检索结果-内蒙古大学图书馆

A hamiltonian approach to the eikonal equation 2nd

2nd International Workshop on Energy Minimization Methods in computer vision and Pattern Recognition, EMMCVPR 1999

作者： Siddiqi, Kaleem Tannenbaum, Allen Zucker, Steven W. School of Computer Science and Center for Intelligent Machines McGill University McGill University 3480 University Street MontréalPQH3A 2A7 Canada Department of Electrical and Computer Engineering University of Minnesota University of Minnesota 200 Union Street S. E MinneapolisMN55455 United States Department of Computer Science and Center for Computational Vision and Control Yale University Yale University New HavenCT06520-8285 United States

ISBN: (纸本)3540662944

The eikonal equation and variants of it are of significant interest for problems in computer vision and image processing. It is the basis for continuous versions of mathematical morphology, stereo, shapefrom-shading and for recent dynamic theories of shape. Its numerical simulation can be delicate, owing to the formation of singularities in the evolving front, and is typically based on level set methods introduced by Osher and Sethian. However, there are more classical approaches rooted in Hamiltonian physics, which have received little consideration in the computer vision literature. Here the front is interpreted as minimizing a particular action functional. In this context, we introduce a new algorithm for simulating the eikonal equation, which offers a number of computational advantages over the earlier methods. In particular, the locus of shocks is computed in a robust and efficient manner. We illustrate the approach with several numerical examples. © Springer-Verlag Berlin Heidelberg 1999.

关键词： Mathematical morphology

来源：评论

学校读者我要写书评

暂无评论

Task specification and monitoring for uncalibrated hand/eye coordination

Task specification and monitoring for uncalibrated hand/eye ...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Z. Dodds G.D. Hager A.S. Morse J.P. Hespanha Center for Computational Vision and Control Yale University New Heaven CT USA Department of Electrical Engineering University of California Berkeley Berkeley CA USA

Most of the work in robotic manipulation and visual servoing has emphasized how to specify and perform particular tasks. Recent results have formally shown what tasks are possible with uncalibrated imaging systems. This paper extends those results by characterizing in a constructive manner the set of tasks which can be performed with different types of uncalibrated camera models. The tasks resulting structure provides a principle foundation both for a specification language and for automatic execution monitoring in uncalibrated environments.

关键词： Cameras Robot vision systems Robot kinematics Specification languages Robustness computer vision Computed tomography Visual servoing computerized monitoring Robotics and automation

来源：评论

学校读者我要写书评

暂无评论

Model-based 3D object tracking using projective invariance

Model-based 3D object tracking using projective invariance

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Sung-Woo Lee Bum-Jae You G.D. Hager Intelligent System Control Research Center Korea Institute of Science and Technology Seoul South Korea Department of Computer Science Yale University New Heaven CT USA

This paper describes a method of 3D object tracking by projective invariance. Usually, projective invariance has been used for object recognition and its property discards the need for cumbersome camera calibration to obtain metric information. We focus on the fact the projective invariance is not only regarded as recognition cues but also able to verify, the status of a 3D object for visual tracking. With projective invariance relevant to points, we develop a fast and reliable visual tracking strategy by combining a recognition module using projective invariance, window-based corner trackers for object's center tracking and a visibility checking module. The proposed method is experimented in single IBM-PC platform successfully.

关键词： Object oriented modeling Cameras Optical filters Calibration Image motion analysis Target tracking Intelligent systems Intelligent control control systems computer science

来源：评论

学校读者我要写书评

暂无评论

Bas-relief ambiguity

引用

International Journal of computer vision 1999年第1期35卷 33-44页

作者： Belhumeur, Peter N. Kriegman, David J. Yuille, Alan L. Center for Comp. Vision and Control Dept. of Electrical Engineering Yale University New Haven CT 06520 United States Beckman Institute Department of Computer Science Univ. of Illinois Urbana-Champaign Urbana IL 61801 United States Smith-Kettlewell Eye Res. Institute San Francisco CA 94115 United States

When an unknown object with Lambertian reflectance is viewed orthographically, there is an implicit ambiguity in determining its 3-d structure: we show that the object's visible surface f(x, y) is indistinguishable from a `generalized bas-relief' transformation of the object's geometry, f¯(x, y) = λf(x, y)+μx+vy, and a corresponding transformation on the object's albedo. For each image of the object illuminated by an arbitrary number of distant light sources, there exists an identical image of the transformed object illuminated by similarly transformed light sources. This result holds both for the illuminated regions of the object as well as those in cast and attached shadows. Furthermore, neither small motion of the object, nor of the viewer will resolve the ambiguity in determining the flattening (or scaling) λ of the object's surface. Implications of this ambiguity on structure recovery and shape representation are discussed.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Three-dimensional pose determination for a humanoid robot using binocular head system

Three-dimensional pose determination for a humanoid robot us...

引用

IEEE International Workshop on Intelligent Robots and Systems (IROS)

作者： Hong-Jae Kim Bum-Jae You G.D. Hager Sang-Rok Oh Chong Won Lee Display Division Information & Home Appliances Business Samsung Electronics Company Limited Suwon Kyunggi South Korea Intelligent System Control Research Center Korea Institute of Science and Technology Seoul South Korea Department of Computer Science Yale University New Heaven CT USA

There has been much interests on three-dimensional pose estimation of an object since there are a lot of robotic applications such as intelligent robotic assembly and/or vision-guided control of a humanoid or human-friendly robot. In this paper, there are proposed a simple and fast stereo matching algorithm for real-time robotic applications and an improved scheme for feature matching using three-dimensional information by adopting backprojection as a feedback element measuring the degree of feature matching. The degree of feature matching is determined by checking existence ratio of each feature point in real images after back-projecting an object model into image plane. The proposed pose determination algorithm is applied for a humanoid robot in KIST, whose name is CENTAUR, successfully and determine the pose of several polyhedral objects using 3D information of vertexes on the outline of an object in image plane.

关键词： Humanoid robots Intelligent robots Robotic assembly Robot vision systems Image reconstruction Head Feedback Image recognition Three dimensional displays computer displays

来源：评论

学校读者我要写书评

暂无评论

Comparing images under variable illumination

Comparing images under variable illumination

引用

Conference on computer vision and Pattern Recognition (CVPR)

作者： D.W. Jacobs P.N. Belhumeur R. Basri NEC Research Institute Inc. Princeton NJ USA Center for Computational Vision & Control Yale University New Heaven CT USA Weizmann Institute of Science Rehovoth Israel

We consider the problem of determining whether two images come from different objects or the same object in the same pose, but under different illumination conditions. We show that this problem cannot be solved using hard constraints: even using a Lambertian reflectance model, there is always an object and a pair of lighting conditions consistent with any two images. Nevertheless, we show that for point sources and objects with Lambertian reflectance, the ratio of two images from the same object is simpler than the ratio of images from different objects. We also show that the ratio of the two images provides two of the three distinct values in the Hessian matrix of the object's surface. Using these observations, we develop a simple measure for matching images under variable illumination, comparing its performance to other existing methods on a database of 450 images of 10 individuals.

关键词： Lighting Reflectivity Shape Jacobian matrices National electric code computer vision Computed tomography Image databases Visual databases Object recognition

来源：评论

学校读者我要写书评

暂无评论

control of a rigid robot using an uncalibrated stereo vision system

Control of a rigid robot using an uncalibrated stereo vision...

引用

American control Conference (ACC)

作者： Wen-Chung Chang A.S. Morse Center for Computational Vision and Control Department of Electrical Engineering Yale University New Heaven CT USA

A supervisor of the estimator-based type together with a certainty equivalence control is proposed for controlling the position of a rigid robot in a prescribed workspace using data observed by two uncalibrated video cameras. By exploiting a well known algebraic relationship from the computer vision field (the epipolar constraint), the supervisor is able to falsify or eliminate over time, unpromising candidate camera models.

关键词： control systems Robot vision systems Stereo vision Cameras Robot kinematics Orbital robotics computer vision Jacobian matrices Uncertainty Linear systems

来源：评论

学校读者我要写书评

暂无评论

Area and length minimizing flows for shape segmentation

Area and length minimizing flows for shape segmentation

引用

Conference on computer vision and Pattern Recognition (CVPR)

作者： K. Siddiqi Y.B. Lauziere A. Tannenbaum S.W. Zucker Center forComputational Vision & Control Yale University USA Cent. for Intelligent Machines McGill University Canada Department of Electrical Engineering University of Minnesota USA Center for Computational Vision & Control Yale University USA

Several active contour models have been proposed to unify the curve evolution framework with classical energy minimization techniques for segmentation, such as snakes. The essential idea is to evolve a curve (in 2D) or a surface (in 3D) under constraints from image forces so that it clings to features of interest in an intensity image. Recently the evolution equation has been derived from first principles as the gradient flow that minimizes a modified length functional, tailored to features such as edges. However, because the flow may be slow to converge in practice, a constant (hyperbolic) term is added to keep the curve/surface moving in the desired direction. The authors provide a justification for this term based on the gradient flow derived from a weighted area functional, with image dependent weighting factor. When combined with the earlier modified length gradient flow they obtain a PDE which offers a number of advantages, as illustrated by several examples of shape segmentation on medical images. In many cases the weighted area flow may be used on its own, with significant computational savings.

关键词： Shape Active contours Equations computer vision Image segmentation Image converters Biomedical imaging Mathematical model Physics computational intelligence

来源：评论

学校读者我要写书评

暂无评论

Abstracts

引用

Environmental Management 1977年第1期1卷 67-96页

作者： Frankenfeld, John W. Schulz, Wolfgang McMurty, George J. Petersen, Gary W. May, G. A. Hering, F. S. Schwartz, J. I. Heywood, J. B. Chigier, N. A. Grohse, E. W. Walker, J. D. Colwell, R. R. Petrakis, L. Pergament, H. S. Thorpe, R. D. Schoepf, Richard W. Krzyczkowski, Roman Henneman, Suzanne S. Hudson, Charles L. Putnam, Evelyn S. Thiesen, Donna J. Parks, G. A. McCarty, Perry L. Leckie, J. O. Schrumpf, Barry J. Simonson, G. H. Paine, D. P. Lawrence, R. D. Pyott, W. T. Leh, M. Elders, W. Combs, J. Caplen, T. Harrison, F. L. Wong, K. M. Heft., R. E. Charnell, Robert L. Lehmann, Edward J. Mallon, Lawrence G. Hatfield, Cecile Adams, Gerald H. Johanning, James Talvitie, Antti Noll, Kenneth E. Miller, Terry Smiarowski, Joseph F. Willis, Cleve E. Foster, John H. Schlesinger, Benjamin Daetz, Douglas Lear, Donald U. Smith, Mona F. Hundemann, Audrey S. Crockett, Pernell W. Werner, Kirk G. Carroll, Thomas E. Maase, David L. Genco, Joseph E. Ifeadi, Christopher N. Lowman, F. G. Christensen, S. W. Van Winkle, W. Mattice, J. S. Harrison, Elizabeth A. Barker, James C. Chesness, Jerry L. Smith, Ralph E. Shaheeen, Donald G. Raney, R. Keith Borton, T. Wezernak, C. T. Raney, R. K. Sherwani, Jabbor K. Moreau, David H. Eisenberg, Norman A. Lynch, Cornelius J. Breeding, Roger J. Johnson, J. D. Foster, K. E. Mouat, D. A. Clark, R. Hyden, John William Owen, Wilfred Bayfield, Neil G. Barrow, Graham C. Stolz, Stephanie B. Wienckowski, Louis A. Brown, Betram S. Keyfitz, Nathan Wilson, W. L. Newman, Peter W. G. Bammi, Deepak Bammi, Dalip Goddard, James E. Chisholm, Tony Walsh, Cliff Brennan, Geoffrey Thompson, K. S. Richardson, R. Jensen, Clayton E. Brown, Dail W. Mirabito, John A. Cowing, Thomas G. Binghamton, Suny Siehl, George H. Albrecht, O. W. Alexander, Ariel Barde, Jean -Philippe Darby, William P. McMichael, Francis Clay Dunlap, Robert W. Muckleston, Keith W. Frankenhoff, Charles A. Giulini, Lorenzo T. Wyatt, T. Black, Peter E. Keating, William Thomas Leonard, M. E. Fisher, E. L. Brunelle, M. F. Dickinson, J. E. Pethig, Rudiger Clapham Exxon Research & Engineering Co. Linden Government Research Lab Coast Guard Washington D.C. Department of Transportation Washington D.C. Office For Remote Sensing of Earth Resources. NASA Earth Resources Survey Program Pennsylvania State University Washington D.C. Department of the Navy Washington D.C. Cambridge. Dept. of Mechanical Engineering Massachusetts Inst. of Technology USA Huntsville. School of Graduate Studies and Research Alabama Univ. USA Dept. of Microbiology. Office of Naval Research Maryland Univ. Arlington Research and Development Co. Pittsburgh AeroChem Research Labs. Inc. Princeton Dept. of the Interior Office of Library Services. Bibliographic Series (Final) Washington D.C. Interplan Corp. Santa Barbara Urban Mass Transportation Adm. Washington D.C. Naval Underwater Systems Center Newport Calif. Mercury Project. National Science Found Stanford Univ Washington D.C. Div. of Advanced Environmental Research & Tech. USA Corvallis. NASA Earth Resources Survey Program Oregon State Univ. Washington D.C. Riverside. Inst. of Geophysics and Planetary Physics National Science Foundation California Univ. Washington D.C. Livermore Lawrence Livermore Lab. California Univ. USA Atlantic Oceanographic and Meteorological Labs. National Oceanic and Atmospheric Administration Miami National Technical Information Service Springfield Miami Univ. Coral Gables School of Law National Oceanic and Atmospheric Administration Rockville National Academy of Sciences Office of Sea Grant Washington D. C. School of Law National Oceanic and Atmospheric Administration Office of Sea Grant. Rockville Norman. Dept. of Civil Engineering and Environmental Science. Urban Mass Transportation Administration Oklahoma Univ. Washington D. C. Knoxville.Dept. of Civil Engineering. Federal Highway Administration Tennessee Univ. Washington D. C. Amherst.Water Resources Research Center. Office of Water Research and Technology Massachusetts Univ. Washington D. C. Calif. Dept. of Industria

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：