmentation of the frame in real-time. Even if the obtained results do not minimize the number of regions, it is a good starting point for higher level post processing, when the decision on how to regroup regions in object can rely on both spatial and temporal information. In the second type of the algorithm stochastic optimization methods are used to form homogenous dense optical vector fields which act directly on motion vectors instead of 2D or 3D motion parameters. This makes the algorithm simple and less time consuming than many other relaxation methods. Then we apply morphological operators to handle disocclusion effects and to map the motion field to the spatial content. Computer simulations of the CNN architecture demonstrate the usefulness of our methods. All solutions in our approach suggest a fully parallel implementation in a newly developed CNN-UM VLSI chip architecture.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Anisotropic diffusion as a preprocessing step for efficient image compression

Anisotropic diffusion as a preprocessing step for efficient ...

引用

International Conference on Pattern Recognition

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

Anisotropic diffusion is an image enhancement method. It is a nonlinear process which removes noise and irrelevant details while preserving the edges, i.e. it "extracts" the essential visual information. The paper proposes a useful application of anisotropic diffusion in image data compression. We argue that for high compression an anisotropic diffusion preprocessing results in better quality of the decoded image.

关键词： Anisotropic magnetoresistance image coding image processing Transform coding Space heating Equations Laboratories Automation Time of arrival estimation Data mining

来源：评论

学校读者我要写书评

暂无评论

Anisotropic diffusion as a preprocessing step for efficient image compression

Anisotropic diffusion as a preprocessing step for efficient ...

引用

14th International Conference on Pattern Recognition, ICPR 1998

作者： Sziranyi, Tamás Kopilovic, Ivan Toth, Barnabas P. University of Veszprem Department of Image Processing and Neurocomputing Egyetem u. 10 H-8200 Veszprem Hungary Analogical and Neural Computing Laboratory Comp. and Automation Inst. Hungarian Academy of Sciences Kende u. 13-17 H-1111 Budapest Hungary

ISBN: (纸本)0818685123

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

image compression by orthogonal decomposition and dynamic segmentation using cellular nonlinear network chips

Image compression by orthogonal decomposition and dynamic se...

引用

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

作者： T. Sziranyi L. Czuni I. Kopilovic T. Gyimesi Analogical and Neural Computing Laboratory Hungarian Academy of Sciences Computer and Automation Institute Budapest Hungary Department of Image Processing 8z Neurocomputing University of Veszprém Veszprem Hungary

A method is shown using the CNN chip-set hardware architecture for the implementation of a high-speed, low bit-rate image coding system. A simple and fast algorithm is introduced to generate basis functions of 2 dimensional (2D) orthogonal transformations. Using the 2D basis functions of the Hadamard or Cosine functions, the transformation coefficients of the basic block of the image are measured by the CNN. Meanwhile, the CNN can produce the inverse transformation of the measured coefficients and the actual distortion-rate can be computed. If a required distortion-rate is reached, the coding process could be stopped (the use of even more coefficients would increase bit-rate needlessly). Effects of noise and VLSI computing accuracy are also considered to optimise the architecture. We also give a short description of how to join the transform coding method and the object-oriented image model.

关键词： image coding image segmentation Discrete cosine transforms Cellular neural networks Object oriented modeling Optimization methods Computer networks Distortion measurement Nonlinear distortion Very large scale integration

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：