检索结果-内蒙古大学图书馆

International Conference on Intelligent Computation and Bio-Medical Instrumentation (ICBMI)

作者： Liantang Lou Hua Zeng Wenliang Gao Lingling Li School of Science Hubei Province Key Laboratory of Intelligent Robot Wuhan Institute of Technology Wuhan China Department of Computer Science & Application ZhengZhou Institute of Aeronautical Industry Management Zhengzhou China

In the paper, scale parameter of Schrödinger transform of image is discussed. First, the experiments show Schrödinger transformation of image can be seen as the result of primitive image shrinking inside and spreading outward at the center of object, like as interference wave, and the bigger the parameter a is, the more obvious the interference is, on the other hand, contour curves of object in the transformed image are similar to contour curves of object in the original image. Then, we explain the parameter a is the scale parameter of Schrödinger transform of image. Finally, we investigate the relation between propagation distance and the scale parameter a, size of image and object.

关键词： Manganese Equations Fourier transforms Quantum mechanics Mathematical model Kernel

来源：评论

学校读者我要写书评

暂无评论

A no-reference image quality evaluation based on power spectrum

A no-reference image quality evaluation based on power spect...

引用

3DTV Conference

作者： Yan Zhang Ping An Qiuwen Zhang Liquan Shen Zhaoyang Zhang School of Communication and Information Engineering Shanghai University China Department of Computer Science and Technology Anhui University of Finance and Economics China Key Laboratory of Advanced Displays and System Application Ministry of Education China

ISBN: (纸本)9781612841618

No-reference quality evaluation is more difficult because it does not refer to any image. However, in some cases, like virtual view images, can not find the reference image, no-reference method had to be used. With the free viewpoint video technology development and application, measuring the performance of the multiview video system is essential and virtual view image quality evaluation is one of the key technologies in the system. The characteristic of virtual view image quality evaluation is that most of the virtual view images haven't reference images and can't be assessed using general measures such as PSNR of full-reference. Therefore, this paper proposed a no-reference image quality evaluation method based on image power spectrum. Experimental results show that the proposed method is consistent with PSNR.

关键词： PSNR Image quality Three dimensional displays Transform coding Mathematical model Speckle

来源：评论

学校读者我要写书评

暂无评论

An improved depth map estimation for coding and view synthesis

An improved depth map estimation for coding and view synthes...

引用

IEEE International Conference on Image Processing

作者： Qiuwen Zhang Ping An Yan Zhang Liquan Shen Zhaoyang Zhang School of Communication and Information Engineering Shanghai University China Key Laboratory of Advanced Displays and System Application Ministry of Education China Department of Computer Science and Technology Anhui University of Finance and Economics China

Inaccuracy depth estimation may influence on depth coding and virtual view rendering in the free-viewpoint television (FTV) system, an improved depth map estimation is proposed to solve the problem for coding and view synthesis. Firstly, check the consistency of initial depth, and the influence of initial miss-matches is minimized by introduction of an additional adaptive matching error selection that penalizes the unreliable matches. Then according to certain criteria, the multi-reference depth maps are merged into one disparity map to improve the quality of disparity map. Finally, a multilateral filtering is used to preserve details in the depth map and simultaneously smooth the depths in occluded areas at object boundary, less texture and discontinuity regions. Experimental results show a significant improvement of the initial input depth maps and coding efficiency, as well as a reduction of view synthesis artifacts.

关键词： Estimation Image coding Rendering (computer graphics) Transform coding Three dimensional displays Filtering

来源：评论

学校读者我要写书评

暂无评论

A novel method on incremental information acquisition for deep web

引用

Journal of Convergence Information technology 2011年第6期6卷 383-389页

作者： Wei, Fang Wu-bin, Pan Zhi-Ming, Cui Jiangsu Engineering Center of Network Monitoring NanJing University of Information Science and Technology NanJing 210044 China School of Computer and Software Nanjing University of Information Science and Technology Nanjing 210044 China JiangSu Province Support Software Engineering R and D Center for Information Technology Application in Enterprise Suzhou China

Deep Web is autonomous, independently updating, and its data are always in a state of frequent update. However, the user always hopes to obtain the newest content in the current Web database. Different from previous research, this paper wants to emphasize the importance of updating frequency in the study of Deep Web information acquisition. And, an approach on incremental information acquisition based on logical reinforcement learning has been proposed. Then, we find in our research that under the same condition of constraint resources, the novel approach can improve the freshness of data, discovery efficiency of new data and the service quality of Deep Web information integration.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Improved multi-view depth estimation for view synthesis in 3D video coding

Improved multi-view depth estimation for view synthesis in 3...

引用

3DTV Conference

ISBN: (纸本)9781612841618

Multi-view depth estimation is an important part in the virtual view synthesis and depth map coding within the 3DV/FTV applications. However, existing depth estimation methods generally have difficulty to generate good depth results around object edges or in areas with less texture. To solve this problem, we propose an improved algorithm to obtain a smooth and accurate depth map for view synthesis in 3D video coding. The proposed method aims to preserve details in the depth map and simultaneously smooth depths in object boundary occluded area, less texture and discontinuity regions, to avoid blurring in the synthesized views. Experimental results show a significant improvement of the initial input depth maps and coding efficiency, as well as a reduction of view synthesis artifacts.

关键词： Estimation Pixel Three dimensional displays Encoding Rendering (computer graphics) Image coding Transform coding

来源：评论

学校读者我要写书评

暂无评论

Efficient rendering distortion estimation for depth map compression

Efficient rendering distortion estimation for depth map comp...

引用

IEEE International Conference on Image Processing

作者： Qiuwen Zhang Ping An Yan Zhang Zhaoyang Zhang School of Communication and Information Engineering Shanghai University China Key Laboratory of Advanced Displays and System Application Ministry of Education China Department of Computer Science and Technology Anhui University of Finance and Economics China

A depth map represents three-dimensional (3D) scene information and is used to synthesize virtual views in 3D video. Since the quality of synthesized virtual views highly depends on the quality of depth map, efficient depth compression is crucial to realize the 3D video system. However compressing depth map using existing video coding techniques yields unacceptable distortions while rendering virtual views. To solve this problem, we propose an efficient depth map compression method for the view rendering, a novel distortion metric base on view rendering distortions instead of distortion of depth map itself. First, we derive relationships between distortions in coded depth map and rendered view. Then, a region based video characteristics distortion model is proposed for precisely estimation distortion in view synthesis. Finally, experimental results have shown that 1.8 dB coding gain in terms of PSNR and subjective quality improvement of synthesized views are achieved by the proposed method.

关键词： Image coding Rendering (computer graphics) Three dimensional displays Cameras Geometry Encoding Estimation

来源：评论

学校读者我要写书评

暂无评论

PRINCIPAL COMPONENT ANALYSIS AND SELF-ORGANIZING MAP FOR VISUAL CLUSTERING OF MACHINE-PART CELL FORMATION IN CELLULAR MANUFACTURING SYSTEM

引用

Systems Research Forum 2011年第1期5卷 25-51页

作者： MANOJIT CHATTOPADHYAY PRANAB K. DAN SITANATH MAZUMDAR Department of Computer Application Pailan College of Management and Technology West Bengal India Department of Industrial Engineering and Management School of Engineering and Technology West Bengal University of Technology West Bengal India Social Welfare and Business Management Calcutta University West Bengal India Professor & Dean Faculty Counsil for P.G. Studies in Commerce.

The present paper attempts to generate visual clustering and data extraction of cell formation problem using both principal component analysis (PCA) and self-organizing map (SOM) from input of sequence based on the machine-part incidence matrix. Firstly, the focus is to utilize PCA for extracting high-dimensionality of input variables and project the dataset onto a 2D space. Secondly, the unsupervised competitive learning of SOM algorithm is used for data visualization and subsequently, to solve cell formation problem based on ordinal sequence data via the node cluster on the SOM map. Although the numerically illustrated results from dataset revealed that PCA has explained most of the cumulative variance of data but in reality, when the very large-dimensional cell formation problem based on sequence is available then, obtaining the clustering structure from PCA projection becomes very difficult. Most importantly, in the visual clustering of ordinal data, the use of U-matrix alone cannot be efficient to get the cluster structure but with color extraction, hit map, labeling via the SOM node map it becomes a powerful clustering visualization methodology and thus, the present research contribute significantly in the research of cellular manufacturing.

关键词： Cellular manufacturing operation sequence self-organizing map principal component analysis visual clustering U-matrix

来源：评论

学校读者我要写书评

暂无评论

TelosCAM: Identifying Burglar through Networked Sensor-Camera Mates with Privacy Protection

TelosCAM: Identifying Burglar through Networked Sensor-Camer...

引用

Real-Time Systems Symposium (RTSS)

作者： Shaojie Tang Xiang-Yang Li Haitao Zhang Jiankang Han Guojun Dai Cheng Wang Xingfa Shen Department of Computer Science Illinois Institute of Technology Chicago IL USA TNLIST School of Software Tsinghua University China Beijing Key Laboratory of Intelligent Telecommunication Software and Multimedia Beijing University of Posts and Telecommunications China Institute of Computer Application Technology Hangzhou Dianzi University Hangzhou China Department of Computer Science Tongji University Shanghai China

We present TelosCAM, a networking system that integrates wireless module nodes (such as TelosB nodes) with legacy surveillance cameras to provide storage-efficient and privacy-aware services of accurate, real time tracking and identifying of the burglar who stole the property. In our system, a property owner will have a wireless module node (called secondary module) attached to the property that s/he wants to protect. The secondary wireless module node will not store any personal information about the owner, nor any specific information about the property to be protected. Each user of the system will also have a unique wireless module node (called primary module) that contains some security information about the user, thus should be privately held by the user and be kept to the user always. Once a tracking process is triggered in privacy preserving manner, the secondary module will start sending out the alarm signal periodically. The alarm signal will be captured by some surveillance wireless module, integrated with existing surveillance cameras. Using the trajectory information provided by the secondary wireless module node, and the videos captured by the surveillance cameras, our system will then automatically pinpoint a burglar (e.g., a person or a car) that is more likely to carry the stolen property. Our extensive evaluation of the system shows that we can find the burglars with surprisingly high accuracy under various experiment settings, with significantly reduced storage-requirement of the legacy video surveillance system. It also can help the police to catch the burglars more efficiently by providing critical images or videos containing the burglars.

关键词： Wireless communication Videos Cameras Surveillance Communication system security Wireless sensor networks Trajectory

来源：评论

学校读者我要写书评

暂无评论

引用

中国计算机科学前沿 2010年第4期4卷 500-515页

作者： Ye TIAN Bangchuan LIU Zhenhua HE Anhui Province Key Laboratory on High Performance Computing and Application School of Computer Science and TechnologyUniversity of Science and Technology of ChinaHefei 230027China

With the success of lnternet video-on-demand (VoD) streaming services, the bandwidth required and the financial cost incurred by the host of the video server becoming extremely large. Peer-to-peer (P2P) networks and proxies are two common ways for reducing the server workload. In this paper, we consider a peer-assisted Internet VoD system with proxies deployed at domain gateways. We formally present the video caching problem with the objectives of reducing the video server workload and avoiding inter-domain traffic, and we obtain its optimal solution. Inspired by theoretical analysis, we develop a practical protocol named PopCap for Internet VoD services. Compared with previous work, PopCap does not require additional infrastructure support, is inexpensive, and able to cope well with the characteristic workloads of Interact VoD services. From simulationbased experiments driven by real-world data sets from YouTube, we find that PopCap can effectively reduce the video server workload, therefore provides a superior performance regarding the video server's traffic reduction.

关键词： Internet video-on-demand (VoD) peer-to-peer (P2P) caching algorithm/protocol design and analysis

来源：评论

学校读者我要写书评

暂无评论

Heuristic information retrieval using variable identifiers in mobile ad-hoc networks

Heuristic information retrieval using variable identifiers i...

引用

3rd IEEE International Conference on Intelligent Networking and CollaborativeSystems, INCoS 2011

作者： Kume, Kazuki Ohnishi, Kei Tsukamoto, Kazuya Yamamura, Shinya Nagata, Akira Graduate School of Computer Science and Systems Engineering Kyushu Institute of Technology 680-4 Kawazu Iizuka-shi Fukuoka 820-8502 Japan Fujitsu Kyushu Network Technologies Limited Fujitsu Kyushu R and D Center 2-2-1 Momochihama Sawara-ku Fukuoka 814-8588 Japan Network Application Engineering Laboratories Ltd. JPR Hakata Building 1-4-4 Hakataekimae Hakata-ku Fukuoka 812-0011 Japan

ISBN: (纸本)9780769545790

We observe through simulations that an information sharing scheme using variable identifiers in mobile ad-hoc networks, which we previously proposed, enables us to heuristically find desired information by having identifiers varied. In the information sharing, people create identifiers that represent their interest, and information published by the people are probabilistically propagated using distances between identifiers of the people. The identifiers of the people dynamically change depending on people surrounding each person. Under a situation that an identifier is variable, we set how many times people obtained desired information to be an observation item. Also, we consider a process that people heuristically find desired information into a simulation model and set how many times people obtain such information to be an observation item. In simulations, we show examples of observation for these items. © 2011 IEEE.

关键词： Mobile ad hoc networks

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：