检索结果-内蒙古大学图书馆

IEEE Conference on computer Vision and Pattern Recognition

作者： Xiaowu Chen Dongqing Zou Steven ZhiYing Zhou Qinping Zhao Ping Tan State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Department of Electrical & Computer Engineering National University of Singapore

ISBN: (纸本)9781467364102

In this paper we propose a novel alpha matting method with local and nonlocal smooth priors. We observe that the manifold preserving editing propagation [4] essentially introduced a nonlocal smooth prior on the alpha matte. This nonlocal smooth prior and the well known local smooth prior from matting Laplacian complement each other. So we combine them with a simple data term from color sampling in a graph model for nature image matting. Our method has a closed-form solution and can be solved efficiently. Compared with the state-of-the-art methods, our method produces more accurate results according to the evaluation on standard benchmark datasets.

关键词： Graphical models standardized benchmark Imagery (Psychotherapy) Image images Adrenergic alpha-Antagonists editing Laplacian operator

来源：评论

学校读者我要写书评

暂无评论

MULTI-SCALE, MULTI-LEVEL, HETEROGENEOUS FEATURES EXTRACTION AND CLASSIFICATION OF VOLUMETRIC MEDICAL IMAGES

MULTI-SCALE, MULTI-LEVEL, HETEROGENEOUS FEATURES EXTRACTION ...

引用

IEEE International Conference on Image Processing

作者： Shuai Li Qinping Zhao Shengfa Wang Aimin Hao Hong Qin State Key Laboratory of Virtual Reality Technology and Systems Beihang University China Department of Computer Science Stony Brook University USA

ISBN: (纸本)9781479923427

This paper articulates a novel method for the heterogeneous feature extraction and classification directly on volumetric images, which covers multi-scale point feature, multi-scale surface feature, multi-level curve feature, and blob feature. To tackle the challenge of complex volumetric inner structure and diverse feature forms, our technical solution hinges upon the integrated approach of locally-defined diffusion tensor (DT), DT-based anisotropic convolution kernel (DACK), DACK-based multi-scale analysis, and DT-governed curve feature growing. The extracted structural features can be further semantically classified. At the computational fronts, we design CUDA-based algorithm to conduct parallel computation for time consuming tasks. Various experiments and timing tests demonstrate the effectiveness, robustness, and high performance of our method.

关键词： Volumetric image Multi-scale heterogeneous features Curve propagation Diffusion tensor CUDA Feature extraction images multi-scale multilayers PARALLEL PROCESSING (computerS) HIGH-PERFORMANCE Taxonomy

来源：评论

学校读者我要写书评

暂无评论

Activities Information Diffusion in Chinese Largest Recommendation Social Network: Patterns and Generative Model

Activities Information Diffusion in Chinese Largest Recommen...

引用

IEEE Global Communications Conference

作者： Jianwei Niu Shaluo Huang Lei Shu Ivan Stojmenovic State Key Laboratory of Virtual Reality Technology and Systems Beihang University Guangdong Petrochemical Equipment Fault Diagnosis Key Laboratory Guangdong University of Petrochemical Technology Electrical Engineering and Computer Science University of Ottawa

ISBN: (纸本)9781479913510

Nowadays, networks play an indispensable role in social life, and social networks have become a new advertising medium for offline activities. Previous studies of information diffusion or behavior spread over social networks have mostly focused on diffusion models and analysis of virtual interaction between online users, and very few of them focus on the propagation of real world activities in these social networks. To address this problem, we use data obtained from the Chinese largest recommendation social network - Douban, and study how the offline activities spread from one user to another through Douban. By using cascading subgraphs and diffusion trees, we break a whole cascade into local subgraphs. After analyzing the activities of about 1.47 million users, we observe the statistical and topological characteristics of these local cascading subgraphs. Next, we find the size and degree distributions of these cascading subgraphs and several common patterns of topology of local cascades. Moreover, we also have some other interesting discoveries, like the relation between the number of initial adopters and the final cascade size, and the underlying influences driving user behaviors. Finally, we propose a diffusion model that can generate information cascades that follow the patterns we have observed, and validate it by empirical analysis.

关键词： Social network Offline activity Information diffusion Underlying influence Generative models Social Networks cascades Social Media DIFFUSION MODELS Social Capital activity diffusion

来源：评论

学校读者我要写书评

暂无评论

Fast Coding Unit Depth Decision Algorithm for Interframe Coding in HEVC

Fast Coding Unit Depth Decision Algorithm for Interframe Cod...

引用

Data Compression Conference (DCC)

作者： Yongfei Zhang Haibo Wang Zhe Li Beijing Key Laboratory of Digital Media School of Computer Science and Engineering State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China Beijing Key Laboratory of Digital Media School of Computer Science and Engineering Beihang University Beijing China

ISBN: (纸本)9781467360371

As the next generation standard of video coding, the High Efficiency Video Coding (HEVC) achieves significantly better coding efficiency than all existing video coding standards. A Coding Unit (CU) quad tree concept is introduced to HEVC to improve the coding efficiency. Each CU node in quad tree will be traversed by depth first search process to find the best Coding Tree Unit (CTU) partition. Although this quad tree search process can obtain the best CTU partition, it is very time consuming, especially in interframe coding. To alleviate the encoder computation load in interframe coding, a fast CU depth decision method is proposed by reducing the depth search range. Based on the depth information correlation between spatio-temporal adjacent CTUs and the current CTU, some depths can be adaptively excluded from the depth search process in advance. Experimental results show that the proposed scheme provides almost 30% encoder time savings on average compared to the default encoding scheme in HM8.0 with only 0.38% bit rate increment in coding performance.

关键词： Encoding Correlation Video coding Educational institutions Standards Optimization Classification algorithms

来源：评论

学校读者我要写书评

暂无评论

On the Spatial-Temporal Reachability of DTNs

On the Spatial-Temporal Reachability of DTNs

引用

第二届中国互联网学术年会

作者： Chunhe XIA Cheng ZHANG Haiquan WANG Xiaojian LI State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China B Beijing Key Laboratory of Network Technology Beihang University Beijing China Beijing Key Laboratory of Network Technology Beihang University Beijing China College of Software Beijing Key Laboratory of Network Technology Beihang University Beijing China College of Computer

In DTNs,routing protocols use “store-carry-forward” approaches to complete the communication *** traditional “Connectivity” concept from the Internet ignores the possibility of opportunistic contacts in DTNs,this paper brings time dimension into consideration,proposes Spatial-Temporal Path,Spatial-Temporal Reachability and K-Reachability in order to better describe the whole communication process and “Eventual Transportability” of *** and simulation results are given to show the correctness of our ***,Spatial-Temporal Reachability and K-Reachability,which tell a network’s robustness in a quantitative fashion,are proved to be suitable for analyzing efficiency and routing performance of DTNs.

关键词： DTN Connectivity Spatial-Temporal Reachability

来源：评论

学校读者我要写书评

暂无评论

Multi-sensor data fusion and target location in pipeline monitoring and a pre-warning system based on multi-seismic sensors

Multi-sensor data fusion and target location in pipeline mon...

引用

International Conference on Pipelines and Trenchless technology 2012: Better Pipeline Infrastructure for a Better Life, ICPTT 2012

作者： Sun, Jiedi Zhang, Jinquan Wang, Xiaojun College of Information Science and Engineering Yanshan University No. 438 Hebei Avenue Qinhuangdao City Hebei Province China Key Laboratory for Computer Virtual Technology and System Integration of HeBei Province No. 438 Hebei Avenue Qinhuangdao City 066004 China Information Technology Unit of China Petrolium Communication Company No. 49 Jin'guang Road Langfang Hebei Province 065000 China

ISBN: (纸本)9780784412619

As a safe and economical method the pipeline is widely used to transport the oil and gas. At present, most of serious pipeline accidents are the artificial damages. The traditional leakage detection methods only infer the leakages by analyzing the parameters. The sensitivities are low and the leakage warning exclusively arrives after the leakage. The urgent problem is to detect the intrusions and locate the threat position. For this reason, we studied and developed a novel pipeline security monitoring and pre-warning system based on multi-seismic sensors. The system consists of many seismic geophones and data acquisition modules which are laid along the pipeline. The events such as footstep, car moving and the digging generate the seismic waves. These sensors and modules acquire the seismic signals. The empirical mode decomposition is used to acquire the IMFs (intrinsic mode functions). Then the IMF kurtosis features are normalized and used to recognize the different targets. In order to improve the individual target recognition accuracy, it proposes to fuse the identification results by using the Dempster-Shafer evidence theory and obtain the final judgment. If the target belongs to threat, the location will be finished. The time-frequency analysis method is used to process the seismic signals. The EMD outcomes are transformed by Hilbert-Huang Transform and then it can acquire the signal's instantaneous properties such as instantaneous frequency, phase and amplitude. In this paper we also discuss the localization procedures and put forward to a new passive localization method based on HHT and TDOA. The filed trails show the proposed methods work well. © 2013 American Society of Civil Engineers.

关键词： Hilbert-Huang transform

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Co-segmentation of Complex Image Set via Bi-harmonic Distance Governed Multi-level Deformable Graph Clustering

Unsupervised Co-segmentation of Complex Image Set via Bi-har...

引用

IEEE International Symposium on Multimedia

作者： Jizhou Ma Shuai Li Aimin Hao Hong Qin State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China Department of Computer Science Stony Brook University (SUNY Stony Brook) Stony Brook USA

Despite the recent success of extensive co-segmentation studies, they still suffer from limitations in accommodating multiple-foreground, large-scale, high-variability image set, as well as their underlying capability for parallel implementation. To improve, this paper proposes a bi-harmonic distance governed flexible method for the robust coherent segmentation of the overlapping/similar contents co-existing in image group, which is independent of supervised learning and any other user-specified prior. The central idea is the novel integration of bi-harmonic distance metric design and multi-level deformable graph generation for multi-level clustering, which gives rise to a host of unique advantages: accommodating multiple-foreground images, respecting both local structures and global semantics of images, being more robust and accurate, and being convenient for parallel acceleration. Critical pipeline of our method involves intrinsic content-coherent measuring, super-pixel assisted bottom-up clustering, and multi-level deformable graph clustering based cross-image optimization. We conduct extensive experiments on the iCoseg benchmark and Oxford flower datasets, and make comprehensive evaluations to demonstrate the superiority of our method via comparison with state-of-the-art methods collected in the MSRC database.

关键词： Measurement Image segmentation Image color analysis Manifolds Robustness Optimization Matrix converters

来源：评论

学校读者我要写书评

暂无评论

Multi-scale local features based on anisotropic heat difusion and global eigen-structure

引用

Science China(Information Sciences) 2013年第11期 57-66页

作者： LI Shuai QIN Hong HAO AiMin State Key Laboratory of Virtual Reality Technology and Systems Beihang University School of Biological Science and Medical Engineering Beihang University Department of Computer Science State University of New York at Stony BrookStony Brook NY 11794-4400 USA

Multi-scale local feature detection enables downstream registration and recognition tasks in medical image *** paper articulates a novel robust method for multi-scale local feature extraction on volumetric *** central idea is the elegant unifcation of local/global eigen-structures within the powerful framework of anisotropic heat ***,the local vector feld is constructed by way of Hessian matrix and its eigenvectors/***,anisotropic heat kernels are computed using the vector feld’s global graph *** local features are manifested as extrema across multiple time scales,serving as volumetric heat kernel *** tackle the computational challenge for massive volumetric data,we propose a multiresolution strategy for hierarchical feature extraction based on our feature-preserving down-sampling *** a result,heat kernels and local feature identifcation can be approximated at a coarser level frst,and then are pinpointed in a localized region at a fner *** novelty of this work lies at the initial heat design directly using local eigenvalue for anisotropic heat difusion across the volumetric *** conduct experiments on various medical datasets,and draw comparisons with 3D SIFT *** difusion property of our local features,which can be interpreted as random walks in statistics,makes our method robust to noise,and gives rise to intrinsic multi-scale characteristics.

关键词： volumetric heat kernel anisotropic difusion multi-scale local feature local/global eigen-structure volumetric image

来源：评论

学校读者我要写书评

暂无评论

An efficient collision detection algorithm of convex polygons based on Minkowski sum

引用

ICIC Express Letters 2013年第2期7卷 461-464页

作者： Geng, Qingjia Guo, Xijuan Zhang, Jianfei Zhang, Buying The Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province College of Information Science and Engineering Yanshan University No. 438 Hebei Ave. Qinhuangdao 066004 China College of Computer Hebei Normal University of Science and Technology No. 360 West Hebei St. Qinhuangdao 066004 China

Collision detection is a hot research topic in the field of path planning of mobile robot, virtual assembly simulation, and so on. Fast and accurate collision detection has become one of the most key technologies of restricting their development. The study method based on Minkowski sum is an effective method for accurate collision detection through accurate numerical calculations. This paper presents a new efficient collision detection algorithm of convex polygons based on Minkowski sum, which uses the minimum separation distance to detect whether two convex polygons collide or not. The algorithm's performance is also analyzed and verified by experiment in the paper. Compared with the traditional collision detection algorithms based on the Minkowski sum, the algorithm's calculation is simpler and execution performance is higher. © 2013 ISSN 1881-803X.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

A novel algorithm for outlier mining in the internet of things

引用

ICIC Express Letters 2013年第1期7卷 215-219页

作者： Chen, Wei Liu, Yongshan Zhang, Yang College of Information Science and Engineering Yanshan University No. 438 Hebei Ave. Qinhuangdao 066004 China The Key Laboratory for Computer Virtual Technology and System Integration of HeBei Province No. 438 Hebei Ave. Qinhuangdao 066004 China

Most of the traditional outlier mining algorithms are not suitable for high dimensional datasets. However, the dimensionality of the dataset in the field of the Internet of Things is high. Therefore, Hypergraph-based Outlier Mining (HOM) algorithm is proposed to solve the problem. Two different hypergraph models are constructed in the HOM algorithm. One is itemset hypergraph. One-itemset in transaction database is itemset hypergraph's vertices, and the transactions are itemset hypergraph's hyperedges. The other one is transaction hypergraph. The transactions are its vertices, and frequent itemsets are the hyperedges. The outliers are found by hypergraph partitioning. Experiments show that HOM algorithm can effectively find the outliers in high dimensional space. ©2013 ICIC International.

关键词： Statistics

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：