检索结果-内蒙古大学图书馆

2014 International Conference on Artificial Intelligence and Industrial Application (AIIA2014)

作者： C.Lu J.P.Du Q.P.Li Beijing Key Laboratory of Intelligent Telecommunication Software and Multimedia School of Computer ScienceBeijing University of Posts and Telecommunications

ISBN: (纸本)9781784660529

This paper uses the Gauss Filter and the Canny Operator to calculate the gradient and region energy of the transformation result based on wavelet transform, and decides the frequency coefficients based on gradient and region energy to solve the problem that the result of traditional fusion method may lose edge information. The new fusion method has an improvement in the definition of edge, and reducing White Gauss Noise(WGN) interference. The experiment uses entropy and average gradient to evaluate the fusion result. The experiment result shows that the new method has more image information and edge information;it can also reduce WGN interference.

关键词： image fusion gradient region energy edge information wavelet transform

来源：评论

学校读者我要写书评

暂无评论

Image sequence interpolation based on segmentation and optical flow

Image sequence interpolation based on segmentation and optic...

引用

2014 International Conference on Artificial Intelligence and Industrial Application (AIIA2014)

作者： E.W.Bai J.P.Du M.Y.Liang Beijing Key Laboratory of Intelligent Telecommunications Software and Multimedia School of Computer ScienceBeijing University of Posts and Telecommunications

ISBN: (纸本)9781784660529

As traditional image sequence interpolation methods cannot decide the occlusions and disocclusions properly, this paper proposed a method combining image segmentation and optical flow to interpolate for image sequences. Image segmentation can automatically decide the regions with forward and backward interpolation, incorporating using optical flow to calculate the flow field between two images, and then interpolate for the segmented regions. This method takes advantage of a loop combining with a level set approach to solve the best results. Experiment results show that: comparing with the traditional frame differential method and the optical flow method, the method proposed by this paper gets better results in a subjective consequent and objective assessment indicator.

关键词： image sequence interpolation optical flow image segmentation

来源：评论

学校读者我要写书评

暂无评论

WEB TOPIC DETECTION USING A RANKED CLUSTERING-LIKE PATTERN ACROSS SIMILARITY CASCADES

WEB TOPIC DETECTION USING A RANKED CLUSTERING-LIKE PATTERN A...

引用

IEEE International Conference on multimedia and Expo

作者： Fei Jia Junbiao Pang Weigang Zhang Guorong Li Chunjie Zhang Qingming Huang Yugui Liu School of Computer and Control Engineering University of Chinese Academy of Sciences Beijing Key Laboratory of Multimedia and Intelligent Software Technology College of Metropolitan Transportation Beijing University of Technology School of Computer Science and Technology Harbin Institute of Technology

ISBN: (纸本)9781479947607

In multi-media and social media communities, web topic detection poses two main difficulties that conventional approaches can barely handle: 1) there are large inter-topic variations among web topics;2) supervised information is rare to identify the real topics. In this paper, we address these problems from the similarity diffusion perspective among objects on web, and present a clustering-like pattern across similarity cascades (SCs). SCs are a series of subgraphs generated by truncating a weighted graph with a set of thresholds, and then maximal cliques are used to describe the topic candidates. Poisson deconvolution is adopted to efficiently identify the real topics from these topic candidates. Experiments demonstrate that our approach outperforms the state-of-the-arts on two datasets. In addition, we report accuracy v.s. false positives per topic (FPPT) curves for performance evaluation. To our knowledge, this is the first complete evaluation of web topic detection at the topic-wise level, and it establishes a new benchmark for this problem.

关键词： Web Topic detection Maximal cliques Unsupervised ranking Poisson process Similarity cascade

来源：评论

学校读者我要写书评

暂无评论

Interpolating subdivisions from approximating subdivisions

引用

Journal of Information and Computational Science 2013年第17期10卷 5467-5481页

作者： Xue, Juan Yin, Baocai Zhang, Yong Kong, Dehui Beijing Key Laboratory of Multimedia and Intelligent Software Technology College of Computer Science Beijing University of Technology Beijing 100124 China

A subdivision surface is a method of representing a smooth, continuous, seamless surface via the specification of a coarser piecewise linear polygon mesh. In this paper, we propose an innovative unified method for constructing interpolating subdivisions. Our algorithm extends the selected approximating subdivision by merging the merits of other different interpolating functions. By using Loop subdivision and Two-point Linear interpolation as specified approximating subdivision and difference interpolating function respectively, the generated interpolating subdivision is modified Butterfly scheme. In addition, the Butterfly subdivision was also used as an instance of corresponding difference interpolating function. A novel interpolating subdivision scheme, which is named Loop-Butterfly scheme and refers to the features of both Loop and Butterfly subdivision, is introduced in this paper. The Loop-Butterfly subdivision scheme can produce more fairing surface than the Butterfly subdivision only using the initial control points for the final interpolation. The results of our experiments reveal that our method utilizes the advantages of both the approximation subdivision method and the difference interpolating function. The convergence analysis verified that the graph of Loop-Butterfly subdivision is a C1 continuous surface. © 2013 Binary Information Press.

关键词： Interpolation

来源：评论

学校读者我要写书评

暂无评论

Comparison of field-based crowd simulation approach based on different parallel architectures

引用

Journal of Information and Computational Science 2013年第17期10卷 5661-5670页

作者： Zhao, Xinxin Zhang, Yong Kong, Dehui Yin, Baocai Beijing Key Laboratory of Multimedia and Intelligent Software Technology College of Computer Science and Technology Beijing University of Technology Beijing 100022 China

Crowd simulation has been very significant and widely applied in many fields of virtual reality. How to greatly increase the efficiency and realism becomes the focus of the research about crowd simulation. In this paper, a real-time crowd simulation system is designed on parallel architectures. The system is applied to simulating the evacuation of massive crowd in an Olympic venue and then experiments are done to compare and analyze their different simulation efficiencies on different architectures. The best simulation performance comes from the hybrid architecture in combination of CPU and GPU with parallel computing on multi-core CPUs and the it can reach 52 fps when the number of crowd is 10000. GPU architecture can be used in the crowd simulation system with few data transmission times between CPU and GPU, branch statements and texture look-ups better. © 2013 Binary Information Press.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Facial expression recognition based on modular two dimensional canonical correlation analysis

引用

Journal of Information and Computational Science 2013年第7期10卷 1989-1997页

作者： Sun, Yanfeng Jiang, Tianchang Hu, Yongli Beijing Key Laboratory of Multimedia and Intelligent Software Technology College of Computer Science and Technology Beijing University of Technology Beijing 100124 China

Traditional canonical correlation analysis as an effective feature extraction method has been widely used in many areas of pattern recognition, including facial expression recognition. The canonical correlation analysis makes the within-class covariance matrix constituted of two groups of feature vectors to be singular, resulting in small sample size problem, meanwhile the canonical correlation analysis as a global linear projection method, not a good description of nonlinear facial expression recognition problem. In order to solve the above problems, we present a facial expression recognition algorithm based on modular two dimensional canonical correlation analysis. The algorithm uses a modular method, and better takes advantage of local non-linear characteristics of the facial expression image, meanwhile the direct use of two-dimensional facial expression feature matrix is effective to relieve the small sample size problem. In recognition stage, we use the voting method, which can improve the robustness of local expression feature changes. Experiments on JAFFE facial expression database show that the proposed method is robust and effective. © 2013 by Binary Information Press.

关键词： Covariance matrix

来源：评论

学校读者我要写书评

暂无评论

LOW ILLUMINATION IMAGE RETINEX ENHANCEMENT ALGORITHM BASED ON GUIDED FILTERING

LOW ILLUMINATION IMAGE RETINEX ENHANCEMENT ALGORITHM BASED O...

引用

2014 IEEE 3rd International Conference on Cloud Computing and Intelligence Systems

作者： Jingcao Yin Hongbo Li Junping Du Pengcheng He Beijing Key Lab of Intelligent Telecommunication Software and Multimedia Beijing University of Posts and Telecommunications Department of Computer Science and Technology Tsinghua University

It has been shown by Retinex theory that the object's color in the image is determined by its *** this frame work,several Retinex-based algorithms have been developed to uncover the real appearance of objects by estimating their reflectance in *** this paper we propose an algorithm of optimizing the illumination based on guided image filter theory,where bilateral filter is utilized to estimate the illumination *** proposed algorithm removes the halo phenomenon precisely and strengthens the partial contrast gradient *** are given to demonstrate the effectiveness of the proposed method.

关键词： image enhancement Retinex algorithm guided filter Gamma correction.

来源：评论

学校读者我要写书评

暂无评论

Low illumination image Retinex enhancement algorithm based on guided filtering

Low illumination image Retinex enhancement algorithm based o...

引用

IEEE International Conference on Cloud Computing and Intelligence Systems (CCIS)

作者： Jingcao Yin Hongbo Li Junping Du Pengcheng He Beijing Key Lab of Intelligent Telecommunication Software and Multimedia Beijing University of Posts and Telecommunications Beijing China Department of Computer Science and Technology Tsinghua University Beijing China

ISBN: (纸本)9781467369541

It has been shown by Retinex theory that the object's color in the image is determined by its reflectance. Under this frame work, several Retinex-based algorithms have been developed to uncover the real appearance of objects by estimating their reflectance in image. In this paper we propose an algorithm of optimizing the illumination based on guided image filter theory, where bilateral filter is utilized to estimate the illumination image. The proposed algorithm removes the halo phenomenon precisely and strengthens the partial contrast gradient effectively. Examples are given to demonstrate the effectiveness of the proposed method.

关键词： Entropy Filtering Lighting Image edge detection Lubricating oils Standards

来源：评论

学校读者我要写书评

暂无评论

How to Crowdsource Tasks Truthfully without Sacrificing Utility: Online Incentive Mechanisms with Budget Constraint

How to Crowdsource Tasks Truthfully without Sacrificing Util...

引用

IEEE International Conference on computer Communications

作者： Dong Zhao Xiang-Yang Li Huadong Ma Beijing Key Laboratory of Intelligent Telecommunications Software and Multimedia Beijing University of Posts and Telecommunications China Department of Computer Science and Technology Tsinghua University China Beijing University of Posts and Telecommunications Beijing Beijing CN

Mobile crowdsourced sensing (MCS) is a new paradigm which takes advantage of pervasive smartphones to efficiently collect data, enabling numerous novel applications. To achieve good service quality for a MCS application, incentive mechanisms are necessary to attract more user participation. Most of existing mechanisms apply only for the offline scenario where all users' information are known a priori. On the contrary, we focus on a more realistic scenario where users arrive one by one online in a random order. Based on the online auction model, we investigate the problem that users submit their private types to the crowdsourcer when arrive, and the crowdsourcer aims at selecting a subset of users before a specified deadline for maximizing the value of services (assumed to be a non-negative monotone submodular function) provided by selected users under a budget constraint. We design two online mechanisms, OMZ and OMG, satisfying the computational efficiency, individual rationality, budget feasibility, truthfulness, consumer sovereignty and constant competitiveness under the zero arrival-departure interval case and a more general case, respectively. Through extensive simulations, we evaluate the performance and validate the theoretical properties of our online mechanisms.

关键词： Sensors Resource management Smart phones Mechanical factors Conferences computers Complexity theory

来源：评论

学校读者我要写书评

暂无评论

A reproductive particle swarm optimization algorithm for data clustering

引用

International Journal of Applied Mathematics and Statistics 2013年第22期51卷 309-316页

作者： Zhao, Mingru Tang, Hengliang Guo, Jian Sun, Yuan Beijing Municipal Key Laboratory of Multimedia and Intelligent Software Technology College of Computer Science and Technology Beijing University of Technology Beijing 100124 China Beijing Key Laboratory of Intelligent Logistics System Beijing Wuzi University Beijing 101149 China

Data clustering is a popular approach for automatically finding classes or groups of patterns. In recent years, data clustering is still a popular analysis tool for data statistics to identify some inherent structures that presents in the objects. In this paper, in order to improve the convergence and global searching capacity of particle swarm optimization(PSO) in solving data clustering ,an improved particle swarm optimization clustering algorithm (EPSOK) based on reproductive strategy is presented. In the algorithm, the best particles in the search process reproduce, at the same time, the worst particles disappear. Through comparing with the classical K-Means algorithm, the improved algorithm has obvious advantages in the experiments. © 2013 by CESER Publications.

关键词： Clustering algorithms

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：