检索结果-内蒙古大学图书馆

A Principal Component Clustering Approach to Object-Oriented Motion Segmentation and Estimation

Journal of VLSI Signal Processing systems for Signal, Image, and Video Technology 1997年第2-3期17卷 163-187页

作者： Lin, Yun-Ting Chen, Yen-Kuang Kung, S.Y. Department of Electrical Engineering Princeton University Princeton NJ 08544 United States National Taiwan University Taiwan Princeton University United States National Taiwan University Taiwan Princeton University NJ United States Stanford University United States Amdahl Corporation Sunnyvale CA United States Dept. of Elec. Engineering-Systems University of Southern California Los Angeles CA United States Stanford University Delft University of Technology United States Waseda University Tokyo Japan Department of Electrical Engineering Princeton University United States IEEE Transactions on Neural Networks United States VLSI Area United States IEEE Sign. Proc. Soc.'s Admin. Comm. United States IEEE United States

This paper presents a framework for object-oriented scene segmentation in video, which uses motion as the major characteristic to distinguish different moving objects and then to segment the scene into object regions. From the feature block (FB) correspondences through at least two frames obtained via a tracking algorithm, the reference feature measurement matrix and feature displacement matrix are formed. We propose a technique for initial motion clustering of the FBs, in which the principal components (PC) of the two matrices are adopted as the motion features. The motion features have several advantages: (1) They are low-dimensional (2-dim). (2) They preserve well both the spatial closeness and the motion similarity of their corresponding FBs. (3) They tend to form distinctive clusters in the feature space, thus allowing simple clustering schemes to be applied. The Expectation-Maximization (EM) algorithm is applied for clustering the motion features. For those scenes involving mainly the camera motion, the PC-based motion features will exhibit nearly parallel lines in the feature space. This facilitates a simple and yet effective layer extraction scheme. The final motion-based segmentation involves labeling of all the blocks in the frame. The EM algorithm is again applied to minimize an energy function which takes motion consistency and neighborhood-sensitivity into account. The proposed algorithm has been applied to several test sequences and the simulation results suggest a promising potential for video applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Extended algorithm of a fuzzy-set based power-system stabilizer with genetic algorithm tuning

引用

EUROPEAN TRANSACTIONS ON electrical POWER 1997年第3期7卷 205-210页

作者： Pedram, MM Seifi, H [?]Mir Mohsen Pedram (1967) received his B.Sc. and M.Sc. degrees in Electrical Engineering from Isfahan University of Technology (Isfahadnn) and Tarbiat-Modarres University (Tehran/Inn) in 1990 and 1994 respectively. His research interests are power-system control neural networks genetic algorithms and their applications in power systems. He is currently with Tarbiat-Modarres University. (Dept. of Electr. Engng. T d i at-Modarres University P.O. Box I4 155-4838. Tehradlran Phone: +9821/8005035 Fax: +9821/8006544 E-mail: E-Pednm@netef.modares.ac.ir)

The application of fuzzy logic controllers to improve power-system damping behaviour has received some attention in the literature during the last few years. The paper presents an approach in which besides speed and its first derivative, the second derivative is applied to the Fuzzy-set based power-system stabilizer (PSS), so that a three-dimensional space with improved behaviour is formed. The parameters are then optimized by the new searching technique, the genetic algorithm. Excellent digital simulation results are demonstrated for a single machine infinite bus-bar systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Formulation and algorithms for blind signal recovery

Formulation and algorithms for blind signal recovery

引用

Midwest Symposium on Circuits and systems (MWSCAS)

作者： F.M. Salam A.B. Gharbi G. Erten Circuits Systems and Artificial Neural Networks Laboratory Department of Electrical Engineering Michigan State University East Lansing MI USA Michigan State University East Lansing MI US Dept. of Electr. Eng. Michigan State Univ. East Lansing MI USA IC Tech Inc. Okemos MI USA

We review some recent approximations of the averaged mutual information criterion and its use as a measure of signal independence. We describe an update law and its comparison with previous work in the literature. We also identify the link between the minimization of the mutual information and the information-maximization of the output entropy function of a (nonlinear) neural network. Example simulations demonstrate the performance of our recently developed algorithm in static and dynamic environments.

关键词： Mutual information neural networks Finite impulse response filter Density measurement Circuits Artificial neural networks Laboratories Aging Electric variables measurement Minimization

来源：评论

学校读者我要写书评

暂无评论

Improvement of generalization for a perceptron with localized representation

引用

systems AND COMPUTERS IN JAPAN 1996年第5期27卷 74-85页

作者： Oohori, T Watanabe, K Hoshino, K Member Faculty of Engineering Hokkaido Institute of Technology Sapporo Japan 006 Takafumi Oohori graduated in 1973 from Dept. Electrical Eng. Hokkaido Univ. where he received his Ph.D. degree in 1978. He was a Lecturer in 1978 Assoc. Prof. in 1981 and Prof. in the Dept. Electrical Eng. Hokkaido Univ. He is engaged in research on systems engineering and neural net. He is a member of Inf. Prof. Soc. Japan. Associate Member

This paper intends to solve problems in the BP learning in the conventional multilayered perceptron, and proposes two methods, the local generalization and the global generalization, improve the generalization ability of the perceptron with the localized representation. In the local generalization, the generalization learning is executed so that the generalization ability function based on the distance between the separating partial hyperplanes and the set of patterns for learning, is maximized under the given order of separation in the learning. A problem then is that the range of adjustment for the separating partial hyperplane is limited depending on the order of separations, which prevents the improvement of the generalization ability. In the global generalization, the generalization ability function is defined considering the order of category separation and the optimal separating partial hyperplanes are determined simultaneously to maximize the function. Simulation experiments are carried out for the learning task on the two-dimensional plane and the recognition task for the handwritten Chinese characters. It is seen that the generalization ability is improved greatly. It is seen that the local generalization can realize nearly the same generalization ability, and the global generalization can realize a better generalization ability, compared to the BP learning.

关键词： generalization learning generalization ability function multilayered perceptron perceptron with localized representation handwritten Chinese character recognition

来源：评论

学校读者我要写书评

暂无评论

A modular analog chip for feed-forward networks with on-chip learning

A modular analog chip for feed-forward networks with on-chip...

引用

Midwest Symposium on Circuits and systems (MWSCAS)

作者： Hwa-Joon Oh F.M.A. Salam Circuits and systems and Artificial neural networks Laboratory Department of Electrical Engineering Michigan State University East Lansing MI USA Michigan State University East Lansing MI US Dept. of Electr. Eng. Michigan State Univ. East Lansing MI USA

A feedforward artificial neural network (ANN) with learning capability in modular design is presented using CMOS circuits. We employ a modified error backpropagation continuous-time learning rule. A (nonlinear) analog Gilbert multiplier is used as a synapse and a wide-range transconductance amplifier is used as soma. For learning circuits, the, same multiplier is used for updating the weights. Test results demonstrate the successful operation of the chip. Finally, a modular chip design for a large scale implementation of feedforward ANN with learning is described.< >

关键词： Feedforward systems Network-on-a-chip Artificial neural networks Equations Large-scale systems Neurons Circuits and systems Laboratories Electronic mail Circuit testing

来源：评论

学校读者我要写书评

暂无评论

An analog VLSI edge detection chip and digital multiprocessor chip for neural-based vision processing

An analog VLSI edge detection chip and digital multiprocesso...

引用

IEEE International Conference on systems engineering

作者： H. Okada B.J. Sheu C.-F. Chang Department of Electrical Engineering (Electrophysics and Systems) Signal & Image Processing Institute Center for Neural Engineering University of Southern California CA USA Dept. of Electr. Eng. Univ. of Southern California Los Angeles CA USA

A mixed-signal VLSI design for early vision processing, which includes an analog edge detection chip with embedded array photosensors and a digital multiprocessor chip, is described. The system architecture overview shows that the combination of the analog chip and the digital processors can perform highly efficient processing in neural-based vision processing. The analog edge detection chip consisting of 258*258 photosensor cells can be implemented in an area of 13.5 mm*15.5 mm using the MOSIS 0.8- mu m CMOS technology. The digital multiprocessor chip, which includes 64 processing elements, can be implemented in a 15.0-mm*18.0-mm chip using an industrial-scale 0.5- mu m CMOS technology. A system implementation for fingerprint verification is presented as an example of possible applications.< >

关键词： Very large scale integration Image edge detection Circuits CMOS technology Image processing Random access memory Control systems neural networks Image sensors Voltage

来源：评论

学校读者我要写书评

暂无评论

Harmonic insertion in PWM inverter drive schemes

引用

European Transactions on electrical Power 1992年第3期2卷 143-151页

作者： Theocharis, J. Petridis, V. Dr.-Ing. John Theocharis (1956) graduated as an Electrical Engineer from Aristotelian University of Thessaloniki.Greece in 1980. From 1980 to 1985 he has been with the scientific staff of the Department of Electrical Engineering at the Aristotelian University where he received the Ph.D. degree in 1985. Since 1986 he is working as a lecturer and in 1990 he became assistant professor at the Department of Electronics and Computer Engineering in the m e university. His research activities include control power electronics and electrical motor drives. Recently he is working with the Neural Network Systems with applications to field oriented control problems. Aristotelian University of Thessaloniki School of Engineering Faculty of Electrical Engineering Dept. of Electronics & Computer Engineering P.O. Box 438 GR-Thessalonikil/Greece.T+3131/219784Fax + 3031/274868) Prof. Dr.-Ing. Vasilis Petridis (1946) graduated from National Technical University of Athens Greece in 1969.He obtained the M.Sc. and the Ph.D. in electronics and systems from the University of London in 1970 and 1974. respectively. H i s interests include applied automatic control neural networks drives dynamic systems robotics etc. He is currently professor in the Department of Electronics and Computer Engineering of the University of Thessaloniki. (Aristotelian University of Thessaloniki. School of EngineeringFaculty of Electrical Engineering Dept. of Electronics & Computer Engineering P.O. Box 438. GR-ThessaloniW Greece T+3031/219784.Fax+3031/274868)

The procedure of harmonic insertion is generalized in this paper. Analytical expressions of the voltage spectra are derived. The insertion of the 3rd harmonic to the modulating signal, which is of particular interest, is considered as a special case. It is demonstrated in this case that the fundamental harmonic component of the phase and the line‐to‐line voltage is not affected by the insertion of the 3rd harmonic for sufficiently high values of the chopping ratio. However it has been shown that the higher harmonic spectrum is significantly improved as compared to the case of pure sinusoidal modulation. For different values of the fundamental component the optimal values of the amplitude of the third harmonic to be inserted have been calculated so that the distortion factor of the higher harmonic spectrum is minimized. Other cases of harmonic insertion are also considered which provide spectrum efficiency improvement. Experimental results are given which have been obtained by means of a microcomputer controlled PWM generator constructed for this purpose. Copyright © 1992 John Wiley & Sons, Ltd.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A VLSI neural network for color constancy 90

A VLSI neural network for color constancy

引用

Proceedings of the 4th International Conference on neural Information Processing systems

作者： Andrew Moore Geoffrey Fox John Allman Rodney Goodman Computation and Neural Systems Program California Institute of Technology Pasadena CA Dept. of Physics Syracuse University Syracuse NY and Dept. of Physics California Institute of Technology Pasadena CA Dept. of Biology California Institute of Technology Pasadena CA Dept. of Electrical Engineering California Institute of Technology Pasadena CA

ISBN: (纸本)9781558601840

A system for color correction has been designed, built, and tested successfully; the essential components are three custom chips built using subthreshold analog CMOS VLSI. The system, based on Land's Retinex theory of color constancy, produces colors similar in many respects to those produced by the visual system. Resistive grids implemented in analog VLSI perform the smoothing operation central to the algorithm at video rates. With the electronic system, the strengths and weaknesses of the algorithm are explored.

关键词：

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：