检索结果-内蒙古大学图书馆

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

Neural Fault Detection and Accommodation for Interconnected Power Systems

引用

IFAC Proceedings Volumes 1997年第18期30卷 943-947页

作者： Spyros Tzafestas Yiannis Anthopoulos Efthimios Kyriannakis Intelligent Robotics and Automation Laboratory Department of Electrical and Computer Engineering National Technical University of Athens Zographou 15773 Athens Greece. Tel: +30-1-7722489 +30-1-772-1527 Fax: +30-1-7722490 +30-1-7722459

Due to increasing safety and reliability demands fault detection and accommodation is a key issue in the design of industrial control systems. This paper presents a neural network based method for fault detection and accommodation, appropriate for interconnected power systems. The simulation results show that the method is very promising.

关键词： fault detection neural networks interconnected systems

来源：评论

学校读者我要写书评

暂无评论

Neural networks based sensorial signal fusion: an application to material identification

Neural networks based sensorial signal fusion: an applicatio...

引用

International Conference on Digital Signal Processing (DSP)

作者： S.G. Tzaiestas Y. Anthopoulos Dept. of Electr. & Comput. Eng. Nat. Tech. Univ. of Athens Greece Intelligent Robotics and Automation Laboratory Department of Electrical and Computer Engineering National and Technical University of Athens Athens Greece

Data acquisition and learning capabilities are necessary for an intelligent system operating in unstructured, dynamically changing environments. For this purpose, a method for the effective use of multiple sensors must be developed. This paper shows how multisensor fusion can be accomplished by neural networks. It first summarizes the conventional fusion techniques and consequently describes the use of neural networks for sensor fusion as well as their advantages. Finally, an application is presented where a neural network is used to fuse the signals of several sensors, of different type, for material identification purposes.

关键词： Neural networks Signal processing Sensor fusion Intelligent sensors Sensor phenomena and characterization Sensor systems Intelligent systems Intelligent robots Costs Recursive estimation

来源：评论

学校读者我要写书评

暂无评论

The active kinematic histogram method for path planning of non-point, non-holonomically constrainted mobile robots

引用

Advanced robotics 1997年第4期12卷 373-395页

作者： Katevas, Nikos I. Tzafestas, Spyros G. Zenon SA - Industrial Automation Athens 15344 Kanari 5 Greece Intelligent Robotics and Automation Laboratory Department of Electrical and Computer Engineering National Technical University of Athens Athens 15773 Zografou Campus Greece

The paper presents a novel path planning method for non-point, non-holonomically constrainted mobile robots. The proposed method, named the Active Kinematic Histogram (AKH) method, is a potential field path-planning method based on the Vector Field Histogram (VFH) method introducedby J. Borenstein and Y. Koren. The method relies on one-dimensional environment representations named AKHs, derived from the available information on the obstacle space and the robot itself. The AKHs provide the information abstraction required for fast, collision-free and kinematically feasiblepath planning for non-point, non-holonomically constrainted mobile robots. The method constructs two AKH structures incorporating the information stored in occupancy grid environment representations as well as the exact robot's size, shape and kinematic features. The method applies simpleand fast procedures, e.g. histogram shifting, in order to determine kinematic feasibility and the result of the robot's steering limits. Being a potential field method, the AKH method uses adaptive thresholding procedures to reduce the inherited drawback of the local minima traps ***, the method proposes specific updating and coding procedures for the environmental information and introduces the Ageing function to insert time parameterization in the path-planning results. Also, the so-called bicycle kinematic model is presented in order to describe the kinematicfamily of mobile robots suitable for applying the AKH method. The method integrates a velocity control procedure which is also based on information provided by the active kinematic histograms. The method produced smooth, collision-free paths in a variety of experimental configurations. Simulationand experimental results are presented. © VSP and robotics Society of Japan 1997.

关键词：

来源：评论

学校读者我要写书评

暂无评论

High-speed extraction of 3D structure of selectable quality using a translating camera

引用

computer vision AND IMAGE UNDERSTANDING 1996年第1期64卷 97-110页

作者： Dalmia, AK Trivedi, M Computer Vision and Robotics Research Laboratory Electrical and Computer Engineering Department The University of Tennessee Knoxville Tennessee 37996-2100

In this paper we present a computational approach for extracting three-dimensional structure of controllable resolution, depth of field, and accuracy, all made available at real-time speeds, This approach utilizes the spatial and the temporal gradients of the streams of images acquired using an actively controlled camera, Depending on the requirements of a particular task, appropriate parameters such as disparity value sought, interframe camera displacement, and number of frames in a stream are chosen to control the resolution, depth of field, and accuracy, The acquisition and processing of the image stream are done in real time on a pipeline architecture based processor. Extensive experiments are presented to demonstrate the system's accuracy, controllability of depth of field and resolution, and ability to perform successfully in a variety of scenes. The system operated with no latency between image acquisition and processing. The total acquisition and processing time in these experiments is in the range from 0.27 to 1.56 s. The depth results have an accuracy of 85% to 92%. (C) 1996 Academic Press, Inc.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Towards a general multi-view registration technique

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 1996年第5期18卷 540-547页

作者： Bergevin, R Soucy, M Gagnon, H Laurendeau, D Computer Vision and Systems Laboratory Department of Electrical and Computer Engineering Laval University QUE Canada

We present an algorithm that reduces significantly the level of the registration errors between all pairs in a set of range views. This algorithm refines initial estimates of the transformation matrices obtained from either the calibrated acquisition setup or a crude manual alignment. It is an instance of a category of registration algorithms known as iterated closest-point (ICP) algorithms. The algorithm considers the network of views as a whole and minimizes the registration errors of all views simultaneously. This leads to a well-balanced network of views in which the registration errors are equally distributed, an objective not met by previously published ICP algorithms which all process the views sequentially. Experimental results show that this refinement technique improves the calibrated registrations and the quality of the integrated model for complex multipart objects. In the case of scenes comprising man-made objects of very simple shapes, the basic algorithm faces problems common to all ICP algorithms and must thus be extended.

关键词： multiple view registration model building three-dimensional objects range images surface modeling multiple view integration

来源：评论

学校读者我要写书评

暂无评论

A generalized Hermite pyramid for ultrasonic image analysis .2. Gallstone

引用

ULTRASONIC IMAGING 1996年第4期18卷 305-327页

作者： Venkatesh, YV Computer Vision and Artificial Intelligence Laboratory Department of Electrical Engineering Indian Institute of Science

This paper deals with the problem of extracting information regarding the chemical composition of stones in the human gallbladder from in vitro and in vivo B-scan ultrasonic images. The images are subjected to the Hermite pyramid decomposition technique described in Part I (Venkatesh, Y. V., Ultrasonic Imaging, 18, 261-301, 1996). In an attempt to determine the chemical composition of the gallstones, the gradients of the decomposed images are input to an unsupervised classifier. The outputs of the classifier exhibit some interesting patterns that appear to be related to the chemical composition of the gallstones contained in these images. (C) 1996 Academic Press.

关键词： gallstones Hermite polynomials image decomposition medical imaging multiscale image analysis ultrasonic image analysis unsupervised classification

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：