检索结果-内蒙古大学图书馆

FGR 2006: 7th International Conference on Automatic Face and Gesture Recognition

作者： Li, Ying Lai, J.H. Yuen, Pong C. Department of Mathematics SUN YAT-SEN University China School of Informatics Guangdong University of Foreign Studies China Department of Electronics and Communication Engineering School of Information Science and Technology SUN YAT-SEN University China Guangdong Province Key Laboratory of Information Security China Department of Computer Science Hong Kong Baptist University Hong Kong Hong Kong

ISBN: (纸本)0769525032

This paper proposed a multi-template ASM algorithm addressing facial feature points detection under nonlinear shape variation of facial images with various kinds of expression. By adding texture information, adopting asymmetric sampling strategy for the feature points on outer contour of face, building multiple templates and integrating local ASM and global ASM, experimental results show that the proposed multi-template ASM algorithm outperforms traditional single template ASM. © 2006 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Robust moving object segmentation in the compressed domain for H.264/AVC video stream

Robust moving object segmentation in the compressed domain f...

引用

25th PCS: Picture Coding Symposium 2006, PCS2006

作者： Yang, Gaobo Yu, Shengfa Zhang, Zhaoyang Network and Information Security Lab School of Computer and Communication Hunan University Changsha Hunan 410082 China School of Electronic Science and Engineering National University of Defense Technology Changsha Hunan 410073 China Key Laboratory of Advanced Displays and System Application Shanghai University Ministry of Education Shanghai 200072 China

ISBN: (纸本)300018726X

Moving object segmentation in the compressed domain plays an important role in many real-time applications, e.g. video indexing, video surveillance, etc. H.264/AVC is the up-to-date video coding standard, which employs several new coding tools and provides a different video format. In this paper, a robust spatio-temporal segmentation approach to extract moving objects in the compressed domain for H.264 video stream is proposed. Coarse moving objects are firstly extracted from the motion vector field through the MRF classification process. Spatial segmentation is based on the HT coefficient, which is used to refine the object boundary of temporal segmentation results. Fusion of spatio-temporal segmentation is based on region projection based labeling technique. Further edge refinement is performed to smooth the object boundaries. The performance of the proposed approach is illustrated by simulation carried on several test sequences. Experimental results show that the proposed approach can provide the visually similar results as by using spatial domain process with much less computational complexity.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Narrowband audio hiding algorithm based on human auditory system

引用

Beijing Youdian Daxue Xuebao/Journal of Beijing University of Posts and Telecommunications 2006年第SUPPL. 2期29卷 101-104+121页

作者： Yuan, Kai-Guo Yang, Ya-Tao Zhang, Ru Niu, Xin-Xin Yang, Yi-Xian Information Security Center Beijing University of Posts and Telecommunications Beijing 100876 China State Key Laboratory of Switching and Networking Beijing University of Posts and Telecommunications Beijing 100876 China Department of Communication Engineering Beijing Electronic Science and Technology Institute Beijing 100070 China

After studying about human auditory system and narrowband communications system model, a narrowband audio hiding algorithm based on human auditory system was presented. A lot of experiments proved that the algorithm had strong robustness to prevent many attacks from such as D/A, A/D, channel noise and so on. In time domain, frequency domain, especially for hearing, it had high transparence. What's more, the algorithm, whose hiding capacity reached up to 20 bit/s, had intelligent blind detection property and can be used in many domains.

关键词： Audio systems

来源：评论

学校读者我要写书评

暂无评论

News video story segmentation

News video story segmentation

引用

International Conference on Multimedia Modeling (MMM)

作者： Yong Fang Xiaofei Zhai Jingwang Fan Electronic Science and Technology Institution Key Laboratory of Security and Secrecy of Information Beijing Beijing China School of Telecommunication Engineering Beijing University of Posts and Telecommunications Beijing China School of Communication Engineering Yanshan University슠 Qinhuangdao China

This paper presents a two-level framework for news video segmentation. Our framework is established-based upon a similar framework as in. We extended the original framework by adding rule-based pre-segmentation module, similarity measurement module and new features. We perform decision tree at the shot level and HMM (hidden Markov models) analysis at the story level, respectively. Experiment result with a training set of 24 hours (967 story units) news video from CCTV-9 (China Central TV-International) and a testing set of 24 hours (779 story units) news video from several TV-channels show that our semi-automatic system can achieve 81.5% of F1 value in the case of CCTV-9

关键词： Face detection Gunshot detection systems Decision trees Hidden Markov models Layout Feature extraction Classification tree analysis Weather forecasting Laboratories information security

来源：评论

学校读者我要写书评

暂无评论

Research on Restraining Low Frequency Oscillation with Flywheel Energy Storage System

Research on Restraining Low Frequency Oscillation with Flywh...

引用

International Conference on Power System technology (POWERCON)

作者： Yun Zhong Jiancheng Zhang Gengyin Li Zhiyuan Chen School of Information Engineering University of Nanchang Baoding Jiangxi China Department of Electrical power Engineering North China Electric Power University Baoding Hebei China Key Laboratory of Power System Protection and Dynamic Security Monitoring and Control under Ministry of Education North China Electric Power University Baoding Hebei China Baoding Zhongli Power Science and Technology Development Company Limited Baoding Hebei China

Low frequency oscillations in the interconnected power systems are observed all around the world. Besides conventional PSS to suppress Low frequency oscillation, there are other modern FACTS devices to damp oscillation, among which flywheel energy storage system (FESS) is a comparative valid way. The theory on restraining low frequency oscillation used by flywheel energy storage system is described through transfer function diagram and complex torque coefficient. A numerical model of flywheel energy storage asynchronous motor controlled by VVVF inverter is derived from its mathematical model in alpha-beta coordinate system. Then the total model eigenvalue is analyzed. Based on analysis, attach control strategy using two parallel independent parts for active power control and reactive power control is designed in FESS to restrain low frequency oscillation. The calculation result shows that flywheel energy storage system is an effective way to restrain low frequency oscillation and enhance power system dynamic performance.

关键词： Frequency Flywheels Energy storage Power system interconnection Transfer functions Torque Numerical models Inverters Mathematical model Power system modeling

来源：评论

学校读者我要写书评

暂无评论

A new general framework for shot boundary detection and key-frame extraction 7

A new general framework for shot boundary detection and key-...

引用

7th ACM SIGMM International Workshop on Multimedia information Retrieval, MIR 2005

作者： Feng, Huamin Fang, Wei Liu, Sen Fang, Yong Key Laboratory of Security and Secrecy of Information Beijing Electronic Science and Technology Institution Beijing100070 China School of Telecommunications Engineering Beijing University of Posts and Telecommunications Beijing100876 China Communication Engineering College YanShan University Qinhuangdao066004 China

ISBN: (纸本)1595932445

Video shot boundary detection is an important step in many video applications. Since the rapid development of video editing technology, especially, the extensive use of sub-window in news video, the original method of video segmentation cannot efficiently detect the video shot boundary caused by special video technique. In this paper, previous temporal multi-resolution analysis (TMRA) work was extended by first using SVM (Supported Vector Machines) classify the video frames within a sliding window into normal frames, gradual transition frames and CUT frames, then clustering the classified frames into different shot categories. The experimental result on ground truth, which has about 21 hours (10,250 shots) news video clip, shows that the new framework has relatively good accuracy for the detection of shot boundaries. It basically resolves the difficulties of shot boundaries detection caused by sub-window technique in video. The framework also greatly improves accuracy of gradual transitions of shot. Copyright © 2005 ACM.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Toward an actualization of social intelligence in human and robot collaborative systems

Toward an actualization of social intelligence in human and ...

引用

2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE Cat. No.04CH37566)

作者： H. Nakajima S. Brave H. Maldonado M. Arao Y. Morishima R. Yamada C. Nass S. Kawaji Control Technology Laboratory OMRON Corporation Kyoto Japan Division of Languages International Christian University Tokyo Japan Department of Communication University of Stanford CA USA School of Education University of Stanford CA USA Department of Systems Engineering and Information Science Kumamoto University Kumamoto Japan

As robot technology is evolving and creating a social community between humans and robots, it is necessary to research and develop a new type of intelligence, which we refer to as "social intelligence''. Social intelligence enables natural and socially appropriate interactions. Its importance is gaining a growing interest among not just the human-computer interaction researchers but also robot technology researchers and developers. This article discusses the definition, importance, and benefits of social intelligence in human and robot collaborative systems. The virtual social environment is employed to implement an experimental social intelligence system because of its low cost and high flexibility. Software robots (i.e. agents) with the social intelligence model have been implemented by featuring an emotion model and a personality model under the virtual environment. The social intelligence model that handles affective responses is based on the theories of personality, emotion, and human-media interaction such as cognitive appraisal theory and media equation. The experiment was conducted with the virtual learning collaborative system to examine the effect of the social intelligence model in the collaborative system. The data showed that the users had more positive impressions about the usefulness and the application and learning experience when the cooperative agent displayed some social responses with personality and emotions. It should be noted here that the cooperative agent did not provide any explicit assistance for the human user such as giving clues and showing answers, and yet the user's evaluation on the usefulness of the learning system was influenced by the social agent. The data also suggested that the cooperative agent contributed to the effectiveness of the learning system.

关键词： Intelligent robots Collaboration Learning systems Human robot interaction Intelligent systems Costs Cognitive robotics Intelligent agent Virtual environment Appraisal

来源：评论

学校读者我要写书评

暂无评论

The functionality of human-machine collaboration systems - mind model and social behavior

The functionality of human-machine collaboration systems - m...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： H. Nakajima R. Yamada S. Brave Y. Morishima C. Nass S. Kawaji Control Technology Laboratory OMRON Corporation Kyoto Japan Department of Communication Center for the Study of Language and Information Stanford CA Division of Languages Intenational Christian University Tokyo Japan Department of Systems Engineering and Information Science Kumamoto University Kumamoto Japan

As machine evolution continues, human-machine collaboration systems are increasing their importance. In this paper, a social and intelligent agent is discussed as a strategy for improving the effectiveness and efficiency of human-machine collaboration. The proposed approach uses an embedded mind model, which enables agents to interact with the human user consistently, context-dependently, and socially. The relationship between the mind model, personality, and social behavior of the agents is studied through implementation of a prototype system as an e-learning application.

关键词： Man machine systems Collaboration Humans communication system control Collaborative work Laboratories Context modeling control systems Data mining Intelligent agent

来源：评论

学校读者我要写书评

暂无评论

On existence of 2-level autocorrelation sequences realized from the decimation-Hadamard transformation

On existence of 2-level autocorrelation sequences realized f...

引用

IEEE International Symposium on information Theory

作者： G. Gong Z. Dai S.W. Golomb Department of Electrical and Computer Engineering University of Waterloo Waterloo Canada State Key Laboratory of Information Security Graduate School (Beijing) University of Science and Technology Beijing China Communication Sciences Institute Electrical Engineering-Systems University of Southern California Los Angeles CA USA

We investigate the decimation-Hadamard transform (DHT) applied to 2-level autocorrelation sequences. We present the kth-order DHT by a matrix representation and show that odd order DHT cannot realize any 2-level autocorrelation sequences. We provide two interesting experimental results including one for the second-order DHT of the generalized GWM sequences.

关键词： Autocorrelation Laboratories Computer security information security Galois fields Binary sequences

来源：评论

学校读者我要写书评

暂无评论

Weight hierarchies of extremal non-chain ternary codes of dimension 4

Weight hierarchies of extremal non-chain ternary codes of di...

引用

IEEE International Symposium on information Theory

作者： Wende Chen T. Klove Laboratory of Systems and Control Institute of Systems Science Academy of Mathematics and Systems Science Chinese Academy of Sciences China Key State Laboratory of Information Security Graduate School of Academia Sinica Chinese Academy and Sciences Beijing China Department of Informatics Bergen High Technology Center University of Bergen Bergen Norway

The weight hierarchy of a linear [n,k;q] code C over GF(q) is the sequence (d/sub 1/,d/sub 2/,...,d/sub k/) where d/sub r/ is the smallest support of an r-dimensional subcode of C. An [n,k;q] code is extremal non-chai... 详细信息

ISBN: (纸本)0780371232

关键词： Hamming weight Councils Laboratories information security Informatics

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：