检索结果-内蒙古大学图书馆

Proceedings of the 22nd Southeastern symposium on System Theory

作者： Duncan, B.D. Pieper, R.J. Poon, T.-C. Optical Image Process Lab Virginia Polytech Inst & State Univ Blacksburg VA USA

ISBN: (纸本)0818620382

Real-time image processing has been achieved by using an optical scanning system in conjunction with electronic hardware. A report of experimental results on edge extraction and image thresholding for transmissive objects is presented. Advantages and limitations of the techniques are identified. The results indicate that real-time edge extraction and image thresholding can be satisfactorily achieved.

关键词： image processing

来源：评论

学校读者我要写书评

暂无评论

Achieving fault tolerance on grids with the CPPC framework and the GridWay metascheduler

Achieving fault tolerance on grids with the CPPC framework a...

引用

22nd International symposium on computer Architecture and High Performance Computing, SBAC-PAD 2010

作者： Cores, Iv´an Rodríguez, Gabriel Martín, María J. González, Patricia Computer Architecture Group University of A Coruña Spain

ISBN: (纸本)9780769542164

Grids have brought a significant increase in the number of available resources that can be provided to applications. In the last decade, an important effort has been made to develop middleware that provides grids with functionalities related to application execution. However, support for faulttolerant executions is either lacking or limited. This paper presents an experience to endow with fault tolerance support parallel executions on grids through the integration of CPPC, a checkpointing tool for parallel applications, and GridWay, a well-known metascheduler provided with the Globus Toolkit. Since both tools are not immediately compatible, a new architecture, called CPPC-GW, has been designed and implemented to allow for the transparent execution of CPPC applications through GridWay. The performance of the solution has been evaluated using the NAS Parallel Benchmarks. Detailed experimental results show the low overhead of the approach. © 2010 IEEE.

关键词： Grid computing

来源：评论

学校读者我要写书评

暂无评论

Parallel image processing on a transputer-based system

Parallel image processing on a transputer-based system

引用

Proceedings of the 22nd Southeastern symposium on System Theory

作者： Peng, Antai Kawamura, Kazuhiko Center for Intelligent Syst Vanderbilt Univ Nashville TN USA

ISBN: (纸本)0818620382

The problem addressed is how to use transputer networks for image processing. As is well known, SIMD (single instruction/multiple data) or MIMD (multiple instruction/multiple data) architectures are very useful in parallel computing. The authors describe how to use transputers as an SIMD or MIMD machine to implement parallel image processing. Several image-processing algorithms, including Laplacian of Gaussian, edge detection, region labeling, generalized Hough transform, and thinning, have been tested. The authors maintain that transputer-based systems are suitable for real-time image processing. It is also pointed out that, compared with the other parallel machines, transputer systems can provide high performance and more flexibility with relatively low cost.

关键词： image processing

来源：评论

学校读者我要写书评

暂无评论

Cluster CV2: a computer Vision Approach to Spatial Identification of Data Clusters 22

Cluster CV2: a Computer Vision Approach to Spatial Identific...

引用

22nd symposium on image, Signal processing and Artificial Vision (STSIVA)

作者： Contreras Contreras, Ghiordy Ferney Delgado, Byron Medina Ibarra, Dinael Guevara de Castro, Cristiano Leite Acevedo Jaimes, Brayan Rene Univ Francisco de Paula Santander Elect & Elect Cucuta Colombia Univ Fed Minas Gerais Elect Engn Belo Horizonte MG Brazil

ISBN: (纸本)9781728114910

This work shows a novel application based on techniques of computer Vision and Machine Learning to identify k clusters into a data set with overlapping issue. Used in area of unsupervised data clustering, where separation between groups is tricky. Through pair-to-pair distance calculations upon original data, is gotten a Distances Matrix as representative information of data. This matrix contains visual information, then using morphological operators extract relevant features for individual identification of groups in data set. Next, matrix decomposition performed to covariance matrix, being calculation of data elements for each cluster in order to project data into a new linear space. So, overlapping and separation distances among clusters are corrected without loss information. Results present correct identification of k clusters, without loss information, and eliminating data overlap. Clustering validation metrics such as Silhouette and Precision was used to test the methodology.

关键词： Unsupervised clustering data overlapping computer vision machine learning

来源：评论

学校读者我要写书评

暂无评论

The evaluation of video retrieval methods from temp oral characteristics

The evaluation of video retrieval methods from temp oral cha...

引用

Proceedings of the 22nd Picture Coding symposium: PCS-2001

作者： Takahashi, Hidekazu Kaneda, Kazufumi Kodama, Mei Yamashita, Hideo Hiroshima University 3-10-31 Kagamiyama Higashi-Hiroshima 739-0046 Japan

Today video searching systems are required for interactive video communication service and computer network system. It is the most effective for visual communication. Then, we consider the method of extracting image and matching the feature tables in video searching system. In this paper, we pay attention to temporal characteristics in video retrieval methods. So we propose the temporal approach which grouping parameters of the correlation value are used in order to reduce matching time. As these characteristics, we used the luminance frequency. Next matching methods are verified from the viewpoints of the processing time and matching precision between query images and database images. Finally, our proposed method is evaluated from the viewpoint of probability model by simulation results, and it is shown that grouping methods are particularly useful.

关键词： image retrieval

来源：评论

学校读者我要写书评

暂无评论

computer vision system for tracking players in sports games 1

Computer vision system for tracking players in sports games

引用

1st International Workshop on image and Signal processing and Analysis (IWISPA 2000) in conjunction with the 22nd International Conf on Informat Technol Interfaces

作者： Pers, J Kovacic, S Univ Ljubljana Fac Elect Engn Ljubljana 1000 Slovenia

ISBN: (纸本)9539676924

The development of computer Vision system for tracking players in indoor team games is presented. Several image processing and tracking methods are described, along with camera calibration and lens distortion correction. The output of the system consists of spatio-temporal trajectories of the players, which can be further processed and analyzed by sport experts. In some critical situations the automatic tracking process must be manually interrupted. To correct miss-trackings, human supervision is required. Some experimental results are presented as well.

关键词： object tracking human motion analysis camera calibration handball

来源：评论

学校读者我要写书评

暂无评论

Multiple-image-based restoration for motion blur with non-uniform point spread function

引用

IEICE TRANSACTIONS ON FUndAMENTALS OF ELECTRONICS COMMUNICATIONS And computer SCIENCES 2008年第8期E91A卷 1924-1934页

作者： Patanukhom, Karn Nishihara, Akinori Tokyo Inst Technol Ctr Res & Dev Educ Technol Tokyo 1528552 Japan Tokyo Inst Technol Dept Commun & Integrated Syst Tokyo 1528552 Japan

A blind image restoration for non-linear motion blurs with non-uniform point spread functions based on multiple blurred versions of a same scene is proposed. The restoration is separately considered as identification and deconvolution problems. In the proposed identification process, an identification difficulty is introduced to rank an order of blur identification. A blurred image with the lowest identification difficulty is initially identified by using a single-image-based scheme. Then, other images are identified based on a cross convolution relation between each pair of blurred images. In addition, an iterative feedback scheme is applied to improve the identification results. For the deconvolution process, a spatial adaptive scheme using regional optimal terminating points is modified from a conventional iterative deconvolution scheme. The images are decomposed into sub-regions based on smoothness. The regional optimal terminating points are independently assigned to suppress a noise in smooth regions and sharpen the image in edgy regions. The optimal terminating point for each region is decided by considering a discrepancy error. Restoration examples of simulated and real world blurred images are experimented to demonstrate the performance of the proposed method.

关键词： blur identification motion blur image restoration multiple image

来源：评论

学校读者我要写书评

暂无评论

Differential energy based watermarking algorithm using wavelet tree group modulation (WTGM) and Human Visual System

引用

IEICE TRANSACTIONS ON FUndAMENTALS OF ELECTRONICS COMMUNICATIONS And computer SCIENCES 2008年第8期E91A卷 1961-1973页

作者： Tsai, Min-Jen Shen, Chang-Hsing Natl Chiao Tung Univ Inst Informat Management Hsinchu 300 Taiwan

Wavelet tree based watermarking algorithms are using the wavelet coefficient energy difference for copyright protection and ownership verification. WTQ (Wavelet Tree Quantization) algorithm is the representative technique using energy difference for watermarking. According to the cryptanalysis on WTQ, the watermark embedded in the protected image can be removed successfully. In this paper, we present a novel differential energy watermarking algorithm based on the wavelet tree group modulation structure, i.e. WTGM (Wavelet Tree Group Modulation). The wavelet coefficients of host image are divided into disjoint super trees (each super tree containing two sub-super trees). The watermark is embedded in the relatively high-frequency components using the group strategy such that energies of sub-super trees are close. The employment of wavelet tree structure, sum-of-subsets and positive/negative modulation effectively improve the drawbacks of the WTQ scheme for its insecurity. The integration of the HVS (Human Visual System) for WTGM provides a better visual effect of the watermarked image. The experimental results demonstrate the effectiveness of our algorithm in terms of robustness and imperceptibility.

关键词： copyright protection Human Visual System image watermarking wavelet wavelet tree quantization

来源：评论

学校读者我要写书评

暂无评论

Fluid simulation on surfaces in the GPU

Fluid simulation on surfaces in the GPU

引用

25th Conference on graphics, Patterns and images, SIBGRAPI 2012

作者： Carvalho, Leonardo Andrade, Maria Velho, Luiz IMPA Rio de Janeiro Brazil UFAL Maceió Brazil

ISBN: (纸本)9780769548296

In this paper we present a method to simulate fluids on smooth surfaces of arbitrary topology using a graphics processing unit (GPU). To do this we use the parametrization of Cat mull-Clark subdivision surfaces and obtain the metric information of the distortion caused by this parametrization, so we can calculate differential operators of functions defined on this surface. Then the Navier-Stokes equations on surfaces are solved in the domain of parametrization of each patch. This process can be done in parallel for each point in the discretization of the surface, so the GPU implementation can heavily increase the velocity of computation. © 2012 IEEE.

关键词： graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Autonomous Foraging with SARSA-based Deep Reinforcement Learning 22

Autonomous Foraging with SARSA-based Deep Reinforcement Lear...

引用

22nd symposium on Virtual and Augmented Reality (SVR)

作者： Mesquita, Anderson Nogueira, Yuri Vidal, Creto Cavalcante-Neto, Joaquim Serafim, Paulo Fed Univ Ceara UFC Dept Comp DC Fortaleza Ceara Brazil Inst Atlantic Fortaleza Ceara Brazil

ISBN: (纸本)9781728192314

This work proposes a system capable of autonomous behavior using computer Vision and Deep Reinforcement Learning. These learned behaviors are those related to foraging in an environment that has food and poisons distributed throughout a scenario. We apply the Deep Learning framework for color image processing. These images simulate the agent's vision. The foraging task is modeled as a reinforcement learning problem, in which an input constituted by raw pixels is processed by a convolutional neural network resulting in a set of actions. A Deep Learning algorithm based on SARSA was used. During training, the agent selects the actions based on a probability distribution called Softmax. The objective of this work is to present an agent capable of searching for food and distinguishing it from poisons through continuous learning and without the help or external intervention from humans. The experiments show that the agent is able to distinguish food from poisons without hints or markings in its vision input. This highlights the advantages of combining Deep Learning with reinforcement learning for the foraging problem. The results of this work form an initial basis for understanding the relationship among autonomy, cognition, and perception in artificial agents.

关键词： autonomy deep learning reinforcement learning computer vision

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：