检索结果-内蒙古大学图书馆

11th IEEE and ACM International symposium on Mixed and Augmented Reality (ISMAR)

作者： Herling, Jan Broll, Wolfgang Ilmenau Univ Technol Ilmenau Germany

ISBN: (纸本)9781467346627

Diminished Reality (DR) allows to remove objects from a video stream while preseving a frame to frame coherence. Some approaches apply a pseudo-DR, allowing for the removal of objects only, while their background can be observed by a second camera. Most real DR approaches are highly computational expensive, not even allowing for interactive rates and/or apply significant restrictions regarding the uniformity of the background, or allow linear camera movements or even a static camera only. In this paper we will present a real-time capable Diminished Reality approach for high-quality image manipulation. Our approach achieves a significantly better performance and image quality for almost planar but non-trivial image backgrounds. Our Diminished Reality pipeline provides coherent video streams even for nonlinear camera movements due to the integration of homography based object tracking.

关键词： H.5.1 [Information Interfaces and Presentation]: Multimedia Information Systems—Artificial augmente I.3.6 [Computing Methodologies]: computer graphics—Methodology and Techniques I.4.9 [Computing Methodologies]: image processing and computer Vision—Applications Reality camera movements homography DR coherence image quality Cameras

来源：评论

学校读者我要写书评

暂无评论

Analysis in sensibility of a motion detection algorithm for selecting noise reduction methods in x-ray image sequences

Analysis in sensibility of a motion detection algorithm for ...

引用

25th Conference on graphics, Patterns and images, SIBGRAPI 2012

作者： Silva, Lucas Souza E. Rocha, Filipe Ribeiro Amaral, Lorena Borges Carneiro, Cássio Alves Ferreira, Flávia Maglhães Freitas Peixoto, Zélia Myriam Assis Graduate Program in Electrical Engineering Pontifical Catholic University of Minas Gerais PUC Minas Belo Horizonte Brazil

ISBN: (纸本)9780769548296

The quantum noise, intrinsic to the acquisition of X-ray images, becomes more significant during the processes related to fluoroscopy due to its low signal to noise ratio. In this condition, and if there is presence of motion in the image sequence, the use of temporal filtering is restricted, because it will lead to the generation of traces in the resulting filtered images. This artifact can be minimized using purely spatial filtering on regions where motion has been detected. The combination of temporal filtering / spatial filtering results in the hybrid filtering, which is driven by a binary mask of motion detection and it is obtained from the analysis and classification of pixels, based on statistical properties of the image. In this sense, this article aims at contributing to the methods of motion detection, presenting new analyzes in the sensibility of a detection algorithm and tests with real images of X-ray examinations. Preliminary results indicate that the filtering process can be improved with the proper choice of parameters of the motion detection mask for different types of medical X-ray procedures, which differ fundamentally by the amount of relative movement among consecutive frames and the contrast among gray intensities in an image sequence, in relation to the static background. © 2012 IEEE.

关键词： Quantum noise

来源：评论

学校读者我要写书评

暂无评论

Ambient occlusion using cone tracing with scene voxelization

Ambient occlusion using cone tracing with scene voxelization

引用

25th Conference on graphics, Patterns and images, SIBGRAPI 2012

作者： Favera, Eduardo Ceretta Dalla Celes, Waldemar Tecgraf/PUC-Rio Computer Science Department Pontifical Catholic University of Rio de Janeiro Brazil

ISBN: (纸本)9780769548296

Ambient occlusion is a low-cost technique to simulate indirect ambient illumination in a realistic way. The goal is to estimate the amount of incident ambient light at each visible point. In this paper, we propose a novel ambient occlusion method that produces good quality results in real time. Using an efficient voxelization algorithm, we create a volumetric description of the scene geometry in a regular grid. During scene rendering, the hemisphere around each visible point is sampled by a set of cones, each one representing a package of rays. The volume of each cone is sampled by a series of spheres. The obstructed volumes of the spheres are used to estimate the amount of rays that are blocked by the scene geometry. The final ambient occlusion at each visible point is computed by considering all cones in the hemisphere. This approach has shown to be quite adequate: the intersection of each sphere with the voxelized scene is performed in a very efficient manner, and good quality results are achieved with a small number of cones. Computational experiments demonstrate the efficiency and effectiveness of our proposal. © 2012 IEEE.

关键词： Spheres

来源：评论

学校读者我要写书评

暂无评论

Digital preservation of brazilian indigenous artworks: Generating high quality textures for 3D models

引用

JOURNAL OF CULTURAL HERITAGE 2012年第1期13卷 28-39页

作者： Andrade, Beatriz Trinchao Pereira Bellon, Olga Regina Silva, Luciano Vrubel, Alexandre Univ Fed Parana UFPR IMAGO Res Grp BR-81531980 Curitiba Parana Brazil

Three-dimensional (3D) digital preservation aims at generating 3D models of objects that have cultural or scientific value. It allows realistic visualization of objects through virtual museums or scientific applications, and the restoration of the preserved object in case of natural wear or accidents. This work contributes to this research area by presenting a method to improve color texture quality of 3D models obtained from color and depth images of a laser scanner. Although this device offers precise depth information, the resulting color information is still poor and limits the generation of realistic textures. Our approach is to capture photographs of the object with a high-resolution digital camera and use them to generate a new color texture for the 3D model. Our work proposes a practical technique, easy to replicate, to generate high quality textures for 3D models from photographs. The method is composed by three main steps: (1) calibration of the image acquisition devices;(2) data acquisition;and (3) texture generation. In this paper, we detail our color texture generation method and apply it on the digital preservation of many artworks made by native brazilians (indians) from the Wauja and Karaja communities. These indigenous communities are acknowledged as great ceramic artists, each bearing their own main themes, using a very rich symbolism in their paintings. Their artworks represent important aspects of the native South American culture and their digital preservation is motivated by three main reasons: (1) their fragility;(2) the paintings loose their original appearance with time;and (3) the possibility of extinction of these communities. We present several results of preserved artworks with enhanced quality realistic texture maps. Also, we present a methodology to analyze the quality and accuracy of texture maps. The resulting 3D models can be visualized through a tool we developed to support the virtual exhibit of 3D preserved heritage. (C) 2011 Els

关键词： 3D digital preservation brazilian indigenous artworks Texture generation computer graphics image processing computer vision

来源：评论

学校读者我要写书评

暂无评论

DistributedCL: A framework for transparent distributed GPU processing using the OpenCL API

DistributedCL: A framework for transparent distributed GPU p...

引用

13th symposium on Computing Systems, WSCAD-SSC 2012

作者： Tupinambá, André Sztajnberg, Alexandre Programa de Engenharia Eletrônica - PEL Universidade Do Estado Do Rio de Janeiro - UERJ Rio de Janeiro Brazil Instituto de Matemática e Estatistica - IME Departamento de Informática e Ciência Da Computaç ão Universidade Do Estado Do Rio de Janeiro - UERJ Rio de Janeiro Brazil

ISBN: (纸本)9780769548470

This paper presents the DistributedCL, a framework that provides the applications developed using the OpenCL interface location-transparent GPU processing. The application can explore distributed processing with no modification. The architecture of the framework and the programming model are presented, and the possible performance bottlenecks are discussed. © 2012 IEEE.

关键词： graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Enhancing Virtual Natural Scenes using Quick and Dirty image Based Recipes

Enhancing Virtual Natural Scenes using Quick and Dirty Image...

引用

IEEE 4th International symposium on Plant Growth Modeling, Simulation, Visualization and Applications (PMA)

作者： Jaeger, Marc UMR AMAP GreenLab Amap CIRAD Montpellier France

ISBN: (纸本)9781467300704;9781467300674

computer generated scenes are getting popular in the scientific communities concerned by plant, crop and forest structural and functional modeling. We show that realistic images can be produced from scientific visualizations at low costs, with post-processing functions applied to output images with or without their associated depth maps. We illustrate the use of empirical quick and dirty image based functions to mimic weather conditions and photographic effects. 2D particle systems, depth gradient processes, image with depth maps composing, allow to mimic rain, snow deposit and depth of field effects. Giving moreover a viewing matrix, on restrictive hypothesis related to the view and the illumination, images can be added sky-domes, fake reflections among other process. Compared to existing tools (often complex), the application of these experimental recipes shows fast dedicated parametrization, easy to handle and apply, covering a wide range of applications from single plant to landscape levels, including small forest stands, at various seasons and day times.

关键词： computer graphics Natural phenomena Z-buffer Rendering image based post processing Weather visuals HDR DoF Shadows Sky-Dome Rain Snow Fog

来源：评论

学校读者我要写书评

暂无评论

WebMedia'12 - Proceedings of the 2012 brazilian symposium on Multimedia and the Web

WebMedia'12 - Proceedings of the 2012 Brazilian Symposium on...

引用

18th brazilian symposium on Multimedia and the Web, WebMedia 2012

ISBN: (纸本)9781450317061

The proceedings contain 66 papers. The topics discussed include: an architecture for multidimensional computer adaptive test with educational purposes;engineering device-spanning, multimodal web applications using a model-based design approach;OpenedEyes: developing an information visualization framework using web standards and open web technologies;use of information visualization and adaptive hypermedia techniques on content portals;ConnecTV: an environment to develop and run component-based customized iDTV applications;MDM-KTV: a conceptual framework for multi-data-models for operational, analytic, semantic and linked data based data organization;the knowledge as a service metaphor and its use for building convergence environments;multimedia presentation integrating interactive media produced in real time with high performance processing;and reducing the dimensionality of the SIFT descriptor and increasing its effectiveness and efficiency in image retrieval via bag-of-features.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multiscale AM-FM decompositions with GPU acceleration for diabetic retinopathy screening

Multiscale AM-FM decompositions with GPU acceleration for di...

引用

2012 IEEE Southwest symposium on image Analysis and Interpretation, SSIAI 2012

作者： Carranza, Cesar Murray, Victor Pattichis, Marios Barriga, E. Simon Electrical and Computer Engineering Department University of New Mexico Albuquerque NM 87131 United States Sección Electricidad y Electrónica Pontificia Universidad Católica del Perú Lima-32 Peru VisionQuest Biomedical Albuquerque NM 87106 United States

ISBN: (纸本)9781467318303

A computer Aided Diagnosis system based on multiscale amplitude-modulation frequency-modulation (AM-FM) methods has been recently developed for discriminating between normal and pathological retinal images. The original Matlab implementation of this system required large amounts of computational time and memory resources that would not permit real-time patient consultation. In this manuscript, we present a new implementation of the multiscale AM-FM decomposition, converted from MATLAB code into C/CUDA (Compute Unified Device Architecture) code, in order to take advantage of the graphics processing units (GPU) to significantly reduce the running time and memory resources. To perform the AM-FM decomposition at high speed, the original image is read into the main memory (host side, in the personal computer) and transferred to the global memory in the CUDA card (device side, the GPU), where the AMFM decomposition is computed at thirteen different frequency scales. The results are transferred back to the host and saved in the local hard drive. The intensive mathematical operations are parallelized to achieve maximum utilization of the CUDA card. This new implementation runs 20 times faster than an optimized, parallel implementation in MATLAB running on an personal computer with an Intel Xeon Processor W3520, and the memory requirement is reduced from 4GB to below 0.9GB for images of 2252 × 1996 pixels or smaller. The required resources for the new implementation can be found in entry-level CUDA cards that are currently available. © 2012 IEEE.

关键词： graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Dynamic Modeling of String for Robotics Application

Dynamic Modeling of String for Robotics Application

引用

6th International Conference on Soft Computing and Intelligent Systems (SCIS) / 13th International symposium on Advanced Intelligence Systems (ISIS)

作者： Sahari, Khairul Salleh Mohamed Min, Chew Han Hou, Yew Cheong Univ Tenaga Nas Ctr Adv Mechatron & Robot Jalan IKRAM UNITEN Kajang 43000 Selangor Malaysia

ISBN: (纸本)9781467327435;9781467327428

This paper presents the modeling of deformable objects within the computer graphics. The method to model a physically correct simulator using a mass spring model for string simulation is proposed. The outline of this project is to design a dynamic model of a string. The string t is represented by a model that discretizes the object into a network of interconnected particles, springs and damping elements. The motion of the string is calculated by using nonlinear partial different equations. Besides, a recognition method based on the image information obtained is used to identify the position of string the string particles. The pixel of the image will be recorded as an array in the memory and is converted into grayscale image. After that, several processes such as background elimination and binarization is used to identify the position of each particle. Based on the results obtained, it can be concluded that the mathematical model developed are capable to approximate the real string parameter. Therefore, through modeling, a real string parameter inside a model can be measured and approximated with ease through simulation. Thus, this can be used to design systems for robotics application which have not been manufactured for testing, handling and manipulation.

关键词： computer graphic mass spring model graphical user interface image processing

来源：评论

学校读者我要写书评

暂无评论

Auto-tuning methodology to represent landform attributes on multicore and multi-GPU systems

Auto-tuning methodology to represent landform attributes on ...

引用

13th symposium on Computing Systems, WSCAD-SSC 2012

作者： Boratto, Murilo Alonso, Pedro Giménez, Domingo Valencia Spain Murcia Spain

ISBN: (纸本)9780769548470

Auto-Tuning techniques have been used in the design of routines in recent years. The goal is to develop routines which automatically adapt to the conditions of the computational system, in such a way that efficient executions are obtained independently of the user's experience. This paper aims to explore programming routines that can be automatically adapted to the computational system conditions, making possible to use Auto-Tuning methodology to represent landform attributes on multicores and multi-GPU systems. © 2012 IEEE.

关键词： graphics processing unit

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：