检索结果-内蒙古大学图书馆

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： V. Parameswaran P. Burlina R. Chellappa Computer Vision Laboratory University of Maryland College Park MD USA Department of Electrical Engineering University of Maryland College Park MD USA

Robustness as well as the ability to work in an unsupervised mode are two desirable features of algorithms employed on large image databases. This paper describes parameter optimization strategies for such algorithms and motivates these strategies by focussing on aerial image exploitation and studying certain specific aerial image understanding algorithms, namely local vehicle detection and global vehicle configuration detection. The paper first gives a brief introduction to the problem in the context of aerial imagery. Next, a high level description of the algorithms and parameters that need to be optimized is given. Strategies for parameter optimization are illustrated using examples. Finally a discussion on the applicability and scope for improvement of the strategies is given.

关键词： Performance analysis Vehicle detection Image databases Vehicles Lighting Detection algorithms computer vision Laboratories Educational institutions Robustness

来源：评论

学校读者我要写书评

暂无评论

Using a robot arm to facilitate the learning in young and mentally development-delayed children

Using a robot arm to facilitate the learning in young and me...

引用

International Conference on Emerging Technologies and Factory Automation (ETFA)

作者： J. Gu F. Dong M. Meng A. Cook Department of Electrical and Computer Engineering ART (Advanced Robotics and Teleoperation) Laboratory Canada Faculty of Rehabilitation Medicine University of Alberta Edmonton AB Canada

The study is based on two assumptions: 1) the child is an active, goal-oriented participant in his or her own development; and 2) physical manipulation of objects is a major contributing factor in the development of cognitive and language skills in a very young child. The CRS robot arm system is used in our study. All the functions are under the control of a computer based software control algorithm. The training program uses either the teach pedant or a series of text commands to train the arm. With the teach pedant, the operator can move the arm in desired directions by pressing the button on the teach pedant. In the text training mode, the arm moves according to the command set predefined. Another important aspect of the project is how to set up the interface and communication environment between the young children and the robot arm. The final program lets the child to accomplish a series of processing complex tasks through simple operation of certain buttons. The programmed activities have a development sequence, which eventually brings the robot arm under the control of the child; at the same time it facilitates the learning process of the child.

关键词： Robots Medical robotics Rehabilitation robotics Pediatrics Cognitive robotics Pressing Switches computerized monitoring Wrist Grippers

来源：评论

学校读者我要写书评

暂无评论

Some applications of active contours using ANNs isomorphic to boundaries

Some applications of active contours using ANNs isomorphic t...

引用

International Conference on Information, Communications and Signal Processing

作者： Y.V. Venkatesh N. Rishikesh Computer Vision and Artificial Intelligence Laboratory Department of Electrical Engineering Indian Institute of Science Bangalore India Indian Institute of Science Bangalore Karnataka IN

We present a few applications of the neural active contour model described by Venkatesh Rishikesh (see International Conference on Neural Networks (ICNN-97), Houston, Texas, USA, 1997). The model, which is a neural network based on the principles of self-organization, exploits the principles of spatial isomorphism and self-organization in order to create flexible contours for characterizing shapes in images. We illustrate the versatility of the model by presenting its applications to the problems of boundary extraction, stereo vision, biomedical image analysis and digital image libraries. Only the essential ideas are described.

关键词： Active contours Image edge detection Shape Deformable models Application software computer vision Artificial neural networks Stereo vision Image motion analysis Tracking

来源：评论

学校读者我要写书评

暂无评论

Multisensor integration for scene classification: an experiment in human form detection

Multisensor integration for scene classification: an experim...

引用

IEEE International Conference on Image Processing

作者： S. Shah J.K. Aggarwal J. Eledath J. Ghosh Computer and Vision Research Center Department of Electrical and Computer Engineering University of Texas Austin Austin TX USA University of Texas at Austin Austin TX US Laboratory for Artificial Neural Systems Department of Electrical and Computer Engineering University of Texas Austin Austin TX USA

This paper presents a system for classification of scenes using a multisensor integration framework. Indoor scenes are imaged using a visual and an infrared sensor and the images processed in three stages to perform classification of sensed objects into two classes: human and background. Finally, information from individual classifiers is integrated in order to obtain an improved classification performance. Details of feature extraction and classification using neural network combining a multi-Bayesian framework are presented. Segmentation of the imaged scene is performed using existing techniques such as texture analysis and histogram modeling. Classification results on real-world data are presented. The system represents a first step in the development of improved, robust classifiers based on the concepts of neural networks and multisensor integration.

关键词： Layout Neural networks Infrared sensors Humans Feature extraction Image segmentation Image analysis Image texture analysis Performance analysis Histograms

来源：评论

学校读者我要写书评

暂无评论

Digital halftoning as 2-D delta-sigma modulation

Digital halftoning as 2-D delta-sigma modulation

引用

IEEE International Conference on Image Processing

作者： T.D. Kite B.L. Evans A.C. Bovik T.L. Sculley Laboratory for Vision Systems Department of Electrical and Computer Engineering University of Texas Austin Austin TX USA ESS Technology Inc. Austin TX USA

The error diffusion algorithm for digital halftoning is equivalent in form to a noise-shaping feedback coder, a class of delta-sigma modulator. The white noise assumption of the quantizer error is known to be false; in fact, the quantizer error is seen to be highly correlated with the input image. To account for this correlation, we use a gain model for the quantizer. This model accurately predicts the edge sharpening and noise shaping caused by all error diffusion schemes. It also permits an extension of error diffusion to oversampled imagery.

关键词： Delta-sigma modulation Filters Noise shaping Feedback Delta modulation Predictive models Digital modulation Modulation coding White noise Equivalent circuits

来源：评论

学校读者我要写书评

暂无评论

Synthesized passive feedback control of sensor-rich structures

Synthesized passive feedback control of sensor-rich structur...

引用

American Control Conference (ACC)

作者： P. Akella J.T. Wen Control Laboratory for Mechanical Structures (CLaMS) Center for Advanced Technology in Automation Robotics & Manufacturing Department of Electrical Computer and Systems Engineering Rensselaer Polytechnic Institute Troy NY USA

The passivity property of dissipative mechanical structures has long been exploited in designing passive controllers that provide robust stability even in the presence of unmodeled dynamics of the system. For an input/output map of a flexible structure to be passive, collocation of the actuators and sensors is required and also the sensors should measure the velocity of the system. The so-called smart structures frequently have more sensors than actuators. Therefore, the passive controller can at best utilize only a subset of the sensors. In this paper we consider the design of a squaring down matrix which would render a system passive subject to some additional performance considerations. The problem of obtaining the synthesized passive output is cast as a set of linear matrix inequalities (LMIs) which can be efficiently solved by the LMI Toolbox in Matlab. We apply this procedure with the assumption that the sensors provide both displacement and velocity information which is generally not true. We show that the passive controllers can be implemented without the use of velocity information. By using synthesized passive outputs in addition to naturally occurring passive outputs, we obtain better system performance. We present experimental results involving a single flexible beam with torque input and hub angular position and strain gage outputs.

关键词： Feedback control Intelligent sensors Control system synthesis Mechanical sensors Sensor systems Linear matrix inequalities Mechanical factors Control systems Robust stability Flexible structures

来源：评论

学校读者我要写书评

暂无评论

Growing region technique in the detection of autonomous structures within X-ray radiographs

Growing region technique in the detection of autonomous stru...

引用

IEEE Symposium on Nuclear Science (NSS/MIC)

作者： S.N. Raptis S.G. Tzafestas S. Pavlopoulos D. Koutsouris S. Kollias Intelligent Robotics and Automation Laboratory National and Technical University of Athens Athens Greece Biomedical Engineering Laboratory National and Technical University of Athens Athens Greece Department of Electrical & Computer Engineering National and Technical University of Athens Athens Greece

Nodule identification is a major issue in chest radiography and cancer prevention and detection. The recognition of cancer nodule characteristics in chest radiographs is a key point to the detection procedure. The method described here is based on the extraction of the major geometrical as well as luminance characteristics that make nodule recognizable and easy to detect. The purpose of the proposed method is to detect within a given block of chest X-ray image any homogeneous and autonomous mass that might means the existence of a nodule or some structure within it. The idea of pixels of interest is introduced which makes the growing a finite steps procedure. The growing of the region around a given point is realized gradually in a finite number of iterations at each one of which a set of criteria is evaluated. These criteria are established in a prior training procedure.

关键词： X-ray detection X-ray detectors X-ray imaging Diagnostic radiography Pixel Laboratories Biomedical engineering Cancer detection Character recognition Shape

来源：评论

学校读者我要写书评

暂无评论

Telemanipulator neurocontrol using multiple RBF networks

Telemanipulator neurocontrol using multiple RBF networks

引用

IEEE International Symposium on Intelligent Control (ISIC)

作者： S.G. Tzafestas P.A. Prokopiou C.S. Tzafestas Intelligent Robotics and Automation Laboratory Department of Electrical and Computer Engineering National and Technical University of Athens Athens Greece Laboratoire de Robotique de Paris CNRS UPMC UVSQ France

This paper addresses the control problem of masterslave systems which involve severe modeling errors and other high-level uncertainties, using neural networks. The solution approach is based on a recent teleoperator control scheme of S. Lee and H.S. Lee (1993, 1994), which is suitably enhanced such that to become capable of compensating the uncertainties. The class of radial-basis functions (RBF) neural networks are employed in a multipartitioned neural network architecture, and a special learning scheme is adopted which distributes the learning error to each subnetwork and allows online learning. The effectiveness of the present RBF neurocontroller was investigated through extensive simulation and compared to that of MLP (multilayer perceptron) neurocontroller and a robust sliding-mode controller representative.

关键词： Radial basis function networks Robot kinematics Error correction Neural networks Teleoperators Master-slave Uncertainty Delay effects robotics and automation Neurocontrollers

来源：评论

学校读者我要写书评

暂无评论

Multiscale segmentation and approximation for significant description of 2D contours

Multiscale segmentation and approximation for significant de...

引用

IEEE International Conference on Image Processing

作者： M. Makhtari R. Bergevin Dept. of Electr. & Comput. Eng. Laval Univ. Que. Canada Computer Vision and Systems Laboratory Department of Electrical and Computer Engineering Laval University Sainte-Foy QUE Canada

This paper proposes a new approach for the multiscale segmentation and approximation of 2D contours. Its ultimate goal is to find the best set of constant curvature segments (straight line segments and/or circular arcs) to describe the contour in a way that respects its actual shape for recognition purposes. This approach is strictly based on discrete geometry principles, and the resulting algorithm named MuscaGrip (multiscale segmentation and contour approximation based on the geometry of regular inscribed polygons) computes, at multiple scales, two grouping processes.

关键词： Shape Computational geometry Approximation algorithms Merging Iterative algorithms computer vision Laboratories Multi-stage noise shaping Maximum likelihood detection

来源：评论

学校读者我要写书评

暂无评论

A Dynamic Predicting Algorithm for Estimating Bus Arrival Time

引用

IFAC Proceedings Volumes 1997年第8期30卷 1225-1228页

作者： Edwin M. Reinhoudt S.A. Velastin Delft University of Technology Department of Electrical Engineering Telecommunications and Traffic Control Systems Group Mekelweg 4 2628 CD Delft the Netherlands fax: +31 (15) 278 1774 Department of Electronic & Electrical Engineering Vision and Robotics Laboratory King’s College London Strand London WC2R 2LS United Kingdom fax: +44 (171) 873 2211

In order to maintain a high quality service and keep up with the ever increasing demands in the field of public transport, London Transport Buses (LTB) equipped bus routes in a test area in North London with a new system called Countdown. The system calculates arrival time estimations which inform both the customers and the operators of the company about the running of their buses. The calculations should be as accurate as possible in the interest of customer satisfaction. This paper shows that the use of a dynamic Kalman filter instead of a previously used static averaging algorithm, improves the error distribution up to 7% and often reduces maximum absolute error figures significantly. This technique may also prove to be a useful tool for other predicting systems.

关键词： Measurement Surveillance Estimation Practical Application Results Travel Traffic Information Public Transport

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：