检索结果-内蒙古大学图书馆

Midwest Symposium on Circuits and Systems (MWSCAS)

作者： N. Ramesh V. Chaudhary Vision & Neural Networks Laboratory Department of Computer Science Wayne State University Detroit MI USA Department of Electrical and Computer Engineering Wayne State University Detroit MI USA

Many low level vision tasks that are computationally intensive are easily parallelizable. The lack of parallel processing systems, or their prohibitive costs, have prevented the move of vision processing algorithms from single processor systems to multiprocessor systems. With the recent spurt of parallel processing hardware, there is a need to investigate the feasibility of using such machines for some vision algorithms. Speedup is an important factor in determining the feasibility of migration from single processor systems to parallel processors. In this work, we investigate a particular segmentation algorithm and present theoretical speedup results. Our formula can work out numerical speedups by simply plugging in the parameter values.< >

关键词： Image analysis Image segmentation computer vision Parallel processing Neural networks computer science Concurrent computing Costs Multiprocessing systems Hardware

来源：评论

学校读者我要写书评

暂无评论

Local estimation of Gaussian-based edge enhancement filters using Fourier analysis

Local estimation of Gaussian-based edge enhancement filters ...

引用

1993 IEEE International Conference on Acoustics, Speech, and Signal Processing

作者： B. Wang D.M. Rose A.A. Farag E.J. Delp Engineering Mathematics & Computer Science Department Speed Scientific School University of Louisville Louisville KY USA Computer Vision & Image Processing Laboratory School of Electrical Engineering Purdue University West Lafayette IN USA

An empirical measure for the selection of the edge-enhancement Gaussian filter is developed. The Gaussian filter is specified by its standard deviation sigma ; the filter's spatial support is a function of sigma . An estimation procedure for sigma using Fourier analysis is described. The measure is easy to implement and is based totally on the image at hand. Experimental results suggest that this measure can be used as an aid in deciding the Gaussian filter's spatial support, which is needed to enhance the edges. Other equivalent bandwidth definitions can be used to obtain a measure of the frequency spread in the smoothed image (e.g., the mean-square bandwidth).< >

关键词： Gaussian processes Low pass filters Shape Filtering Frequency Mathematics computer science computer vision Image processing Image segmentation

来源：评论

学校读者我要写书评

暂无评论

On an optimal learning scheme for bidirectional associative memories

On an optimal learning scheme for bidirectional associative ...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： K. Shanmukh Y.V. Venkatesh Comput. Vision & Artificial Intelligence Lab. Inst. of Sci. Bangalore India Computer Vision and Artificial Intelligence Laboratory Department of Electrical Engineering Indian Institute of Science Bangalore India

An optimal learning scheme is proposed for a class of bidirectional associative memories (BAMs). This scheme, based on the perceptron learning algorithm, is motivated by the inadequacies/incompleteness of the weighted learning by global optimization, as derived by Wang et al. (1993). It is shown that the new scheme has superior properties: (1) Convergence to the correct solution, when it exists; and (2) A larger basin of attraction for the given set of patterns.

关键词： Neurons Neural networks Neurofeedback Learning Convergence Pattern recognition computer vision Artificial intelligence Laboratories Artificial neural networks

来源：评论

学校读者我要写书评

暂无评论

Analysis of crowd movements and densities in built-up environments using image processing

Analysis of crowd movements and densities in built-up enviro...

引用

IEE Colloquium on Image Processing for Transport Applications

作者： S.A. Velastin J.H. Yin A.C. Davies M.A. Vicencio-Silva R.E. Allsop A. Penn Vision and Robotics Laboratory (Department of Electronic and Electrical Engineering) King''s College UK Centre for Transport Studies University College London UK Bartlett Schol of Architecture University College London UK

Real-time monitoring of site usage in public areas subject to major crowd movements relies on human observers with limited attention span and varying reliability. It is essential to investigate techniques to acquire crowd data and features automatically first, as part of the data gathering process, to develop realistic models for planning and designing pedestrian facilities in urban areas and, secondly, as online systems to detect problems in crowd movement before or shortly after they occur, using existing CCTV systems wherever possible. Such studies could lead to improved site designs, management procedures, public safety and reduced operating costs. Image processing techniques applicable to the measurement of density and motion in crowded scenes have therefore been presented. These give results comparable to human observers with potential for real-time implementation. Detailed studies of site usage and real-time operation then become feasible.< >

关键词： Image processing Safety

来源：评论

学校读者我要写书评

暂无评论

TRANSFORMATION RELATIONSHIPS FOR 2 COMMONLY UTILIZED EULER ANGLE REPRESENTATIONS

引用

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS 1992年第3期22卷 555-559页

作者： CHEN, CX TRIVEDI, MM Computer Vision and Robotics Research Laboratory Department of Electrical and Computer Engineering University of Tennessee Knoxville TN USA

There is no standard representation scheme that is followed by different groups of robot designers to describe the orientation of a rotating rigid body. For a sensor-based robot, the particular rotation representation scheme used by the robot affects not only the specification of the positioning of the arm and end-effector, but also the specification of the placement of the sensors and the method of computing the sensory-to-world transformation. Thus the need for finding the transformation between different rotation representations is obvious for one involved in the development of high-level software systems that need to be transported to different robots utilizing different rotation representation schemes. Among those representation schemes, Euler angle representations are widely used in commercial robots as well as in research laboratory robots. Typically, there are three different Euler angle representation systems, and each system describes a particular orientation of a rigid body in a reference coordinate frame by specifying three angles. Mathematical derivations of the transformation relationships underlying the parameters from two most commonly utilized representation schemes are presented. These relationships are derived in two different ways. One is based upon the solution of the inverse transform for Euler angles and the other is based upon the Napier's rules associated with spherical trigonometry.

关键词： Robot kinematics Robot sensing systems Manipulators Laboratories Quaternions US department of Energy Software systems Hardware Software standards Control systems

来源：评论

学校读者我要写书评

暂无评论

HERMITE-POLYNOMIALS FOR SIGNAL RECONSTRUCTION FROM ZERO-CROSSINGS .1. ONE-DIMENSIONAL SIGNALS

引用

IEE PROCEEDINGS-I COMMUNICATIONS SPEECH AND vision 1992年第6期139卷 587-596页

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

Generalised Hermite polynomials are employed for the reconstruction of an unknown signal from a knowledge of its zero-crossings, under certain conditions on its spatial/spectral width, but dispensing with the assumption of bandlimitedness. A computational implementation of the proposed method is given for one-variable (or one-dimensional) signals, featuring an application of simulated annealing for optimal reconstruction.

关键词： HERMITE POLYNOMIALS SIGNAL RECONSTRUCTION SIMULATED ANNEALING

来源：评论

学校读者我要写书评

暂无评论

A VLSI PROCESSOR FOR PARALLEL CONTOUR TRACING

引用

IEEE TRANSACTIONS ON SIGNAL PROCESSING 1992年第2期40卷 429-438页

作者： AGI, I HURST, PJ JAIN, AK Solid-state Circuits Research Laboratory Department of Electrical Engineering and Computer Science University of California Davis CA USA Computer Vision Research Laboratory Department of Electrical Engineering and Computer Science University of California Davis CA USA

A custom IC processor that traces contours in black-and-white images is described. The CMOS IC contains a finite state machine, ALU, input delay line, and RAM. Each processor extracts the edges from a rectangular portion of the input image and traces the edges, outputting a description of the contours. A complete tracing system employs an array of these processors. The array architecture allows expansion to handle arbitrarily large images. The processors trace independently, thereby providing fully parallel high-speed operation. Partial contours are generated as a result of the partitioning of the image among the processors. A postprocessor links any partial contours created by the subdivision of the input image. The contour-tracing algorithm and simulation results for compression ratio and number of operations are presented. The architecture and measured performance of the IC are described.

关键词： Very large scale integration Signal processing algorithms Read-write memory Automata Pixel CMOS integrated circuits Delay lines Partitioning algorithms Biomedical measurements

来源：评论

学校读者我要写书评

暂无评论

Multi-primitive hierarchical (MPH) stereo system

Multi-primitive hierarchical (MPH) stereo system

引用

1992 IEEE computer Society Conference on computer vision and Pattern Recognition, CVPR 1992

作者： Marapane, S.B. Trivedi, M.M. Computer Vision and Robotics Research Laboratory Department of Electrical and Computer Engineering University of Tennessee KnoxvilleTN37996-2100 United States

ISBN: (纸本)0818628553

A computational framework for an accurate, robust, and efficient stereo approach is developed. Most of the deficiencies prevailing in current computational models of stereo can be attributed to their use of a single, typically edge-element-based, primitive for stereo analysis and to their use of a single-level control strategy. The multi-primitive hierarchical (MPH) framework for stereo analysis presented is directed toward overcoming these deficiencies. In the MPH model, stereo analysis is performed in multiple stages, incorporating multiple primitives and utilizing a hierarchical control strategy. The higher levels of the hierarchical system are based on primitives containing more semantic information, and the results of stereo analysis at higher levels are used for guidance at the lower levels. It is shown that such a stereo system is superior to a single-level, single-primitive system. © 1992 IEEE.

关键词： Hierarchical systems

来源：评论

学校读者我要写书评

暂无评论

Active exploration using contact and noncontact sensors: An integrated system

Active exploration using contact and noncontact sensors: An ...

引用

1992 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 1992

作者： Gadagkar, H.P. Trivedi, M.M. Computer Vision and Robotics Research Laboratory Electrical and Computer Engineering Department University of Tennessee KnoxvilleTN37996-2100 United States

ISBN: (纸本)0780307372

In this paper we nzake an attempt to bring out the rationale that, for complex robotic applications, contact sensors can provide certain vital information quite easily as compared to non-contact sensors. We begin with describing and discussing our approach towards the development of a multi-sen,sory closed-loop active robotic exploration system for workspace characterization. The exploration system involves acquisition, processing, and integration of sensory inputs acquired from uision, poin,t laser range, tactile, and force/torque sensors. The exploration process results in building three-dimensional Half-space models of various polyhedral (convex and concave) objects encountered in the workspace. Subsequent to the process of building object models using active exploration mechanisms, the object models allow extraction of essential geometric information required for performing tasks such as object identification, grasping, and man ipiila t io n. Th e experim en tal resuh showtli at vurious geometrical descriptors that are required for model building, can be extracted quite reliably using the sensor specific exploratory mechanisms. © 1992 Institute of electrical and Electronics Engineers Inc. All rights reserved.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

Architecture and Automatic Task Planning for Integrated Sensor-based Robots

Architecture and Automatic Task Planning for Integrated Sens...

引用

1992 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 1992

作者： Chen, C. Trivedi, M.M. Computer Vision and Robotics Research Laboratory Electrical and Computer Engineering Department University of Tennessee KnoxvilleTN37996-2100 United States

ISBN: (纸本)0780307372

Intelligent robots interact with the real world by employing their advanced sensory mechanisms to perceive their environment, and their effectors and tools to change the state of their environment. Such intelligent robots should possess three important capabilities: (1) planning, i.e., given a goal, the ability to generate a set of task plans which will lead to achieving the goal, (2) coordination and execution of the perceptual actions, i.e., the abilities to coordinate sensors, acquire sensory data, and process, interpret and transform the sensory information, and (3) coordination and execution of the motor actions, i.e., the ability to navigate in their environments and the ability to coordinate effectors and tools and manipulate objects to accomplish assigned tasks. In this paper we introduce a System Architecture for Sensor-based Intelligent Robots, (SASIR), constructed using a frame data structure, which provides a suitable and flexible scheme for representation and manipulation of the world model, the sensor derived information, as well as for describing the actions reqnired for the execution of a specific task. © 1992 IEEE.

关键词： Intelligent robots

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：