检索结果-内蒙古大学图书馆

International Symposium on Parallel and Distributed Processing with Applications, ISPA

作者： Wan Han Gao Xiaopeng Wang Zhiqiang Li Yi State Key Laboratory of Virtual Reality Technology and System School of Computer Science and Engineering Beijing Aeronautics and Astronautics University Beijing China

Caches play a major role in the performance of high speed computer systems. Trace driven simulator is the most widely used method to evaluate cache architectures. However, as the cache design moves to more complicated architectures, along with the size of the trace is becoming larger and larger. Traditional simulation methods are no longer practical due to their long simulation cycles. Several techniques have been proposed to reduce the simulation time of sequential trace driven simulation. This paper considers the use of generic GPU to accelerate cache simulation which exploits set partitioning as the main source of parallelism. We develop more efficient parallel simulation techniques by introducing more knowledge into the Compute Unified Device Architecture (CUDA) on the GPU. Our experimental result shows that the new algorithm gains 2.76 times performance improvement compared to traditional CPU based sequential algorithm.

关键词： Acceleration Computational modeling computer architecture Analytical models Concurrent computing computer simulation High performance computing Parallel processing Parallel algorithms Distributed processing

来源：评论

学校读者我要写书评

暂无评论

Simulation platform for computing visual hull of 3D objects

引用

Journal of Information and Computational Science 2009年第5期6卷 2169-2176页

作者： Chen, Guojun Su, Huanhuan Jiang, Jie Wu, Wei College of Computer and Communication Engineering China University of Petroleum Dongying 257061 China State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing 100191 China

The visual hull is widely used as a proxy for real-time reconstructing a three-dimensional model from object silhouettes in images. We present a simulation platform for creating and rendering visual hulls(VHSP). This platform has a number of advantages: 1) it is multi camera based OpenGL and implemented purely based on software, 2) it is well-suited to calculating visual hull with various algorithms, and 3) it can be used to compare various algorithms. This platform sets up a uniform coordinate system for multi camera and projection matrix according to OpenGL graphics processing pipeline. On this platform, we develop dynamically computing polyhedral representation of visual hull, and present and develop a method of computing a safe polyhedral visual hull (SPVH) without phantom volumes. Results demonstrate the effectiveness of this platform for researching and developing method of computing visual hull. © 2009 Binary Information Press.

关键词： Surface reconstruction

来源：评论

学校读者我要写书评

暂无评论

Accurate semantic image labeling by fast Geodesic Propagation

Accurate semantic image labeling by fast Geodesic Propagatio...

引用

IEEE International Conference on Image Processing

作者： Xiaowu Chen Dongyue Zhao Yibiao Zhao Liang Lin State Key Laboratory of Virtual Reality Technology and Systems SCSE Beihang University Beijing China School of Computer and Information Technology Beijing Jiaotong University Beijing China Department of Statistic University of California Los Angeles USA

Motivated by recently raised image semantic labeling problem, this paper studies a fast Geodesic Propagation (GP) algorithm that integrates recognition proposal and image compatibility into a graphical representation. Given the recognition proposal map of the image, the initial seeds are selected as confident pixels standing on local proposal peaks by Mean-shift algorithm. The geodesic distance is then defined on a hybrid manifold, combining the color and boundary features with the recognition proposal map. Based on the geodesic distance, the semantic labeling is simultaneously propagated from the initial seeds of all classes to the rest of image pixels. This inference algorithm is capable of multi-labeling an image of 2-mega pixels in one second (with a common PC). In the experiment, we test on 21 generic semantic categories (sky, road, grass ...) on MSRC dataset, and 17 categories on LHI dataset to evaluate the performance.

关键词： Labeling Proposals Image recognition Pixel Testing virtual reality Inference algorithms Image segmentation Layout Markov random fields

来源：评论

学校读者我要写书评

暂无评论

Method based on the degree of object attributes attention for transmission QoS control

引用

Jisuanji Xuebao/Chinese Journal of computers 2009年第1期32卷 115-123页

作者： Xie, Ke Liang, Xiao-Hui Zhao, Qin-Ping State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing 100191 China

In Distributed virtual Environment, it is an important issue that how to manage the distribution of 3D geometry. Instead of downloading the whole virtual world objects into the clients' machines, on-demand method is to copy only objects that the user needs-partial replication of a virtual world rather than full replication. Therefore, a key aspect is how to efficiently replicate the required data in real-time. To solve this problem, a QoS transmission control method and a QoS Management Model, which are based on the degree of object attributes attention, are given in this paper. This method extends the traditional geometry-based model transmission control method. Non-geometric attributes and geometric attributes are integrated together and regarded as QoS parameters. Because real-time property is the most important requirements in distributed virtual environment and it can be affected by network bandwidth during the run time, a dynamic negotiation algorithm, which combines the idea of dynamic QoS management, is given in this paper. Experimental results show that the method is able to reflect user's level of concern a-bout virtual objects in virtual environment comprehensively, and it can gain better transmission results while ensuring the prerequisite of real-time with the changing of the network bandwidth.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

computer network defense policy specification language

引用

Jisuanji Yanjiu yu Fazhan/computer Research and Development 2009年第1期46卷 89-99页

作者： Xia, Chunhe Wei, Yudi Li, Xiaojian Wang, Haiquan He, Wei State Key Laboratory of Virtual Reality Technology Beihang University Beijing 100083 China Key Laboratory of Beijing Network Technology Beihang University Beijing 100083 China College of Computer Science and Information Technology Guilin 541000 China College of Software Beihang University Beijing 100083 China

Policy is an essential part of computer network defense, which has important directive to the deployment, implementation, configuration and effects of defense systems. Presently, models and specifications on access control policy work well. However, they can not be directly applied to the whole defense policy area. In this paper, a new computer network defense policy specification language called CNDPSL is proposed to provide a common method of specifying protection, detection and response policies according to a new defined model called CNDPM, which is put forward by extending Or-BAC (organization based access control model). In CNDPM, automatic assignment mechanism is introduced to improve efficiency, and derivative principles are presented to refine abstract policies to concrete rules. Moreover, completeness, validity and consistency of policy are also formally analyzed and demonstrated. CNDPSL is declarative and able to abstract defense control behaviors of network, which makes this language flexible, extensible and adaptable to network defense requirements. Finally, a policy engine is implemented. Detailed experiments in GTNetS platform indicate that CNDSPL can be refined to concrete technical rules automatically, such as ACL (access control list) in firewall, IDS detection rules, response rules, etc, and obtain defense effects it expresses. The above information proves its effectiveness and efficiency.

关键词： Specification languages

来源：评论

学校读者我要写书评

暂无评论

Panoramic video stabilization algorithm based on spherical transformation

引用

Journal of Information and Computational Science 2008年第5期5卷 2243-2251页

作者： Chen, Ke Li, Yanli Zhou, Zhong Wu, Wei State Key Laboratory of Virtual Reality Technology and Systems Beijing 100191 China School of Computer Science and Engineering Beihang University Beijing 100191 China

The acquisition of panoramic videos usually suffers from undesirable jitters due to deviations and rotations of the cameras. According to the characteristics of spherical panorama, an algorithm aimed to stabilize panoramic videos is proposed in this paper. For each frame, the algorithm estimates the Euler angle of the panoramic camera. With the mapping between spherical panorama and sphere, it then projects each panoramic frame onto a spherical surface, transforms them with the Euler angles of the camera and gets the corrected frames. The sequence of the corrected frames constitutes a stabilized video. The experimental results show that the algorithm corrects the jitters and improves the stability of panoramic video. 1548-7741/Copyright © 2008 Binary Information Press October 2008.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Algorithm of simulation time synchronization over large-scale nodes

引用

Science in China(Series F) 2008年第9期51卷 1239-1255页

作者： ZHAO QinPing1,2,ZHOU Zhong1,2 & Lü Fang1,2 1 State key laboratory of virtual reality technology and Systems,Beihang University,Beijing 100083,China 2 School of computer Science and Engineering,Beihang University,Beijing 100083,China State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing 100083 China School of Computer Science and Engineering Beihang University Beijing 100083 China

In distributed simulation, there is no uniform physical clock. And delay cannot be estimated because of jitter. So simulation time synchronization is essential for the event consistency among nodes. This paper investigates time synchronization algorithms over large-scale distributed nodes, analyzes LBTS （lower bound time stamp） computation model described in IEEE HLA standard, and then presents a grouped LBTS model. In fact, there is a default premise for existing algorithms that controi packets must be delivered via reliable transportation. Although, a theorem of time synchronization message＇s reliability is proposed, which proves that only those control messages that constrain time advance need reliability. It breaks out the default premise for reliability. Then multicast is introduced into the transmis- sion of control messages, and algorithm MCTS （multi-node coordination time synchronization） is proposed based on multicast. MCTS not only promotes the time advance efficiency, but also reduces the occupied network bandwidth. Experiment results demonstrate that the algorithm is better than others in both time advance speed and occupied network bandwidth. Its time advance speed is about 50 times per second when there are 1000 nodes, approximately equal to that of similar systems when there are 100 nodes.

关键词： distributed simulation time synchronization multi-node coordination LBTS multicast

来源：评论

学校读者我要写书评

暂无评论

Routing and scheduling in large-scale hybrid network with heterogeneous infrastructure

Routing and scheduling in large-scale hybrid network with he...

引用

2008 International Conference on Wireless Networks, ICWN 2008

作者： Cao, Jing Liu, Zhaoyi Su, Jinzhao Wu, Wei State Key Laboratory of Virtual Reality Technology and Systems Beijing China School of Computer Science Beihang University Beijing China

ISBN: (纸本)1601320914

We present a practical routing and scheduling method to improving the capacity of ad hoc networks with infrastructure support. The performance of a large scale hybrid network with hundreds nodes connected by infrastructure and ten thousands mobile nodes is studied in this paper. We adopt a more realistic infrastructure assumption that is heterogeneous and has a finite bandwidth. Central of the routing method is using the P2P lookup algorithm to find the destination mobile node corresponded infrastructure node. We also model the schedule problem about how to allocate the wireless links and infrastructure links. A linear programming method and centralized greedy algorithm are designed for this scheduling problem, with a tradeoff between the computation time and performance for different applications. We evaluate the routing method performance under a small scale in-field-testbed and the two scheduling methods by simulation.

关键词： Linear programming

来源：评论

学校读者我要写书评

暂无评论

An interactive virtual environment inhabited virtual agents for oil-field safety operation training

An interactive virtual environment inhabited virtual agents ...

引用

ICALIP 2008 - 2008 International Conference on Audio, Language and Image Processing

作者： Xianmei, Liu Aimin, Hao State Key Laboratory of Virtual Reality Technology Beihang University Beijing 100083 China School of Computer and Information Technology Daqing Petroleum Institute Daqing 163318 China

ISBN: (纸本)9781424417230

This paper presents an interactive, virtual reality-based training environment specifically developed for training of oil-field safety operation, in which it allows operators to experience situations that would be difficult, costly, or impossible in the real world. We have introduced a semi-autonomous virtual agent, analyzed the different training modes that allow for adapting the training environment to the trainee's knowledge and determined the level of interactivity. The development framework of the interactive virtual simulation is given, four phases of which are discussed. The virtual human basic actions are abstracted for behavior defining and re-availability. Hand shapes of virtual human are also classified and described. Scene driving engine consists of a behavioral control, a motion control, a path planning, and a collision detection module, coordinates the interactive action between the virtual human and the operated objects and controls the changes of the virtual scene. The effect for the training of oil-field safety operation can be effectively improved by application of our framework. © 2008 IEEE.

关键词： Personnel training

来源：评论

学校读者我要写书评

暂无评论

Movement model for battlefield with confrontation characteristic

Movement model for battlefield with confrontation characteri...

引用

Asia-Pacific Conference on Communications

作者： Junxia Cai Wei Wu State Key Laboratory of Virtual Reality Technology and Systems Department of Computer Beihang University Beijing China

In this paper we propose a mobility model derived from real-time strategy gamepsilas replays which can reflect confrontation & collaboration characteristic of nodes movement in military scenario. This mobility model covers several unitspsila characters, including the velocity distribution, mutual synergies, creation/destruction and terrain effect. Game playerspsila human decision is also involved, which makes this mobility model completely different from previous ones. We analyze how the confrontation &collaboration characteristics are reflected in our mobility model. We also evaluate the AODV protocol on the proposed model and traditional Random Waypoint model, and simulation results show that the network performances and topologies are significantly different when different mobility models are adopted. According to these results, this model could generate more realistic simulation scenario than the traditional mobility model, and the simulation results are more credible.

关键词： Collaboration Military computing Protocols Game theory Network topology Costs computer aided instruction Laboratories virtual reality Ad hoc networks

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：