检索结果-内蒙古大学图书馆

第十一届中国虚拟现实大会(ICVRV2011)

作者： Changjian Chi Xiaowu Chen Ziqiang Yang Guodong Jia State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing China

Realism and simplicity of virtual experiment scene building can influence the usage of virtual educational experiment applications. This paper proposes an image based method of experiment scene building for virtual Educational Experiments. Firstly, virtual educational experiment components are extracted from images of experiment instrument by using the interactive method of object extraction. Then, the corresponding logical model descriptions are attached to the extracted components. Finally, the components required in a specific experiment are inserted into the selected virtual experiment scene and are connected interactively. A routing algorithm based on equivalent connection line is designed to make the generated line connections between components clear and legible. A virtual experiment scene building system, named VE Scene builder, has been implemented and widely used. The feedbacks demonstrated that our system can rapidly generate realistic and legible virtual experiment scene.

关键词： virtual educational experiment image based virtual scene building routing algorithm

来源：评论

学校读者我要写书评

暂无评论

3D Model Multiple Semantic Automatic Annotation For Small Scale Labeled Data Set

3D Model Multiple Semantic Automatic Annotation For Small Sc...

引用

第十一届中国虚拟现实大会(ICVRV2011)

作者： Feng Tian SHEN Xu-kun Liu Xian-mei Xie Hong-tao State Key Laboratory of Virtual Reality Technology and Systems BeiHang University Beijing China Sch State Key Laboratory of Virtual Reality Technology and Systems BeiHang University Beijing China School of Computer and Information Technology Northeast Petroleum University DaQing China

Automatically assigning keywords to 3D models is of great interest as it allows one to retrieve, index, organize and understand large collections of 3D models. Most Methods require high sample size for training, so the data quality is in high demand. For small scale labeled data set, we propose a semi-supervised method to realize the 3D models multiple semantic annotation, which needs only a small amount of hand tagged information provided by users. The proposed technique utilizes low-level shape features and the keywords are assigned using a graphed-based label transfer mechanism to expand the training dataset. A weighted metric learning method is used to learn the distance measure from the extended dataset. Then multiple semantic annotation task can be completed on the learned distance measure. The proposed method outperforms the current state-of-the-art methods on the small scale labeled dataset and large unlabelled dataset. We believe that such measure will provide a strong platform to label 3D models when a small amount of labeled models were given.

关键词： 3D model annotation 3D model retrieval

来源：评论

学校读者我要写书评

暂无评论

Single Image Based Illumination Estimation for Lighting virtual Object in Real Scene

Single Image Based Illumination Estimation for Lighting Virt...

引用

IEEE International Conference on computer-Aided Design and computer Graphics

作者： Xiaowu Chen Ke Wang Xin Jin State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing China

Rendering virtual objects into real scenes with real illumination can greatly increase the realism of virtual objects and the consistency between the virtual and the real. The main challenge lies in illumination estimation from a single image. This article proposes a novel method of single image based illumination estimation for lighting virtual object in real scene. Only a single image, without any knowledge of the 3D geometry or reflectance, is needed, which greatly increases the applicability of the method. We first estimate coarse scene geometry and intrinsic components including shading image and reflectance image. Then the sparse radiance map of the scene is inferred based on the scene geometry and intrinsic components. Finally, the virtual objects are illuminated by the estimated sparse radiance map. Some experimental results show that this method can convincingly light virtual objects into a single real image, without any pre-recorded 3D geometry and reflectance, illumination acquisition equipments or imaging information of the image.

关键词： Lighting Geometry Estimation Three dimensional displays Light sources Solid modeling Sun

来源：评论

学校读者我要写书评

暂无评论

GPU Accelerating for Rapid Multi-core Cache Simulation

GPU Accelerating for Rapid Multi-core Cache Simulation

引用

IEEE International Symposium on Parallel and Distributed Processing Workshops and Phd Forum (IPDPSW)

作者： Wan Han Long Xiang Gao Xiaopeng Li Yi State Key Laboratory of Virtual Reality Technology and System School of Computer Science and Engineering Beihang University Beijing China

To find the best memory system for emerging workloads, traces are obtained during application's execution, then caches with different configurations are simulated using these traces. Since program traces can be several gigabytes, simulation of cache performance is a time consuming process. Compute unified device architecture (CUDA) is a software development platform which enables programmers to accelerate the general-purpose applications on the graphics processing unit (GPU). This paper presents a real time multi-core cache simulator, which was built based on the Pin tool to get the memory reference, and fast method for multi-core cache simulation using the CUDA-enabled GPU. The proposed method is accelerated by the following techniques: execution parallelism exploration, memory latency hiding, a novel trace compression methodology. We describe how these techniques can be incorporated into CUDA code. Experimental results show that the hybrid parallel method of time-partitioning combines with set-partitioning presented here is 11.10× speedup compared to the CPU serial simulation algorithm. The present simulator can characterize cache performance of single-threaded or multi-threaded workloads at the speeds of 6-15 MIPS. It can simulates 6 cache configurations within one single pass at this speeds compared to CMP$im, which can only simulate one cache configuration each simulation pass at the speeds of 4-10 MIPS.

关键词： Graphics processing unit Instruction sets Computational modeling Parallel processing Instruments Partitioning algorithms

来源：评论

学校读者我要写书评

暂无评论

Cooperatively Resolving Occlusion between Real and virtual in Multiple Video Sequences

Cooperatively Resolving Occlusion between Real and Virtual i...

引用

ChinaGrid Annual Conference (ChinaGrid)

作者： Xin Jin Xiaowu Chen Bin Zhou Hongchang Lin The State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing China

The occlusion between real and virtual objects influences not only seamless merging of virtual and real environments but also users' visual perception of orientations & locations and spatial interactions in augmented reality. If there exist a large amount of video sequences for representing the real environment, and each video sequence utilizes computer vision algorithms to deal with all of occlusions between real and virtual, this often drops down the real-time performance of augmented reality system. This article proposed an approach of cooperatively resolving the occlusion between real and virtual based on multiple video sequences in augmented reality scene. Firstly it analyzes the occlusion relations between virtual and real objects in initial video sequences with their intrinsic parameters and poses, and obtains the spatial relations among video sequences through 3D registration information. Secondly, for each video sequence, it divides and codes the perception regions of relative augmented reality scene. Lastly, according to the spatial relations of video sequences, the known occlusion relations in initial video sequences and the code data of perception regions, three types of occlusion relations including real occluding virtual, virtual occluding real and non-occlusion are detected out and represented in augmented reality scene. Some experimental results show that this approach can reduce redundant calculations on the way of resolving the occlusion between real and virtual objects, and improve the performance of generating augmented reality scene, especially which includes plenty of video sequences and occlusion relations of virtual occluding real or non-occlusion.

关键词： Video sequences Augmented reality Cameras Three dimensional displays Estimation Encoding

来源：评论

学校读者我要写书评

暂无评论

Automatic Compositing Soccer Video Highlights with Core-Around Event Model

Automatic Compositing Soccer Video Highlights with Core-Arou...

引用

IEEE International Conference on computer-Aided Design and computer Graphics

作者： Kai Jiang Xiaowu Chen Qinping Zhao State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing China

This paper presents an automatic video highlighting approach in relation to a soccer match video lasting over ninety minutes, in which only the match video and the target length of the highlight video are required for the composition. Firstly, we propose a core-around event model, which represents the highlight as a complex event and consists of three components: semantic relations, temporal relationship among the activities and local motion appearance of each activity. Secondly, we detect activities involved in a highlight in the soccer match video by the local motion appearance. Thirdly, a candidate highlight video segment is aligned with the model by a specific kernel activity extracted on the basis of the semantic relations, and then assigned a matching score. Finally, we splice together the highlight segments of high matching score. Experimental results demonstrate that the composed highlight videos are attractive episodes of soccer matches, and similar to those edited by professional editors.

关键词： Semantics Motion segmentation Visualization Training Humans Kernel Video sequences

来源：评论

学校读者我要写书评

暂无评论

Face illumination transfer through edge-preserving filters

Face illumination transfer through edge-preserving filters

引用

Conference on computer vision and Pattern Recognition (CVPR)

作者： Xiaowu Chen Mengmeng Chen Xin Jin Qinping Zhao State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing China

This article proposes a novel image-based method to transfer illumination from a reference face image to a target face image through edge-preserving filters. According to our method, only a single reference image, without any knowledge of the 3D geometry or material information of the target face, is needed. We first decompose the lightness layers of the reference and the target images into large-scale and detail layers through weighted least square (WLS) filter after face alignment. The large-scale layer of the reference image is filtered with the guidance of the target image. Adaptive parameter selection schemes for the edge-preserving filters is proposed in the above two filtering steps. The final relit result is obtained by replacing the large-scale layer of the target image with that of the reference image. We acquire convincing relit result on numerous target and reference face images with different lighting effects and genders. Comparisons with previous work show that our method is less affected by geometry differences and can preserve better the identification structure and skin color of the target face.

关键词： Face Image edge detection Lighting Kernel Image color analysis Smoothing methods Periodic structures

来源：评论

学校读者我要写书评

暂无评论

3D Model Multiple Semantic Automatic Annotation for Small Scale Labeled Data Set

3D Model Multiple Semantic Automatic Annotation for Small Sc...

引用

International Conference on virtual reality and Visualization (ICVRV)

作者： Feng Tian Xu-kun Shen Liu Xian-mei Xie Hong-tao State Key Laboratory of Virtual Reality Technology and Systems BeiHang University Beijing China School of Computer and Information Technology Northeast Petroleum University DaQing China

关键词： Solid modeling Three dimensional displays Computational modeling Semantics Measurement Data models Labeling

来源：评论

学校读者我要写书评

暂无评论

Distributed ownership management algorithm for HLA/RTI implementation

引用

Journal of Computational Information Systems 2011年第5期7卷 1628-1637页

作者： Zhou, Zhong Xu, Cheng Hou, Wen Wu, Wei State Key Laboratory of Virtual Reality Technology and Systems Beihang Univ. Beijing 100191 China School of Computer Science and Engineering Beihang Univ. Beijing 100191 China

In a distributed virtual environment, one attribute of an object can only be owned by one simulation node at a moment. In current applications, an ownership server will be set up to manage the ownership during the simulation, if ownership transfer is required. A distributed ownership management algorithm is proposed in the paper that is based on multi-server management and conforms to the HLA standard. It establishes an inherent lookup table between virtual objects and their creator servers. With the table, attribute ownership can find the attribute's server fast via its creator server. The algorithm is implemented in the BH RTI. Experiment results illustrated it can get higher ownership transfer speed and lower network bandwidth cost, especially valuable in the applications that have a great number of attribute ownership transfer. Copyright © 2011 Binary Information Press.

关键词： Table lookup

来源：评论

学校读者我要写书评

暂无评论

Configuration-based optimization for six degree-of-freedom haptic rendering using sphere-trees

Configuration-based optimization for six degree-of-freedom h...

引用

2011 IEEE/RSJ International Conference on Intelligent Robots and Systems

作者： Xin Zhang Dangxiao Wang Yuru Zhang Jing Xiao State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China Department of Computer Science University of North Carolina-Charlotte USA

This paper presents a novel constraint-based six degree-of-freedom (6-DoF) haptic rendering algorithm for simulating both contact forces and torques between interacting rigid bodies. We represent an object using a hierarchy of spheres, i.e., a sphere-tree. Such a representation allows fast detection of multiple contacts/collisions among objects and facilitates contact constraint formulation. Given a moving graphic tool as the avatar of the haptic tool in the virtual environment, we constrain its position and orientation, i.e., its six dimensional configuration, by solving a constrained optimization problem. The constraints in the 6-D configuration space (C-space) of the graphic tool is obtained and updated through on-line mapping of the non-penetration constraint between the spheres of the graphic tool and those of the other objects in the three dimensional physical space, based on the result of collision detection. The problem is further modeled as a quadratic programming problem and solved by classic active-set methods. Our algorithm has been implemented and interfaced with a 6-DoF Phantom Premium 3.0. We demonstrate its performance in dental surgery simulations involving complex, multi-contact virtual environments. Our method enables stable operations and realistic feel of haptic sensation.

关键词： Haptic interfaces Teeth Force Rendering (computer graphics) Dentistry Optimization

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：