Showing papers on "Graphics published in 2011"

Mobile Visual Search

Abstract: Mobile phones have evolved into powerful image and video processing devices equipped with high-resolution cameras, color displays, and hardware-accelerated graphics. They are also increasingly equipped with a global positioning system and connected to broadband wireless networks. All this enables a new class of applications that use the camera phone to initiate search queries about objects in visual proximity to the user (Figure 1). Such applications can be used, e.g., for identifying products, comparison shopping, finding information about movies, compact disks (CDs), real estate, print media, or artworks.

R in Action: Data Analysis and Graphics with R

Abstract: R is a powerful language for statistical computing and graphics that can handle virtually any data-crunching task It runs on all important platforms and provides thousands of useful specialized modules and utilities This makes R a great way to get meaningful information from mountains of raw data R in Action, Second Edition is a language tutorial focused on practical problems Written by a research methodologist, it takes a direct and modular approach to quickly give readers the information they need to produce useful results Focusing on realistic data analyses and a comprehensive integration of graphics, it follows the steps that real data analysts use to acquire their data, get it into shape, analyze it, and produce meaningful results that they can provide to clients Purchase of the print book comes with an offer of a free PDF eBook from Manning Also available is all code from the book

Assembly of finite element methods on graphics processors

Abstract: Recently, graphics processing units (GPUs) have had great success in accelerating many numerical computations. We present their application to computations on unstructured meshes such as those in finite element methods. Multiple approaches in assembling and solving sparse linear systems with NVIDIA GPUs and the Compute Unified Device Architecture (CUDA) are created and analyzed. Multiple strategies for efficient use of global, shared, and local memory, methods to achieve memory coalescing, and optimal choice of parameters are introduced. We find that with appropriate preprocessing and arrangement of support data, the GPU coprocessor using single-precision arithmetic achieves speedups of 30 or more in comparison to a well optimized double-precision single core implementation. We also find that the optimal assembly strategy depends on the order of polynomials used in the finite element discretization. Copyright © 2010 John Wiley & Sons, Ltd.

Visualize This: The FlowingData Guide to Design, Visualization, and Statistics

Abstract: Practical data design tips from a data visualization expert of the modern ageData doesn?t decrease; it is ever-increasing and can be overwhelming to organize in a way that makes sense to its intended audience. Wouldn?t it be wonderful if we could actually visualize data in such a way that we could maximize its potential and tell a story in a clear, concise manner? Thanks to the creative genius of Nathan Yau, we can. With this full-color book, data visualization guru and author Nathan Yau uses step-by-step tutorials to show you how to visualize and tell stories with data. He explains how to gather, parse, and format data and then design high quality graphics that help you explore and present patterns, outliers, and relationships.Presents a unique approach to visualizing and telling stories with data, from a data visualization expert and the creator of flowingdata.com, Nathan YauOffers step-by-step tutorials and practical design tips for creating statistical graphics, geographical maps, and information design to find meaning in the numbersDetails tools that can be used to visualize data-native graphics for the Web, such as ActionScript, Flash libraries, PHP, and JavaScript and tools to design graphics for print, such as R and IllustratorContains numerous examples and descriptions of patterns and outliers and explains how to show themVisualize This demonstrates how to explain data visually so that you can present your information in a way that is easy to understand and appealing. From the Author: Telling Stories with Data Author Nathan Yau A common mistake in data design is to approach a project with a visual layout before looking at your data. This leads to graphics that lack context and provide little value. Visualize This teaches you a data-first approach. Explore what your data has to say first, and you can design graphics that mean something. Visualization and data design all come easier with practice, and you can advance your skills with every new dataset and project. To begin though, you need a proper foundation and know what tools are available to you (but not let them bog you down). I wrote Visualize This with that in mind. You'll be exposed to a variety of software and code and jump right into real-world datasets so that you can learn visualization by doing, and most importantly be able to apply what you learn to your own data. Three Data Visualization Steps: 1) Ask a Question (Click Graphic to See Larger Version) When you get a dataset, it sometimes is a challenge figuring out where to start, especially when it's a large dataset. Approach your data with a simple curiosity or a question that you want answered, and go from there. 2) Explore Your Data (Click Graphic to See Larger Version) A simple curiosity often leads to more questions, which are a good guide for what stories to dig into. What variables are related to each other? Can you see changes over time? Are there any features in the data that stand out? Find out all you can about your data, because the more you know what's behind the numbers, the better story you can tell. 3) Visualize Your Data (Click Graphic to See Larger Version) Once you know the important parts of your data, you can design graphics the best way you see fit. Use shapes, colors, and sizes that make sense and help tell your story clearly to readers. While the base of your charts and graphs will share many of the same properties bars, slices, dots, and lines the final design elements will and should vary by your unique dataset.

Parallel Data Mining on Graphics Processors

Abstract: We introduce GPUMiner, a novel parallel data mining system that utilizes new-generation graphics processing units (GPUs). Our system relies on the massively multi-threaded SIMD (Single Instruction, Multiple-Data) architecture provided by GPUs. As specialpurpose co-processors, these processors are highly optimized for graphics rendering and rely on the CPU for data input/output as well as complex program control. Therefore, we design GPUMiner to consist of the following three components: (1) a CPU-based storage and buffer manager to handle I/O and data transfer between the CPU and the GPU, (2) a GPU-CPU co-processing parallel mining module, and (3) a GPU-based mining visualization module. We design the GPU-CPU co-processing scheme in mining depending on the complexity and inherent parallelism of individual mining algorithms. We provide the visualization module to facilitate users to observe and interact with the mining process online. We have implemented the k-means clustering and the Apriori frequent pattern mining algorithms in GPUMiner. Our preliminary results have shown significant speedups over state-of-the-art CPU implementations on a PC with a G80 GPU and a quad-core CPU. We will demonstrate the mining process through our visualization module. Code and documentation of GPUMiner are available at http://code.google.com/p/gpuminer/.

Comprehension of Graphics

Abstract: Part I. Graphical Codes and Graphics Processing. 1. Contributions of perceptual and cognitive processes to the comprehension of graphics (W. Winn). 2. Codes of instructional pictures (B. Wiedemann). 3. Spatial metaphors and logical pictures (A. Fenk). 4. Comprehending and using maps: Are there two modes of map processing? (J.R. Kirby). 5. Identifying and simulating cognitive strategies for the description of spatial networks (M. Denis, F. Robin, M. Zock, A. Laroui). Part II. Graphics and Mental Representations. 6. Representation and processing of the spatial layout of objects with verbal and nonverbal input (H.D. Zimmer). 7. Size in picture and text (J. Engelkamp, G. Mohr). 8. Visual aids to knowledge construction: Building mental representations from pictures and words (R.E. Mayer). 9. Illustrations, mental models, and comprehension of instructional text (Y. Gyselinck, H. Tardieu). 10. Reference maps as a framework for remembering text (R.W. Kulhavy, W.A. Stock, L.C. Caterino). Part III. Differential and Developmental Aspects. 11. The mnemonic benefit of pictures in text: Selective enrichment for differentially skilled readers (M.A. McDaniel, P.J. Waddill). 12. The use graphics and texts in constructing mental models (W. Schnotz, E. Picard, M. Henninger). 13. Cognitive processes in understanding line graphs (U. Maichle). 14. On children's understanding of an economic concept: The role of graphics in evaluation (C. Grobbo). 15. Visualized analogies and memory for new information in first graders (M.-D. Gineste). Part IV. Instructional Aspects. 16. The supplantation of mental images through graphics: Instructional effects on spatial visualization skills of adults (N.M. Seel, G. Doerr). 17. Enhancing graphic-effects in instructional texts: Influencing learning activities (J. Peeck). 18. Systematic forced processing of text and graphic information (P.J. Moore, J.J. Scevak). Concluding remarks. Author index. Subject index.

Fast Sparse Matrix-Vector Multiplication on GPUs: Implications for Graph Mining

Abstract: Scaling up the sparse matrix-vector multiplication kernel on modern Graphics Processing Units (GPU) has been at the heart of numerous studies in both academia and industry. In this article we present a novel non-parametric, self-tunable, approach to data representation for computing this kernel, particularly targeting sparse matrices representing power-law graphs. Using real data, we show how our representation scheme, coupled with a novel tiling algorithm, can yield significant benefits over the current state of the art GPU efforts on a number of core data mining algorithms such as PageRank, HITS and Random Walk with Restart.

R in Action

Abstract: SummaryR in Action is the first book to present both the R system and the use cases that make it such a compelling package for business developers. The book begins by introducing the R language, including the development environment. Focusing on practical solutions, the book also offers a crash course in practical statistics and covers elegant methods for dealing with messy and incomplete data using features of R. About the TechnologyR is a powerful language for statistical computing and graphics that can handle virtually any data-crunching task. It runs on all important platforms and provides thousands of useful specialized modules and utilities. This makes R a great way to get meaningful information from mountains of raw data. About the BookR in Action is a language tutorial focused on practical problems. It presents useful statistics examples and includes elegant methods for handling messy, incomplete, and non-normal data that are difficult to analyze using traditional methods. And statistical analysis is only part of the story. You'll also master R's extensive graphical capabilities for exploring and presenting data visually. What's InsidePractical data analysis, step by step Interfacing R with other software Using R to visualize data Over 130 graphs Eight reference appendixes================================ Table of ContentsPart I Getting started Introduction to R Creating a dataset Getting started with graphs Basic data management Advanced data management Part II Basic methods Basic graphs Basic statistics Part III Intermediate methods Regression Analysis of variance Power analysis Intermediate graphs Re-sampling statistics and bootstrapping Part IV Advanced methods Generalized linear models Principal components and factor analysis Advanced methods for missing data Advanced graphics

Projectors and depth cameras for deviceless augmented reality and interaction.

Abstract: Architecture that combines multiple depth cameras and multiple projectors to cover a specified space (e.g., a room). The cameras and projectors are calibrated, allowing the development of a multi-dimensional (e.g., 3D) model of the objects in the space, as well as the ability to project graphics in a controlled fashion on the same objects. The architecture incorporates the depth data from all depth cameras, as well as color information, into a unified multi-dimensional model in combination with calibrated projectors. In order to provide visual continuity when transferring objects between different locations in the space, the user's body can provide a canvas on which to project this interaction. As the user moves body parts in the space, without any other object, the body parts can serve as temporary “screens” for “in-transit” data.

Fast sparse matrix-vector multiplication on GPUs: implications for graph mining

Abstract: Scaling up the sparse matrix-vector multiplication kernel on modern Graphics Processing Units (GPU) has been at the heart of numerous studies in both academia and industry. In this article we present a novel non-parametric, self-tunable, approach to data representation for computing this kernel, particularly targeting sparse matrices representing power-law graphs. Using real web graph data, we show how our representation scheme, coupled with a novel tiling algorithm, can yield significant benefits over the current state of the art GPU efforts on a number of core data mining algorithms such as PageRank, HITS and Random Walk with Restart.

CGLX: A Scalable, High-Performance Visualization Framework for Networked Display Environments

Abstract: The Cross Platform Cluster Graphics Library (CGLX) is a flexible and transparent OpenGL-based graphics framework for distributed, high-performance visualization systems. CGLX allows OpenGL based applications to utilize massively scalable visualization clusters such as multiprojector or high-resolution tiled display environments and to maximize the achievable performance and resolution. The framework features a programming interface for hardware-accelerated rendering of OpenGL applications on visualization clusters, mimicking a GLUT-like (OpenGL-Utility-Toolkit) interface to enable smooth translation of single-node applications to distributed parallel rendering applications. CGLX provides a unified, scalable, distributed OpenGL context to the user by intercepting and manipulating certain OpenGL directives. CGLX's interception mechanism, in combination with the core functionality for users to register callbacks, enables this framework to manage a visualization grid without additional implementation requirements to the user. Although CGLX grants access to its core engine, allowing users to change its default behavior, general development can occur in the context of a standalone desktop. The framework provides an easy-to-use graphical user interface (GUI) and tools to test, setup, and configure a visualization cluster. This paper describes CGLX's architecture, tools, and systems components. We present performance and scalability tests with different types of applications, and we compare the results with a Chromium-based approach.

Using graphics rendering contexts to enhance the real-time video coding for mobile cloud gaming

Abstract: The emerging cloud gaming service has been growing rapidly, but not yet able to reach mobile customers due to many limitations, such as bandwidth and latency. We introduce a 3D image warping assisted real-time video coding method that can potentially meet all the requirements of mobile cloud gaming. The proposed video encoder selects a set of key frames in the video sequence, uses the 3D image warping algorithm to interpolate other non-key frames, and encodes the key frames and the residues frames with an H.264/AVC encoder. Our approach is novel in taking advantage of the run-time graphics rendering contexts (rendering viewpoint, pixel depth, camera motion, etc.) from the 3D game engine to enhance the performance of video encoding for the cloud gaming service. The experiments indicate that our proposed video encoder has the potential to beat the state-of-art x264 encoder in the scenario of real-time cloud gaming. For example, by implementing the proposed method in a 3D tank battle game, we experimentally show that more than 2 dB quality improvement is possible.

Techniques for load balancing gpu enabled virtual machines

Abstract: Exemplary techniques for balancing 3D graphical processor unit use among virtual machines are herein disclosed. In an exemplary embodiment, a virtualization platform can load an instance of a graphics rendering module for a virtual machine; select a GPU for the graphics rendering module to run on; and configure the virtual machine to render to the selected GPU. In addition to the foregoing, other aspects are described in the detailed description, claims, and figures.

Efficient parallel lists intersection and index compression algorithms using graphics processing units

Abstract: Major web search engines answer thousands of queries per second requesting information about billions of web pages. The data sizes and query loads are growing at an exponential rate. To manage the heavy workload, we consider techniques for utilizing a Graphics Processing Unit (GPU). We investigate new approaches to improve two important operations of search engines -- lists intersection and index compression.For lists intersection, we develop techniques for efficient implementation of the binary search algorithm for parallel computation. We inspect some representative real-world datasets and find that a sufficiently long inverted list has an overall linear rate of increase. Based on this observation, we propose Linear Regression and Hash Segmentation techniques for contracting the search range. For index compression, the traditional d-gap based compression schemata are not well-suited for parallel computation, so we propose a Linear Regression Compression schema which has an inherent parallel structure. We further discuss how to efficiently intersect the compressed lists on a GPU. Our experimental results show significant improvements in the query processing throughput on several datasets.

Methods and systems for use in providing a remote user interface

Abstract: The present embodiments provide systems, methods and apparatuses for use in providing the playback of content. Some of these embodiments provide methods of playing back multimedia content, comprising: implementing, on a multimedia rendering client device coupled with a LAN, a simplified Internet browser that establishes a browser environment; establishing a network connection over the LAN between the client device and a remote server; operating, within the browser environment, a lightweight remote user interface (RUI) protocol client application that is operated with a JavaScript based graphics application program interface to a graphics protocol stack of the client device; receiving graphics commands; implementing, through the RUI protocol client application in cooperation with the JavaScript based graphics application program interface, the graphics commands and generating graphics in accordance with the graphics commands; and displaying on the client device the graphics consistent with the graphics commands.

GraVVITAS: generic multi-touch presentation of accessible graphics

Abstract: Access to graphics and other two dimensional information is still severely limited for people who are blind. We present a new multimodal computer tool, GraVVITAS, for presenting accessible graphics. It uses a multitouch display for tracking the position of the user's fingers augmented with haptic feedback for the fingers provided by small vibrating motors, and audio feedback for navigation and to provide non-geometric information about graphic elements. We believe GraVVITAS is the first practical, generic, low cost approach to providing refreshable accessible graphics. We have used a participatory design process with blind participants and a final evaluation of the tool shows that they can use it to understand a variety of graphics - tables, line graphs, and floorplans.

ChemInk: a natural real-time recognition system for chemical drawings

Abstract: We describe a new sketch recognition framework for chemical structure drawings that combines multiple levels of visual features using a jointly trained conditional random field. This joint model of appearance at different levels of detail makes our framework less sensitive to noise and drawing variations, improving accuracy and robustness. In addition, we present a novel learning-based approach to corner detection that achieves nearly perfect accuracy in our domain. The result is a recognizer that is better able to handle the wide range of drawing styles found in messy freehand sketches. Our system handles both graphics and text, producing a complete molecular structure as output. It works in real time, providing visual feedback about the recognition progress. On a dataset of chemical drawings our system achieved an accuracy rate of 97.4%, an improvement over the best reported results in literature. A preliminary user study also showed that participants were on average over twice as fast using our sketch-based system compared to ChemDraw, a popular CAD-based tool for authoring chemical diagrams. This was the case even though most of the users had years of experience using ChemDraw and little or no experience using Tablet PCs.

Remote gaming features

Abstract: Features are described herein that may be used to implement a system that enables a user to execute, operate and interact with a software application, such as a video game, on a client wherein the software application is executing on a remote server. The features enable the system to be implemented in an optimized fashion. For example, one feature entails intercepting graphics commands generated by the software application that are directed to a graphics application programming interface (API), manipulating the intercepted graphics commands to produce manipulated graphics commands that are reduced in size as compared to the intercepted graphics commands, and transferring the manipulated graphics commands from the server to the client for rendering thereon.

3D Engine Design for Virtual Globes

Abstract: Supported with code examples and the authors real-world experience, this book offers the first guide to engine design and rendering algorithms for virtual globe applications like Google Earth and NASA World Wind The content is also useful for general graphics and games, especially planet and massive-world engines With pragmatic advice throughout, it is essential reading for practitioners, researchers, and hobbyists in these areas, and can be used as a text for a special topics course in computer graphics Topics covered include: Rendering globes, planet-sized terrain, and vector data Multithread resource management Out-of-core algorithms Shader-based renderer design

High-performance software rasterization on GPUs

Abstract: In this paper, we implement an efficient, completely software-based graphics pipeline on a GPU. Unlike previous approaches, we obey ordering constraints imposed by current graphics APIs, guarantee hole-free rasterization, and support multisample antialiasing. Our goal is to examine the performance implications of not exploiting the fixed-function graphics pipeline, and to discern which additional hardware support would benefit software-based graphics the most.We present significant improvements over previous work in terms of scalability, performance, and capabilities. Our pipeline is malleable and easy to extend, and we demonstrate that in a wide variety of test cases its performance is within a factor of 2--8x compared to the hardware graphics pipeline on a top of the line GPU.Our implementation is open sourced and available at http://code.google.com/p/cudaraster/

Image display system with visual server

Abstract: An image display system with one or more client computers in selective communication with a visual server having image processing capabilities. The client computer generates image modifying data corresponding to a generated image, and transmits the data to the visual server. The visual server receives the image-modifying data, generates a modified image based upon the image-modifying data, and transmits the modified image as compressed data to the client. The client decompresses the modified image data and displays the modified image. In the system, the visual server and client can provide a sequential display of modified frames on client to support animation with complex 3-dimensional graphics.

OpenCL in Action: How to Accelerate Graphics and Computations

Abstract: OpenCL in Action is a thorough, hands-on presentation of OpenCL, with an eye toward showing developers how to build high-performance applications of their own. It begins by presenting the core concepts behind OpenCL, including vector computing, parallel programming, and multi-threaded operations, and then guides you step-by-step from simple data structures to complex functions. ABOUT THE TECHNOLOGY: Whatever system you have, it probably has more raw processing power than you’re using. OpenCL is a high-performance programming language that maximizes computational power by executing on CPUs, graphics processors, and other number-crunching devices. It’s perfect for speed-sensitive tasks like vector computing, matrix operations, and graphics acceleration. ABOUT THIS BOOK: OpenCL in Action blends the theory of parallel computing with the practical reality of building high-performance applications using OpenCL. It first guides you through the fundamental data structures in an intuitive manner. Then, it explains techniques for high-speed sorting, image processing, matrix operations, and fast Fourier transform. The book concludes with a deep look at the all-important subject of graphics acceleration. Numerous challenging examples give you different ways to experiment with working code. A background in C or C++ is helpful, but no prior exposure to OpenCL is needed. WHAT’S INSIDE: Learn OpenCL step by step; Tons of annotated code; Tested algorithms for maximum performance.

A 2589 line topology optimization code written for the graphics card

Abstract: We investigate topology optimization based on the solid isotropic material with penalization approach on compute unified device architecture enabled graphics cards in three dimensions. Linear elasticity is solved entirely on the GPU by a matrix-free conjugate gradient method using finite elements. Due to the unique requirements of the single instruction, multiple data stream processors, special attention is given to the procedural generation of matrix–vector products entirely on the graphics card. The GPU code is found to be extremely efficient, being faster than a 48 core shared memory CPU system. CPU and GPU implementations show different performance bottlenecks. The sources are available at http://www.mathematik.uni-trier.de/~schmidt/gputop.

Graphics processing units and genetic programming: an overview

Abstract: A top end graphics card (GPU) plus a suitable SIMD interpreter can deliver a several hundred fold speed up, yet cost less than the computer holding it. We give highlights of AI and computational intelligence applications in the new field of general purpose computing on graphics hardware (GPGPU). In particular, we surveyed genetic programming (GP) use with GPU. We gave several applications from Bioinformatics and showed that how the fastest GP is based on an interpreter rather than compilation. Finally using GP to generate GPU CUDA kernel C++ code is sketched.