检索结果-内蒙古大学图书馆

Joint 34th Symposium of the German Association for Pattern Recognition, DAGM 2012 and 36th Symposium of the Austrian Association for Pattern Recognition, OAGM 2012

作者： Schroers, Christopher Zimmer, Henning Valgaerts, Levi Bruhn, Andrés Demetz, Oliver Weickert, Joachim Mathematical Image Analysis Group Faculty of Mathematics and Computer Science Saarland University Saarbrücken 66041 Germany Computer Graphics Laboratory Department of Computer Science ETH Zurich Zurich 8092 Switzerland Max-Planck-Institut für Informatik Campus E1.4 Saarbrücken 66123 Germany Institute for Visualization and Interactive Systems University of Stuttgart Universitätsstraße 38 70569 Stuttgart Germany

ISBN: (纸本)9783642327162

Obtaining high-quality 3D models of real world objects is an important task in computer vision. A very promising approach to achieve this is given by variational range image integration methods: They are able to deal with a substantial amount of noise and outliers, while regularising and thus creating smooth surfaces at the same time. Our paper extends the state-of-the-art approach of Zach et al.(2007) in several ways: (i) We replace the isotropic space-variant smoothing behaviour by an anisotropic (direction-dependent) one. Due to the directional adaptation, a better control of the smoothing with respect to the local structure of the signed distance field can be achieved. (ii) In order to keep data and smoothness term in balance, a normalisation factor is introduced. As a result, oversmoothing of locations that are seen seldom is prevented. This allows high quality reconstructions in uncontrolled capture setups, where the camera positions are unevenly distributed around an object. (iii) Finally, we use the more accurate closest signed distances instead of directional signed distances when converting range images into 3D signed distance fields. Experiments demonstrate that each of our three contributions leads to clearly visible improvements in the reconstruction quality. © 2012 Springer-Verlag.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Towards a laboratory instrument for motion analysis 81

Towards a laboratory instrument for motion analysis

引用

8th Annual Conference on computer graphics and Interactive Techniques, SIGGRAPH 1981

作者： Baecker, Ronald Miller, David Reeves, William Dynamic Graphics Project Department of Computer Science Computer Systems Research Group University of Toronto TorontoON Canada Human Computing Resources Corporation Toronto Canada Micom Co. Montreal Canada Sprocket Systems Lucasfilm San AnselmoCA United States

ISBN: (纸本)0897910451

Motion analysis is the systematic and usually quantitative study of the movements of humans, animals, organisms, cells, or other entities as recorded on movie film or video tape. Despite the utility of computer-aided motion analysis to many biological, social, and physical sciences, its role has been limited because it is so time-consuming and so expensive. Automated techniques can only be used-on real images in very special cases;interactive techniques have involved laborious frame by frame operations. In recent years, Futrelle and Potel have revolutionized the process of interactive motion analysis by demonstrating how to digitize entire motions with a single sketch rather than with a sequence of operations on each constituent frame. However, their GALA-TEA system is applicable only to film and not to video tape records, and consists of equipment which cannot easily be engineered into a reliable and mass-producible laboratory instrument. The paper describes a prototype laboratory instrument for the interactive motion analysis of video tape records. The prototype includes a host PDP 11/45 computer, an experimental display processor called SPIWRIT, and a microprocessor-controlled video disk. SPIWRIT generates a computer-animated video representation of the phenomenon being analysed, and superimposes it on the actual video record being streamed from the video disk. SPIWRIT's bit-slice microprogrammable display processor produces true animation on a colour raster display by decoding segmented display file images into alternate halves of a double frame buffer. © 1981 ACM.

关键词： Motion analysis

来源：评论

学校读者我要写书评

暂无评论

Visual Analysis of Point Cloud Neighborhoods via Multi-Scale Geometric Measures

Visual Analysis of Point Cloud Neighborhoods via Multi-Scale...

引用

42nd Annual Conference on European Association for computer graphics, EUROgraphics 2021

作者： Ritter, M. Schiffner, D. Harders, M. Interactive Graphics and Simulation Group The Department of Computer Science University of Innsbruck Austria DIPF Leibniz Institute for Research and Information Education Frankfurt Germany Airborne Hydromapping GmbH Innsbruck Austria

ISBN: (纸本)9783038681335

Point sets are a widely used spatial data structure in computational and observational domains, e.g. in physics particle simulations, computer graphics or remote sensing. Algorithms typically operate in local neighborhoods of point sets, for computing physical states, surface reconstructions, etc. We present a visualization technique based on multi-scale geometric features of such point clouds. We explore properties of different choices on the underlying weighted co-variance neighborhood descriptor, illustrated on different point set geometries and for varying noise levels. The impact of different weighting functions and tensor centroids, as well as point set features and noise levels becomes visible in the rotation-invariant feature images. We compare to a curvature based scale space visualization method and, finally, show how features in real-world LiDAR data can be inspected by images created with our approach in an interactive tool. In contrast to the curvature based approach, with our method line structures are highlighted over growing scales, with clear border regions to planar or spherical geometric structures. © 2021 The Author(s).

关键词： Data visualization

来源：评论

学校读者我要写书评

暂无评论

visualization of Biomolecular Structures: State of the Art 17

Visualization of Biomolecular Structures: State of the Art

引用

17th Eurographics Conference on visualization - State of the Art Reports, EuroVis-STAR 2015

作者： Kozlíková, B. Krone, M. Lindow, N. Falk, M. Baaden, M. Baum, D. Viola, I. Parulek, J. Hege, H.-C. Faculty of Informatics Masaryk University Czech Republic Visualization Research Center University of Stuttgart Germany Department of Visual Data Analysis Zuse Institute Berlin Germany Immersive Visualization Group Linköping University Sweden Laboratoire de Biochimie Théorique UPR 9080 CNRS France Department of Informatics University of Bergen Norway Institute of Computer Graphics and Algorithms Vienna University of Technology Austria

ISBN: (纸本)9783905674996

Structural properties of molecules are of primary concern in many fields. This report provides a comprehensive overview on techniques that have been developed in the fields of molecular graphics and visualization with a focus on applications in structural biology. The field heavily relies on computerized geometric and visual representations of three-dimensional, complex, large, and time-varying molecular structures. The report presents a taxonomy that demonstrates which areas of molecular visualization have already been extensively investigated and where the field is currently heading. It discusses visualizations for molecular structures, strategies for efficient display regarding image quality and frame rate, covers different aspects of level of detail, and reviews visualizations illustrating the dynamic aspects of molecular simulation data. The report concludes with an outlook on promising and important research topics to enable further success in advancing the knowledge about interaction of molecular structures. © The Eurographics Association 2015.

关键词： visualization

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Web-Based Toolkit for Human Modeling

A Hybrid Web-Based Toolkit for Human Modeling

引用

IEEE Scientific visualization Conference (SciVis)

作者： M. Bender R. Klein A. Ebert H. Rodrian Computer Graphics Group Department of Computer Science University of Kaiserslautern Germany Human Modeling Department TECMATH GmbH and Company KG Kaiserslautern Germany Intelligent Visualization and Simulation Systems German Research Center for Artificial Intelligence Germany

Modern web-based Scientific visualization applications try to overcome common limitations imposed by limited internet bandwidth, server bottlenecks or network latency. A further aspect is the desire to gain platform independence by solely using instruments which are platform independent by conception: the programming language Java, the Virtual Reality Modeling Language (VRML), or the 3D API *** present a prototype of a hybrid web-based Scientific visualization system which makes use of the increasing computational power of modern desktop workstations and personal computers on the client side, and the superior performance provided by a powerful machine on the server side. In order to achieve high interaction rates and to balance computational load the user can dynamically assign selected tasks to his client or to the *** the scientific field of human modeling we have implemented a hybrid web-based toolkit for the modeling of human muscles and skin. Our application allows the on-line generation and manipulation of three-dimensional implicit muscle models in a heterogeneous network and it offers various parameters to adjust computation and response time versus rendering quality.

关键词： Humans visualization Delay Java Muscles IP networks Bandwidth Network servers Web server Performance gain

来源：评论

学校读者我要写书评

暂无评论

Delaunay/sup MM/: a visual framework for multimedia presentation

Delaunay/sup MM/: a visual framework for multimedia presenta...

引用

IEEE Symposium on Visual Languages

作者： I.F. Cruz W.T. Lucas Department of Computer Science Worcester Polytechnic Institute USA Database Visualization Research Group Tufts University USA

We introduce a visualization framework called Delaunay/sup MM/ for querying and presenting multimedia information in distributed databases. Users can tailor the layout of virtual documents containing multimedia information at the same time as they specify their contents in an intuitive yet formal way, using a Web-available interface. The data model that we propose is object-oriented, and the query and presentation languages are declarative and incorporate layout constraints. Our framework encompasses the retrieval of heterogeneous distributed information whose data model does not need to conform to the one used by Delaunay/sup MM/.

关键词： Visual databases Object oriented databases Multimedia databases Data visualization Distributed databases Spatial databases Data models Information retrieval Database languages Image databases

来源：评论

学校读者我要写书评

暂无评论

Progressive parallel coordinates

Progressive parallel coordinates

引用

Pacific (formerly Asia-Pacific APVIS) visualization Symposium

作者： René Rosenbaum Jian Zhi Bernd Hamann Visual Computing and Computer Graphics group (VCG) Institute for Computer Science University of Rostock Rostock Germany Institute for Data Analysis and Visualization (IDAV) Department of Computer Science University of California Davis CA USA Department of Industrial Engineering and Operations Research Columbia University NY USA

Progressive refinement is a methodology that makes it possible to elegantly integrate scalable data compression, access, and presentation into one approach. Specifically, this paper concerns the effective use of progressive parallel coordinates (PPCs), utilized routinely for high-dimensional data visualization. It discusses how the power of the typical stages of progressive data visualization can also be utilized fully for PPCs. Further, different implementations of the underlying methods and potential application domains are described. The paper also presents empirical results concerning the benefits of PPC with regard to efficient data management and improved presentation, indicating that the proposed approach is able to close the gap between data handling and visualization.

关键词： Lead visualization Logic gates

来源：评论

学校读者我要写书评

暂无评论

Pose-invariant face alignment with a single CNN

arXiv

引用

arXiv 2017年

作者： Jourabloo, Amin Ye, Mao Liu, Xiaoming Ren, Liu Department of Computer Science and Engineering Michigan State University Visualization Group Bosch Research and Technology Center North America

Face alignment has witnessed substantial progress in the last decade. One of the recent focuses has been aligning a dense 3D face shape to face images with large head poses. The dominant technology used is based on the cascade of regressors, e.g., CNN, which has shown promising results. Nonetheless, the cascade of CNNs suffers from several drawbacks, e.g., lack of end-to-end training, handcrafted features and slow training speed. To address these issues, we propose a new layer, named visualization layer, that can be integrated into the CNN architecture and enables joint optimization with different loss functions. Extensive evaluation of the proposed method on multiple datasets demonstrates state-of-the-art accuracy, while reducing the training time by more than half compared to the typical cascade of CNNs. In addition, we compare multiple CNN architectures with the visualization layer to further demonstrate the advantage of its utilization. Copyright © 2017, The Authors. All rights reserved.

关键词： visualization

来源：评论

学校读者我要写书评

暂无评论

Communication via eye blinks and eyebrow raises: Video-based human-computer interfaces

引用

Universal Access in the Information Society 2003年第4期2卷 359-373页

作者： Grauman, K. Betke, M. Lombardi, J. Gips, J. Bradski, G.R. Vision Interface Group AI Laboratory Massachusetts Institute of Technology 77 Massachusetts Avenue CambridgeMA02139 United States Computer Science Department Boston University 111 Cummington St BostonMA02215 United States EagleEyes Computer Science Department Boston College Fulton Hall Chestnut HillMA02467 United States Vision Graphics and Pattern Recognition Microcomputer Research Laboratory Intel Corporation SC12-303 2200 Mission College Blvd Santa ClaraCA95054-1537 United States

Two video-based human-computer interaction tools are introduced that can activate a binary switch and issue a selection command. "BlinkLink," as the first tool is called, automatically detects a user's eye blinks and accurately measures their durations. The system is intended to provide an alternate input modality to allow people with severe disabilities to access a computer. Voluntary long blinks trigger mouse clicks, while involuntary short blinks are ignored. The system enables communication using "blink patterns:" sequences of long and short blinks which are interpreted as semiotic messages. The second tool, "EyebrowClicker," automatically detects when a user raises his or her eyebrows and then triggers a mouse click. Both systems can initialize themselves, track the eyes at frame rate, and recover in the event of errors. No special lighting is required. The systems have been tested with interactive games and a spelling program. Results demonstrate overall detection accuracy of 95.6% for BlinkLink and 89.0% for EyebrowClicker. © Springer-Verlag 2003.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Guest editors' introduction: Special section on IEEE PacificVis 2019

IEEE Pacific Visualization Symposium

引用

IEEE Pacific visualization Symposium 2019年 2019-April卷 XIV-XV页

作者： Maciejewski, Ross Seo, Jinwook Westermann, Rüdiger School of Computing Informatics and Decision Systems Engineering Arizona State University TempeAZ United States Department of Computer Science and Engineering Seoul National University Seoul Korea Republic of Computer Graphics and Visualization Group Technische Universitat Munchen Garching Germany

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：