检索结果-内蒙古大学图书馆

22nd IEEE Virtual Reality Conference (VR)

作者： Islam, A. B. M. Tariqul Scheel, Christian Pajarola, Renato Staadt, Oliver Univ Rostock Visual Comp Lab D-18055 Rostock Germany Univ Zurich Visualizat & MultiMedia Lab CH-8006 Zurich Switzerland

ISBN: (纸本)9781479917273

We propose a new method to fill missing or invalid values in depth images generated from the Kinect depth sensor. To fill the missing depth values, we use a robust least median of squares (LMedS) approach. We apply our method for telepresence environments, where Kinects are used very often for reconstructing the captured scene in 3D. We introduce a modified 1D LMedS approach for efficient traversal of consecutive image frames. Our approach solves the unstable nature of depth values in static scenes that is perceived as flickering. We obtain very good result both for static and moving objects inside a scene.

关键词： I.3.7 [computer graphics]: Three-Dimensional graphics and Realism [Virtual Reality] I.4.3 [image processing and computer Vision]: Enhancement

来源：评论

学校读者我要写书评

暂无评论

A computer Vision System for Automatic Classification of Most Consumed brazilian Beans 11th

A Computer Vision System for Automatic Classification of Mos...

引用

11th International symposium on Visual Computing (ISVC)

作者： Araujo, S. A. Alves, W. A. L. Belan, P. A. Anselmo, K. P. Univ Nove de Julho Informat & Knowledge Management Grad Program Sao Paulo Brazil

ISBN: (纸本)9783319278636;9783319278629

In this work we propose a computer vision system (CVS) for automatic classification of beans. It is able to classify the beans most consumed in Brazil, according to their skin colors and is composed by three main steps: (i) image acquisition and pre-processing, (ii) segmentation of grains and (iii) classification of grains. In the conducted experiments, we used an apparatus controlled by a PC that includes a conveyor belt, an image acquisition chamber and a camera, to simulate an industrial line of production. The results obtained in the experiments indicate that proposed system could be used to support the visual quality inspection of brazilian beans.

关键词： Beans Granulometry computer vision system

来源：评论

学校读者我要写书评

暂无评论

LeSSS: Learned Shared Semantic Spaces for Relating Multi-Modal Representations of 3D Shapes

引用

computer graphics FORUM 2015年第5期34卷 141-151页

作者： Herzog, Robert Mewes, Daniel Wand, Michael Guibas, Leonidas Seidel, Hans-Peter MPI Informat Comp Graph Dept Saarbrucken Germany Johannes Gutenberg Univ Mainz Inst Comp Sci Mainz Germany Stanford Univ Dept Comp Sci Stanford CA 94305 USA

In this paper, we propose a new method for structuring multi-modal representations of shapes according to semantic relations. We learn a metric that links semantically similar objects represented in different modalities. First, 3D-shapes are associated with textual labels by learning how textual attributes are related to the observed geometry. Correlations between similar labels are captured by simultaneously embedding labels and shape descriptors into a common latent space in which an inner product corresponds to similarity. The mapping is learned robustly by optimizing a rank-based loss function under a sparseness prior for the spectrum of the matrix of all classifiers. Second, we extend this framework towards relating multi-modal representations of the geometric objects. The key idea is that weak cues from shared human labels are sufficient to obtain a consistent embedding of related objects even though their representations are not directly comparable. We evaluate our method against common base-line approaches, investigate the influence of different geometric descriptors, and demonstrate a prototypical multi-modal browser that relates 3D-objects with text, photographs, and 2D line sketches.

关键词： Categories and Subject Descriptors (according to ACM CCS) computer graphics [I.3.5]: Computational Geometry and Object Modeling—Curve, surface, solid, and object representations Artificial Intelligence [I.2.10]: Vision and Scene Understanding— Shape image processing and computer Vision [I.4.8]: Scene Analysis—Object recognition multi-modal learning object recognition collaborative filtering 3D-shape descriptors semantic correspondences object retrieval

来源：评论

学校读者我要写书评

暂无评论

A Parallel Implementation of Data Fusion Algorithm Using Gamma 27

A Parallel Implementation of Data Fusion Algorithm Using Gam...

引用

IEEE 27th International symposium on computer Architecture and High Performance Computing

作者： Mello Junior, Rui R. de Almeida, Rubens H. P. Franca, Felipe M. G. Paillard, Gabriel A. L. Brazilian Navy Res Insitute Digital Syst Grp Rio De Janeiro RJ Brazil Univ Fed Rio de Janeiro Syst Engn & Comp Sci Program Rio De Janeiro RJ Brazil Univ Fed Ceara Virtual Univ Inst Fortaleza Ceara Brazil

ISBN: (纸本)9781467386210

In this paper we carried out designing and implementing of a target tracking data fusion algorithm based on a two stages graph solution using the computational model Gamma (General Abstract Model for Multiset mAnipulation). The proposed solution is the first parallel implementation of the method PPTS (Pairs of Plots in Two Stages). For this, we employed three Gamma implementations, where two of them exploited the resources of a parallel hardware environment, one using the MPI (Message Passing Interface) and the other one GPU (graphics processing Unit). Thus, the studied algorithm was evaluated from the parallelism exploited and finally was carried out a performance analysis of this algorithm in the three Gamma implementations used. The aim of this study is to provide an implementation on a real problem using for this the paradigm Gamma, which contributes to the implementations of the Gamma computational model, since it enables the performance analysis of these implementations and provides some suggestions for possible improvements. In addition, this work contributes to the PPTS method since it provides the parallelization of the first stage.

关键词： Data Fusion Gamma Parallel Programming

来源：评论

学校读者我要写书评

暂无评论

DjiNN and Tonic: DNN as a Service and Its Implications for Future Warehouse Scale computers 15

DjiNN and Tonic: DNN as a Service and Its Implications for F...

引用

ACM/IEEE 42nd Annual International symposium on computer Architecture (ISCA)

作者： Hauswald, Johann Kang, Yiping Laurenzano, Michael A. Chen, Quan Li, Cheng Mudge, Trevor Dreslinski, Ronald G. Mars, Jason Tang, Lingjia Univ Michigan Clar Lab Ann Arbor MI 48109 USA

ISBN: (纸本)9781450334020

As applications such as Apple Siri, Google Now, Microsoft Cortana, and Amazon Echo continue to gain traction, webservice companies are adopting large deep neural networks (DNN) for machine learning challenges such as image processing, speech recognition, natural language processing, among others. A number of open questions arise as to the design of a server platform specialized for DNN and how modern warehouse scale computers (WSCs) should be outfitted to provide DNN as a service for these applications. In this paper, we present DjiNN, an open infrastructure for DNN as a service in WSCs, and Tonic Suite, a suite of 7 end-to-end applications that span image, speech, and language processing. We use DjiNN to design a high throughput DNN system based on massive GPU server designs and provide insights as to the varying characteristics across applications. After studying the throughput, bandwidth, and power properties of DjiNN and Tonic Suite, we investigate several design points for future wsc architectures. We investigate the total cost of ownership implications of having a WSC with a disaggregated GPU pool versus a WSC composed of homogeneous integrated GPU servers. We improve DNN throughput by over 120X for all but one application (40X for Facial Recognition) on an NVIDIA K40 GPu. On a GPU server composed of 8 NVIDIA K40s, we achieve near-linear scaling (around 1000X throughput improvement) for 3 of the 7 applications. Through our analysis, we also find that GPU-enabled WSCs improve total cost of ownership over CPU-only designs by 4-20X, depending on the composition of the workload.

关键词： Total Cost Of Ownership GRAPPER PICK UP graphics processing Unit Servers WAREHOUSE Facial Recognition Legal Services Throughput computers Language processing Scale formation

来源：评论

学校读者我要写书评

暂无评论

Parallel Unsteady Flow Line Integral Convolution for High-Performance Dense Visualization 8

Parallel Unsteady Flow Line Integral Convolution for High-Pe...

引用

IEEE Pacific Visualization symposium (PacificVis)

作者： Ding, Zi'ang Liu, Zhanping Yu, Yang Chen, Wei Purdue Univ Dept Comp Sci W Lafayette IN 47907 USA Kentucky State Univ Div Comp Sci Frankfort KY USA Zhejiang Univ State Key Lab CAD&CG Hangzhou Zhejiang Peoples R China

ISBN: (纸本)9781467368797

This paper presents an accurate parallel implementation of unsteady flow line integral convolution (UFLIC) for high-performance visualization of large time-varying flows. Our approach differs from previous implementations by using a novel value scattering+gathering mechanism to parallelize UFLIC and designing a pathline reuse strategy to reduce the computational cost of pathline integration. By exploiting the massive parallelism of modern graphical processing units (GPU), the proposed method allows for real-time dense visualization of unsteady flows with high spatial-temporal coherence.

关键词： I.3.3 [computer graphics]: Pictures / image Generation

来源：评论

学校读者我要写书评

暂无评论

11th International symposium on Advances in Visual Computing, ISVC 2015

11th International Symposium on Advances in Visual Computing...

引用

11th International symposium on Advances in Visual Computing , ISVC 2015

ISBN: (纸本)9783319278629

The proceedings contain 79 papers. The special focus in this conference is on Applications, computer Vision, computer graphics, Segmentation and Biometrics. The topics include: Hybrid example-based single image super-resolution;conductor tutoring using the Microsoft kinect;lens distortion rectification using triangulation based interpolation;a computer vision system for automatic classification of most consumed brazilian beans;stereo-matching in the context of vision-augmented vehicles;a real-time depth estimation approach for a focused plenoptic camera;range image processing for real time hospital-room monitoring;stereo correspondence evaluation methods;user-assisted inverse procedural facade modeling and compressed image rendering;facial fattening and slimming simulation based on skull structure;many-lights real time global illumination using sparse voxel octree;a parallel rigid body simulation framework for web applications;a Markov random field and active contour image segmentation model for animal spots patterns;effective information and contrast based saliency detection;edge based segmentation of left and right ventricles using two distance regularized level sets;automatic crater detection using convex grouping and convolutional neural networks;segmentation of Saimaa ringed seals for identification purposes;fingerprint matching with optical coherence tomography;improve non-graph matching feature-based face recognition performance by using a multi-stage matching strategy;neighbors based discriminative feature difference learning for kinship verification;a comparative analysis of two approaches to periocular recognition in mobile scenarios;visual perception and analysis as first steps toward human-robot chess playing and automatic verification of properly signed multi-page document images.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Texture Mapping Real-World Objects with Hydrographics

引用

computer graphics FORUM 2015年第5期34卷 65-75页

作者： Panozzo, Daniele Diamanti, Olga Paris, Sylvain Tarini, Marco Sorkine, Evgeni Sorkine-Hornung, Olga Swiss Fed Inst Technol Zurich Switzerland Univ Insubria Varese Italy CNR ISTI I-56100 Pisa Italy

In the digital world, assigning arbitrary colors to an object is a simple operation thanks to texture mapping. However, in the real world, the same basic function of applying colors onto an object is far from trivial. One can specify colors during the fabrication process using a color 3D printer, but this does not apply to already existing objects. Paint and decals can be used during post-fabrication, but they are challenging to apply on complex shapes. In this paper, we develop a method to enable texture mapping of physical objects, that is, we allow one to map an arbitrary color image onto a three-dimensional object. Our approach builds upon hydrographics, a technique to transfer pigments printed on a sheet of polymer onto curved surfaces. We first describe a setup that makes the traditional water transfer printing process more accurate and consistent across prints. We then simulate the transfer process using a specialized parameterization to estimate the mapping between the planar color map and the object surface. We demonstrate that our approach enables the application of detailed color maps onto complex shapes such as 3D models of faces and anatomical casts.

关键词： Three Dimensions Color Printing color image Surjective Texture mapping CURVES (GEOMETRY) Fabrication process Paint Water transfer

来源：评论

学校读者我要写书评

暂无评论

Portable lensless wide-field microscopy imaging platform based on digital inline holography and multi-frame pixel super-resolution

引用

Light(Science & Applications) 2015年第1期4卷 152-162页

作者： Antonio C Sobieranski Fatih Inci H Cumhur Tekin Mehmet Yuksekkaya Eros Comunello Daniel Cobra Aldo von Wangenheim Utkan Demirci Demirci Bio-Acoustic-MEMS in Medicine(BAMM)Laboratory Division of Biomedical EngineeringDivision of Renal MedicineDepartment of MedicineBrigham and Women’s HospitalHarvard Medical SchoolBostonMAUSA Demirci Bio-Acoustic-MEMS in Medicine(BAMM)Laboratory Division of Infectious DiseasesBrigham and Women’s HospitalHarvard Medical SchoolBostonMAUSA INCoD–National Brazilian Institute for Digital Convergence/LAPIX Image Processing and Computer Graphics LabFederal University of Santa CatarinaBrazil Demirci Bio-Acoustic-MEMS in Medicine(BAMM)Laboratory Stanford University School of MedicineCanary Center at Stanford for Cancer Early DetectionPalo AltoCAUSA Present Address:Department of Biomedical Engineering Faculty of Engineering Bas¸kent UniversityAnkaraTurkey VisionLab Master in Applied ComputingUniversity of Itajaı´ValleyBrazil CERTI Foundation FlorianopolisBrazil

In this paper,an irregular displacement-based lensless wide-field microscopy imaging platform is presented by combining digital in-line holography and computational pixel super-resolution using multi-frame *** samples are illuminated by a nearly coherent illumination system,where the hologram shadows are projected into a complementary metal-oxide semiconductor-based imaging *** increase the resolution,a multi-frame pixel resolution approach is employed to produce a single holographic image from multiple frame observations of the scene,with small planar *** are resolved by a hybrid approach:(i)alignment of the LR images by a fast feature-based registration method,and(ii)fine adjustment of the sub-pixel information using a continuous optimization approach designed to find the global optimum *** method for phase-retrieval is applied to decode the signal and reconstruct the morphological details of the analyzed *** presented approach was evaluated with various biological samples including sperm and platelets,whose dimensions are in the order of a few *** obtained results demonstrate a spatial resolution of 1.55 μm on a field-of-view of<30 mm^(2).

关键词： digital in-line holography image registration lensless imaging point-of-care platform pixel super-resolution

来源：评论

学校读者我要写书评

暂无评论

Applying Feature Integration Theory to Glyph-based Information Visualization 8

Applying Feature Integration Theory to Glyph-based Informati...

引用

IEEE Pacific Visualization symposium (PacificVis)

作者： Cai, Zhuang Li, Yi-Na Zheng, Xianjun Sam Zhang, Kang Tianjin Univ Sch Comp Software Tianjin 300072 Peoples R China Nankai Univ Sch Business Tianjin 300072 Peoples R China Tsinghua Univ Dept Psychol Beijing 100084 Peoples R China Chinese Acad Sci Inst Software State Key Lab Comp Sci Beijing 100190 Peoples R China

ISBN: (纸本)9781467368797

Feature integration theory, the classic visual attention model, provides a theoretical foundation for optimizing visual communication. This paper proposes a set of glyphs named RoseShape that aim at improving users' visual information search in visualization. RoseShapes integrate rich and easy-to-catch attributes for mapping data variables, enabling automatic and unconscious information processing in the pre-attentive stage. A case study illustrating the levels of education funding in the United States in 2008 validates the feasibility of this approach.

关键词： H.5.0 [Information Systems]: Information Interfaces and Presentation - General I.3.3 [Computing Methodologies]: computer graphics - Pictrue/image Generation

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：