检索结果-内蒙古大学图书馆

Data stream clustering algorithm based on spatial directed graph

Advances in Information Sciences and Service Sciences 2012年第20期4卷 241-249页

作者： Ren, Jiadong Yuan, Xuemei Dong, Jun College of Information Science and Engineering Yanshan University Qinhuangdao Hebei 066004 China The Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Qinhuangdao City 066004 China

Recently, the grid-density based clustering has become one of the major issues among all of the clustering approaches, it has special advantages over other clustering algorithms, such as less computation and the ability of clustering with arbitrarily shape, which are particularly useful for the data stream clustering. This paper defines a spatial directed graph named Grid-Based Graph (GBG) to store the non-empty grids in data space, and proposes a data stream clustering algorithm based on spatial directed graph GBGSClu (Grid-Based Graph Stream Clustering). GBG graph composes of vertices and directed edges, if a vertex A has a neighboring dense vertex B, and then there is a directed edge from vertex B to A in GBG. The algorithm maps the data stream into the non-empty vertices online, updates the vertices' feature vectors with the arriving of data stream, deletes the sparse vertices every gap time, generates GBG graph when the clustering quest coming and finally clusters on the current structure. The eventual clustering results can be obtained by only checking the vertices' in-degree which can reduce the computation needed in clustering. The validity and efficiency of GBGSClu algorithm have been tested and verified by clustering on real and synthetic datasets.

关键词： Directed graphs

来源：评论

学校读者我要写书评

暂无评论

Clustering based search algorithm for motion estimation

Clustering based search algorithm for motion estimation

引用

2012 13th IEEE International Conference on Multimedia and Expo, ICME 2012

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

ISBN: (纸本)9781467316590

Motion estimation is the key part of video compression since it removes the temporal redundancy within frames and significantly affects the encoding quality and efficiency. In this paper, a novel fast motion estimation algorithm named Clustering Based Search algorithm is proposed, which is the first to define the clustering feature of motion vectors in a sequence. The proposed algorithm periodically counts the motion vectors of past blocks to make progressive clustering statistics, and then utilizes the clusters as motion vector predictors for the following blocks. It is found to be much more efficient for one block to find the best-matched candidate with the predictors. Compared with the mainstream search algorithms, this algorithm is almost the most efficient one, 35 times faster in average than the full search algorithm, while its mean-square error is even competitively close to that of the full search algorithm. © 2012 IEEE.

关键词： Motion estimation

来源：评论

学校读者我要写书评

暂无评论

Radiance-based color calibration for image-based modeling with multiple cameras

引用

Science China(Information Sciences) 2012年第7期55卷 1509-1519页

作者： ZHAO Xu 1,2 ,ZHOU Zhong 1,2 & WU Wei 1,2 1 State key laboratory of virtual Reality technology and Systems,Beihang University,Beijing 100191,China 2 School of computer Science and Engineering,Beihang University,Beijing 100191,China 1. State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing 100191 China2. School of Computer Science and Engineering Beihang University Beijing 100191 China

Photo-consistency estimation is an important part for many image-based modeling *** paper presents a novel radiance-based color calibration method to reduce the uncertainty of photo-consistency estimation across multiple *** idea behind our method is to convert colors into a uniform radiometric color space in which multiple image data are *** results demonstrate that our method can achieve comparable color calibration effect without adjusting camera parameters and is more robust than other existing ***,we obtain an auto-determined threshold for photo-consistency check,which will lead to a better performance than existing photo-consistency based reconstruction algorithms.

关键词： color calibration photo-consistency estimation multi-camera system image-based modeling

来源：评论

学校读者我要写书评

暂无评论

Displacement residual based DDM matching algorithm

引用

Science China(Information Sciences) 2012年第9期55卷 2090-2101页

作者： ZHANG Lin 1,2,ZHOU Zhong 1,2,LIU Lin 1,2 & WU Wei 1,2 1 State key laboratory of virtual Reality technology and Systems,Beihang University,Beijing 100191,China 2 School of computer Science and Engineering,Beihang University,Beijing 100191,China 1. State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing 100191 China2. School of Computer Science and Engineering Beihang University Beijing 100191 China

High level architecture(HLA) is the prevailing standard for modeling and *** data distribution management(DDM) service of HLA is defined for reducing the delivery of irrelevant *** key in DDM implementation is the region overlap computation,*** matching between update and subscription *** algorithms usually make a compromise between region fidelity and network *** paper takes both the matching algorithm efficiency and bandwidth cost into *** main contributions are:1) illustrating the relationship between region changes and overlap changes,as helps reduce the number of region matching and then improves the total matching efficiency;2) classifying region updates into two types of data expression,snapshot and *** network traffic will be reduced by transmitting only residual data instead of full region representations ***,a region matching algorithm called displacement residual-based DDM matching(DRBM) is proposed in the *** analysis,algorithm implementation and experiment evaluation are *** results show that DRBM provides better matching performance and significant network payload reductions especially when there is a large number of changing regions.

关键词： distributed simulation high level architecture data distribution management region snapshot region residual

来源：评论

学校读者我要写书评

暂无评论

A RIHS-tree-based algorithm of mining frequent closed itemsets in high dimensional datasets

引用

Journal of Convergence Information technology 2012年第21期7卷 467-476页

作者： Huang, Guoyan Chen, Shuai Ren, Shenyuan Dong, Jun College of Information Science and Engineering Yanshan University Qinhuangdao Hebei 066004 China The Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Qinhuangdao City 066004 China College of Computer Science Sichuan University Chengdu Sichuan 610000 China

In order to fully utilize the minimum support threshold to prune the rowset search space and avoid scanning the whole dataset in close-checking, we proposed two new data structure, Rowset-Itemset-Hybrid-Search-Tree (RIHS-Tree) and Frequent-Closed-Itemset-Rowset-Tree (FCIR-Tree). The former stores the rowsets which share common rowid prefixes, according to some predefined order of rowids. Each path from the root node to the leaf node represents a rowset in which the rowids increase. The later also stores the large rowsets which also share common rowid prefixes. The corresponding closed itemsets are stored in the nodes carrying the last rowids in rowsets. Moreover, a new algorithm, RIHS-Tree-based algorithm for mining frequent closed patterns (FCIM-RIHS), is proposed. We translate the whole dataset into a transposed table, construct RIHS-Tree according to the rowsets in the transposed table and use a bottom-up search strategy to traverse RIHS-Tree. In the process of mining, we use the rowsets-inclusion strategy to implement pattern growth and then obtain large rowsets with their corresponding frequent closed itemsets. In FCIR-Tree, if the nodes in the subtree rooted by the nodes carrying the last rowid in the rowsets do not contain the found itemsets, the found itemsets are frequent closed itemsets. The experiment results with dataset demonstrate that FCIM-RIHS has highly efficiency.

关键词： Trees (mathematics)

来源：评论

学校读者我要写书评

暂无评论

Artistic illumination transfer for portraits

Artistic illumination transfer for portraits

引用

Eurographics Symposium on Rendering 2012, EGSR 2012

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

Relighting a portrait in a single image is still a challenging problem, particularly when only a single artistic reference photograph or painting is provided In this paper, we propose an artistic illumination transfer system for portraits based on a database of portrait images (photographs and paintings) associated with hand-drawn illumination templates (276) by artists. Users can select a reference portrait image in the database, and the corresponding illumination template is transferred to an input portrait using image warping. Users can also provide reference portrait images those are not in the database. Based on the Face Illumination Descriptor (FID), the system selects from the database the reference image with the closest illumination to that of the user-provided reference image and adjusts the corresponding illumination template to match the contrast of the user-provided reference image. Experiments on not only paintings but also photographs, paper-cuts and sketches demonstrate that convincing illumination transferred results can be rendered by our system. © 2012 The Eurographics Association and Blackwell Publishing Ltd. Published by Blackwell Publishing.

关键词： Database systems

来源：评论

学校读者我要写书评

暂无评论

Persistent object tracking in road panoramic videos

Persistent object tracking in road panoramic videos

引用

13th Pacific-Rim Conference on Multimedia, PCM 2012

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

ISBN: (纸本)9783642347771

Panorama has the full directional view of the scene and can provide an object vision persistently from its emerging to vanishing except occlusion. Though, traditional tracking algorithms are apt to fail since the object may change its appearance or even disappear occasionally during its display lifetime. A persistent object tracking algorithm for static objects in panoramic videos is proposed in this paper. It creates several auxiliary trackers to guide the tracking. Once the object is obscured or deformed, the auxiliary trackers are engaged in estimating the position of the main tracker. Even though the appearance of the object changes a lot, its position still could be estimated with help of the auxiliary trackers. Experiment results illustrated that this algorithm provides a real-time tracking effectively on signs in road panoramic videos. This algorithm is easy to perform and especially valuable for road sign labeling and management. © 2012 Springer-Verlag.

关键词： Roads and streets

来源：评论

学校读者我要写书评

暂无评论

A novel grouping aggregation algorithm for online analytical processing

引用

2012 National Conference on Information technology and computer Science, CITCS 2012

作者： Chen, Wei Liu, Yongshan Wang, Ning College of Information Science and Engineering Yanshan University Qinhuangdao China Key Laboratory for Computer Virtual Technology and System Integration of HeBei Province Qinhuangdao China

ISBN: (纸本)9789491216381

As regard to improve the efficiency of grouping aggregation calculation, the data is compressed by using binary encoding, and the dimension hierarchical grouping attribute set encodings of each dimension table are calculated by using the dimension hierarchy tree. Then different encodings are put into temporary table to be sorted and grouped, and the grouping sequence numbers of fact table records which satisfy the query conditions are computed. Finally, the buffer is located by the grouping sequence number and the grouping aggregation calculation is completed. Theoretical analysis and experimental results show that the proposed algorithm can significantly improve the efficiency of grouping aggregation calculation. © 2012. The authors - Published by Atlantis Press.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Automatic image tagging by multiple feature tag relevance learning

Automatic image tagging by multiple feature tag relevance le...

引用

2012 5th Chinese Conference on Pattern Recognition, CCPR 2012

作者： Tian, Feng Shen, Xu-Kun Shang, Fu-Hua Zhou, Kai State Key Laboratory of Virtual Reality Technology and Systems BeiHang University Beijing 100191 China School of Computer and Information Technology Northeast Petroleum University DaQing 163318 China

ISBN: (纸本)9783642335051

In this paper, we present an image tagging framework based on multiple feature tag relevance learning (MFTRL). First, in specific feature space, each training image is encoded as a sparse linear combination of other training images by 1 minimization, component images are treated as the nearest neighbors of the target image, so we can get each image's 1 nearest-neighbor by the 1 norm cost function. Then, maximum a posteriori (MAP) principle is utilized to determine the tag relevance for the testing image in specific feature space. Finally, the output of many tag relevance by diverse features can be combined in the manner of combining multi-feature tag relevance. The experiments over the well known data set demonstrate that the proposed method is beneficial and outperforms most existing image tagging algorithms. © 2012 Springer-Verlag.

关键词： Image annotation

来源：评论

学校读者我要写书评

暂无评论

Simultaneous structure and geometry detail completion based on interactive user sketches

引用

Science China(Information Sciences) 2012年第5期55卷 1123-1137页

作者： YANG Shen 1,QI Yue 1 & QIN Hong 2 1 State key laboratory of virtual Reality technology and Systems,Beihang University,Beijing 100191,China 2 Department of computer Science,State University of New York at Stony Brook,Stony Brook,New York 11794-4400,USA 1. State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing 100191 China2. Department of Computer Science State University of New York at Stony Brook Stony Brook New York 11794-4400 USA

We articulate a novel approach to geometric model completion via interactive sketches in this ***,the initial incomplete model (with holes) is decomposed into a base model and a high-frequency component,which represents global rough shape and geometric details,*** then repair the base model via smooth hole-filling,and compute the geometry detail image using high frequency *** novel element of our approach is that we allow users to interactively sketch a few structural curves that span across hole regions,with a goal to repair both local geometric details and global *** the help of local parameterization,we convert detailed geometry into gradient-domain images which can propagate along user-specified *** integrating recovered gradient-domain images and base shape,we can generate a complete model that faithfully recovers both global structure and local *** salient contribution of this paper is the unified approach for user interaction,global structure,and geometry details towards high-fidelity model *** demonstrate our new approach using a number of examples that exhibit salient global structure as well as local geometry details.

关键词： model repair geometric modeling interactive sketch 3D graphics

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：