检索结果-内蒙古大学图书馆

Sparse feature maps in a scale hierarchy 2

2nd International Workshop on Algebraic Frames for the Perception-Action Cycle, AFPAC 2000

作者： Forssén, Per-Erik Granlund, Gösta Computer Vision Laboratory Department of Electrical Engineering Linköping University LinköpingSE-58183 Sweden

ISBN: (纸本)3540410139

This article describes an essential step towards what is called a view centered representation of the low-level structure in an image. Instead of representing low-level structure (lines and edges) in one compact feature map, we will separate structural information into several feature maps, each signifying features at a characteristic phase, in a specific scale. By characteristic phase we mean the phases 0, π, and ±π/2, corresponding to bright, and dark lines, and edges between different intensity levels, or colours. A lateral inhibition mechanism selects the strongest feature within each local region of scale represented. The scale representation is limited to maps one octave apart, but can be interpolated to provide a continous representation. The resultant image representation is sparse, and thus well suited for further processing, such as pattern detection. © Springer-Verlag Berlin Heidelberg 2000.

关键词： Edge detection

来源：评论

学校读者我要写书评

暂无评论

An associative perception-action structure using a localized space variant information representation 2

引用

2nd International Workshop on Algebraic Frames for the Perception-Action Cycle, AFPAC 2000

作者： Granlund, Gösta H. Computer Vision Laboratory Department of Electrical Engineering Linköping University LinköpingSE-581 83 Sweden

ISBN: (纸本)3540410139

Most of the processing in vision today uses spatially invariant operations. This gives efficient and compact computing structures, with the conventional convenient separation between data and operations. This also goes well with conventional Cartesian representation of data. Currently, there is a trend towards context dependent processing in various forms. This implies that operations will no longer be spatially invariant, but vary over the image dependent upon the image content. There are many ways in which such a contextual control can be implemented. Mechanisms can be added for the modification of operator behavior within the conventional computing structure. This has been done e. g. for the implementation of adaptive filtering. In order to obtain sufficient flexibilility and power in the computing structure, it is necessary to go further than that. To achieve sufficiently good adaptivity, it is necessary to ensure that sufficiently complex control strategies can be represented. It is becoming increasingly apparent that this can not be achieved through prescription or program specification of rules. The reason being that these rules will be dauntingly complex and can not be be dealt with in sufficient detail. At the same time that we require the implementation of a spatially variant processing, this implies the requirement for a spatially variant information representation. Otherwise a sufficiently effective and flexible contextual control can not be implemented. This paper outlines a new structure for effective space variant processing. It utilises a new type of localized information representation, which can be viewed as outputs from band pass filters such as wavelets. A unique and important feature is that convex regions can be built up from a single layer of associating nodes. The specification of operations is made through learning or action controlled association. © Springer-Verlag Berlin Heidelberg 2000.

关键词： Adaptive filtering

来源：评论

学校读者我要写书评

暂无评论

Fast and accurate motion estimation using orientation tensors and parametric motion models

Fast and accurate motion estimation using orientation tensor...

引用

15th International Conference on Pattern Recognition, ICPR 2000

作者： Farneback, Gunnar Computer Vision Laboratory Department of Electrical Engineering Linkoping University LinkopingSE-581 83 Sweden

ISBN: (纸本)0769507506

Motion estimation in image sequences is an important step in many computer vision and image processing applications. Several methods for solving this problem have been proposed, but very few manage to achieve a high level of accuracy without sacrificing processing speed. This paper presents a novel motion estimation algorithm, which gives excellent results on both counts. The algorithm starts by computing 3D orientation tensors from the image sequence. These are combined under the constraints of a parametric motion model to produce velocity estimates. Evaluated on the well-known Yosemite sequence, the algorithm shows an accuracy substantially better than those obtained using previously published methods. Computationally, the algorithm is simple and can be implemented by means of separable convolutions, which also makes it fast. © 2000 IEEE.

关键词： Motion estimation

来源：评论

学校读者我要写书评

暂无评论

Activity monitoring and summarization for an intelligent meeting room

Activity monitoring and summarization for an intelligent mee...

引用

Workshop on Human Motion

作者： I. Mikic K. Huang M. Trivedi Computer Vision and Robotics Research Laboratory Department of Electrical and Computer Engineering University of California San Diego USA

Intelligent meeting rooms should support efficient and effective interactions among their occupants. In this paper, we present our efforts toward building intelligent environments using a multimodal sensor network of static cameras, active (pan/tilt/zoom) cameras and microphone arrays. Active cameras are used to capture details associated with interesting events. The goal is not only to make a system that supports multi-person interactions in the environment in real time, but also to have the system remember the past, enabling reviews of past events in an intuitive and efficient manner. In this paper, we present the system specifications and major components, integration framework, active network control procedures and experimental studies involving multi-person interactions in an intelligent meeting room environment.

关键词： Monitoring Intelligent sensors Intelligent networks Smart cameras Microphone arrays Sensor arrays Intelligent structures Multimodal sensors Real time systems Control systems

来源：评论

学校读者我要写书评

暂无评论

Multimodality image registration and fusion using neural network

Multimodality image registration and fusion using neural net...

引用

3rd International Conference on Information Fusion, FUSION 2000

作者： Mostafa, Mostafa G. Farag, Aly A. Essock, Edward Computer Vision and Image Processing Laboratory Department of Electrical and Computer Engineering University of Louisville Louisville KY 40292 United States Department of Psychology University of Louisville Louisville KY 40292 United States

ISBN: (纸本)2725700000

Multi-modality image registration and fusion are essential steps in building 3D models from remote sensing data. In this paper, we present a neural network technique for the registration and fusion of multi-modality remote sensing data for the reconstruction of 3D models of terrain regions. A feedforward neural network is used to fuse the intensity data sets with the spatial data set after learning its geometry. Results on real data are presented. Human performance evaluation is assessed on several perceptual tests in order to evaluate the fusion results. © 2000 Int. Soc. Inf. Fusion.

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

A hybrid pneumatic/electrostatic milli-actuator

A hybrid pneumatic/electrostatic milli-actuator

引用

ASME 2000 International Mechanical engineering Congress and Exposition, IMECE 2000

作者： Chiang, Kenneth H. Fearing, Ronald S. Robotics and Intelligent Machines Laboratory Department of Electrical Engineering and Computer Sciences University of California 265M Cory Hall BerkeleyCA94720-1770 United States

ISBN: (纸本)9780791819005

In typical MEMS applications, actuation is accomplished directly by converting electrical input power to useful mechanical power. However, indirect schemes employing electrically driven primary and alternately driven secondary actuators can trade simplicity and bandwidth for lower forces and strokes in the primary actuator, hence reducing power consumption. Because it is generally easier to build actuators with high force and low stroke. we propose a hybrid actuator with a pneumatic oscillator as the secondary and an electrostatic clamp as the primary. By clamping the oscillator at its extremes of travel, the hybrid actuator can be turned on and off. In this paper, we report on progress towards fabricating such a hybrid actuator. We have demonstrated operation of a 40x40x30 mm3 oscillator at 6 Hz with a stroke of 2.5 mm and a peak force of 1.1 N, although fabrication of the electrostatic clamp has not been accomplished. Copyright © 2000 by ASME

关键词： Pneumatics

来源：评论

学校读者我要写书评

暂无评论

Complementary linear biases in spatial derivative estimation for improving geometry-driven diffusion processes

Complementary linear biases in spatial derivative estimation...

引用

15th International Conference on Pattern Recognition, ICPR 2000

作者： Toczyski, William D. Papanikolopoulos, Nikolaos P. Artificial Intelligence Robotics and Vision Laboratory Department of Computer Science and Engineering University of Minnesota 4-192 EE/CS Bldg. 200 Union Street SE MinneapolisMN55455 United States

ISBN: (纸本)0769507506

This paper introduces a broadly applicable technique for visibly improving the digitized, grey-level outputs produced by a host of iterative geometric diffusion methods. By replacing standard, central-difference estimates of discrete spatial gradients with alternating image derivative estimates that are offset by known, complementary biases, errors accumulated during iteration are reduced and the quality of geometric diffusions is improved. This unexpected synergy occurs at no added computational cost over central difference methods. Very simple to implement, the innovation is introduced at the level of spatial derivatives;hence, for a given process, any derived higher level mathematical properties - for example, group invariance or scale-space properties - can be preserved. © 2000 IEEE.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Detecting rotational symmetries using normalized convolution

Detecting rotational symmetries using normalized convolution

引用

International Conference on Pattern Recognition

作者： B. Johansson H. Knutsson G. Granlund Computer Vision Laboratory Department of Electrical Engineering Linköping University Linkoping Sweden

ISBN: (纸本)0769507506

Perceptual experiments indicate that corners and curvature are very important features in the process of recognition. This paper presents a new method to detect rotational symmetries, which describes complex curvature such as corners, circles, star, and spiral patterns. It works in two steps: 1) it extracts local orientation from a gray-scale or color image; and 2) it applies normalized convolution on the orientation image with rotational symmetry filters as basis functions. These symmetries can serve as feature points at a high abstraction level for use in hierarchical matching structures for 3D estimation, object recognition, image database retrieval, etc.

关键词： Convolution computer vision Filters Spirals Color Laboratories Gray-scale Object recognition Image databases Humans

来源：评论

学校读者我要写书评

暂无评论

Fast and accurate motion estimation using orientation tensors and parametric motion models

Fast and accurate motion estimation using orientation tensor...

引用

International Conference on Pattern Recognition

作者： G. Farneback Computer Vision Laboratory Department of Electrical Engineering Linköping University Linkoping Sweden

ISBN: (纸本)0769507506

关键词： Motion estimation Tensile stress Image sequences Spatiotemporal phenomena computer vision Laboratories Image processing Filtering algorithms Maximum likelihood detection Maximum likelihood estimation

来源：评论

学校读者我要写书评

暂无评论

Design and implementation of a logic controller using petri nets and ladder logic diagrams

引用

IFAC Proceedings Volumes 2000年第20期33卷 333-338页

作者： S.G. Tzafestas M.G. Pantelelis D.L. Kostis Intelligent Robotics and Automation Laboratory Department of Electrical and Computer Engineering National Technical University of Athens Zografou 15773 Athens Greece

This paper presents a new method for using Petri net models in order to design and implement a sequence controller for a small scale robotic cell which consists of a robotic manipulator, a variety of sensors and electro-pneumatic actuators. The proposed method leads directly to the generation of the associated Ladder Logic Diagrams (LLDs) and it has proved to be effective through the application to sequence control of a small-scale industrial system. In addition, it has reduced the period for developing, debugging and reengineering of the LLD, compared to die traditional method that directly prepares an LLD. Experimental results are included to show the effectiveness of the PN/LDD controller.

关键词： Discrete industrial systems Petri nets LLD PLC

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：