检索结果-内蒙古大学图书馆

13th International Conference on systems Simulation, AsiaSim 2013

作者： Yin, Xinyi shen, xukun Zhang, Fengquan Huang, Guanzhe State Key Laboratory of Virtual Reality Technology and Systems Beihang University China

ISBN: (纸本)9783642450365

We present an efficient framework for fluid-solid coupling, including both rigid and elastic bodies. Based on a unified particle model, we apply different coupling scheme for fluid-solid and solid-solid coupling respectively. Realistic and versatility are achieved by coupling all the objects adaptively. With the help of GPU accelerating, we gain a realtime simulation. © Springer-Verlag Berlin Heidelberg 2013.

关键词： Hydrodynamics

来源：评论

学校读者我要写书评

暂无评论

Robust wrinkle-aware non-rigid registration for triangle meshes of hand with rich and dynamic details

Robust wrinkle-aware non-rigid registration for triangle mes...

引用

作者： Zhao, Ling shen, xukun Long, Xiang State Key Laboratory of Virtual Reality Technology and Systems Beihang University China

Consistence of topology for 3D models with such rich details as pores and wrinkles is very important for performing higher level tasks like deformation and animation. In this paper, we propose a novel wrinkle-aware registration method, which aligns not only the large-scale poses, but also high-resolution deformable details, in a unified framework. Using large-scale alignment enables us to solve a template-based energy minimization problem through pure Euclidean measurement. Fine-scale features are aligned by firstly computing crest lines for both the intermediately registered mesh and the target, and then evaluating the shape descriptors at the feature points, followed by a graph matching procedure to achieve a global optimization of the closest point matching. Experiments show that our method is effective and robust in preserving the quality of the source, while matching the fine-scale details of the target. © 2012 Elsevier Ltd. All rights reserved.

关键词： Deformation

来源：评论

学校读者我要写书评

暂无评论

Real-time particle fluid simulation with WCSPH 20

Real-time particle fluid simulation with WCSPH

引用

20th Pacific Conference on Computer Graphics and Applications, PG 2012

作者： Zhang, Fengquan shen, xukun Long, Xiang Zhao, Bin Hu, Lei State Key Laboratory of Virtual Reality Technology and Systems Beihang University China

ISBN: (纸本)9783905673944

In this paper, based on weakly compressible smoothed particles hydrodynamics (WCSPH), we present a method for simulating high quality fluid. We propose a new pressure equation to reduce time overhead, speed up convergence towards small density fluctuations and allow for a larger time step than that of traditional approaches. And based on the new equation, we introduce a new adaptive time-stepping approach that automatically adapts the time step according to each particle current individual time step, thus improving the efficiency of computation and contributing much to a real-time particle fluid simulation. For real-time simulation, we make full use of CPU and GPU in a combined way to build a parallel platform, namely Multi-GPU platform. And optimization of the platform design is made to run a simulation with realistic visual effects in real time. © The Eurographics Association 2012.

关键词： Hydrodynamics

来源：评论

学校读者我要写书评

暂无评论

Adaptive SIFT matching using cascading vocabulary tree

Adaptive SIFT matching using cascading vocabulary tree

引用

2011 International Conference on virtual reality and Visualization, ICVRV 2011

作者： ZhiQiang, Fan xukun, shen State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China

ISBN: (纸本)9780769546025

We present a novel vocabulary tree data structure for adaptive SIFT matching. Our matching process contains an offline module to cluster features from a group of reference images and an online module to match them to the live images in order to enhance matching robustness. The main contribution lies in constructing two different vocabulary structures cascaded in one tree, which we have called cascading vocabulary tree that can be used to not only cluster features but also implement exact feature matching as k-d tree does. Cascading key frame selection using our vocabulary structure can be put the matching process forward, which gives us a way to employ a cascading feature matching strategy to combine matching results of cascading vocabulary tree and key frame. Experimental results show that our method not only dramatically enhances matching robustness but also has enough flexibility to adaptively adjust itself to meet diverse requirements of domain applications for efficiency and robustness of SIFT matching. © 2011 IEEE.

关键词： Trees (mathematics)

来源：评论

学校读者我要写书评

暂无评论

Structure-based mesh completion

Structure-based mesh completion

引用

2009 International Conference on Computational Intelligence and Software Engineering, CiSE 2009

作者： Zhang, Dehui Qi, Yue Yang, shen Hou, Fei State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing 100191 China

ISBN: (纸本)9781424445073

Meshes acquired with range scanning devices typically contain complex holes missing salient structure features. This paper presents a novel method to complete meshes by means of structure propagation. In our system, firstly, the unknown region is commonly filled with smooth patch that interpolates the shape and density of the surrounding mesh. Secondly, the user manually specifies the missing structure information by extending a few sketch curves from known to unknown area in a proper viewpoint. Thirdly, structure propagation is operated in a greedy manner with constraints of structure and consistency. Finally, structural geometric details are transferred onto the unknown region by operating over the intrinsic representation based on the Laplacian of the mesh. We demonstrate our approach at several examples, showing that complete meshes are generated in a pleasing way and preserve the structural geometric details as much as possible. ©2009 IEEE.

关键词： Curve fitting

来源：评论

学校读者我要写书评

暂无评论

An automatic registration method based on fiducial marker for image guided neurosurgery system

An automatic registration method based on fiducial marker fo...

引用

13th International Conference on systems Simulation, AsiaSim 2013

作者： Yin, Minjie shen, xukun Hu, Yong Fang, Xiaorui State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing 100191 China

ISBN: (纸本)9783642450365

Patient-to-image registration is a fundamental step of Image Guided Neurosurgery System. In this paper, we propose an automatic technique to register the patient space with the preoperative images based on fiducial markers. Our technique includes three parts. First, we identify the markers in the image space based on multi-scale features and then cluster all this features to find marker centers. And in patient space, we combine Trajkovicspi0215es and Harrisspi0215es algorithm to detect the corners in the center of the markers and then reconstruct 3D coordinates based on binocular stereo vision. At last, we register these two sets of centers using RANSAC. Experiments show that the marker centers can be localized precisely and the two space can be perfectly registered. © Springer-Verlag Berlin Heidelberg 2013.

关键词： Stereo image processing

来源：评论

学校读者我要写书评

暂无评论

A method of 3D modeling and codec

引用

Science in China(Series F) 2009年第5期52卷 758-769页

作者： QI Yue YANG shen CAI Su HOU Fei shen xukun ZHAO QinPing State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing 100191 China Institute of Modern Educational Technology Beijing Normal University Beijing 100875 China

3D modeling and codec of real objects are hot issues in the field of virtual reality. In this paper, we propose an automatic registration two range images method and a cycle based automatic global registration algorithm for rapidly and automatically registering all range images and constructing a realistic 3D model. Besides, to meet the requirement of huge data transmission over Internet, we present a 3D mesh encoding/decoding method for encoding geometry, topology and attribute data with high compression ratio and supporting progressive transmission. The research results have already been applied successfully in digital museum.

关键词： 3D modeling range images registration 3D model compression and codec

来源：评论

学校读者我要写书评

暂无评论

Saliency-driven depth compression for 3D image warping 22

Saliency-driven depth compression for 3D image warping

引用

22nd Pacific Conference on Computer Graphics and Applications, PG 2014

作者： Gu, Minjie Hu, Shanfeng Wang, Xiaochuan Liang, Xiaohui shen, xukun Qin, Aihong State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China Zhejiang Institute of Media and Communications Hangzhou China

ISBN: (纸本)9783905674736

Current compression methods compress depth images by incorporating 2D features, which leads to a loss of the detail of the original 3D object in the recovered depth image. The main idea of this paper is to augment 2D features with 3D geometric information to preserve important regions of the depth image. Mesh saliency is used to represent the important regions of the 3D objects, and discontinuity edges are extracted to indicate the important regions of the depth image. We use mesh saliency to guide the adaptive random sampling to generate a random pixel sample of the depth image and then, combine this sample with the depth discontinuity edge to build the sparse depth representation. During the depth reconstruction, the depth image is recovered by using an up- and down-sampling schema with Gaussian bilateral filtering. The effectiveness of the proposed method is validated through 3D image warping applications. The visual and quantitative results show a significant improvement of the synthetic image quality compared with state-of-the-art depth compression methods. © The Eurographics Association 2014.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

GRANet: Global refinement atrous convolutional neural network for semantic scene segmentation 25

GRANet: Global refinement atrous convolutional neural networ...

引用

25th IEEE International Conference on Image Processing, ICIP 2018

作者： Feng, Zhou Yong, Hu xukun, shen State Key Laboratory of Virtual Reality Technology and Systems Beihang University China School of New Media Art and Design Beihang University China

ISBN: (纸本)9781479970612

The main problems of complex-scene understanding and semantic scene segmentation are caused by mismatched relationships, confusion categories, and inconspicuous classes. Towards above issues, we propose a global refinement atrous convolutional neural network (GRANet) for semantic scene segmentation. To enlarge the receptive field of filters, we use atrous convolution instead of the downsampling operators. To handle the challenge caused by the existence of objects at multiple scales in a scene, we adopt multiple rates atrous convolution structure. And to overcome the problem that the current semantic segmentation architecture can not make good use of global information, we propose a multiple pooling module schemes to utilize the global context information to boost the performance of our GRANet. The proposed GRANet achieves state-of-the-art performance on the SiftFlow Dataset and attains comparable performance with other state-of-the-art works on Cityscapes dataset. © 2018 IEEE.

关键词： Semantics

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

2011 International Conference on virtual reality and Visualization, ICVRV 2011

作者： Tian, Feng shen, Xu-Kun Xian-Mei, Liu Hong-Tao, Xie State Key Laboratory of Virtual Reality Technology and Systems BeiHang University Beijing China School of Computer and Information Technology Northeast Petroleum University DaQing China

ISBN: (纸本)9780769546025

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. © 2011 IEEE.

关键词： Semantics

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：