检索结果-内蒙古大学图书馆

IEEE International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)

作者： Nattachai Watcharapinchai Supavadee Aramvith Supakorn Siddhichai Sanparith Marukatat Digital Signal Processing Research Laboratory Department of Electrical Engineering Chulalongkom University Bangkok Thailand National Electronics and Computer Technology Center Pathumthani Thailand

The problem of automatic object categorization is investigated under the proposed bag of feature object categorization framework. The framework consists of feature detection and representation which uses the scale invariant feature transform (SIFT) as local feature and bag of feature model to represent the image. Learning process utilizes k-NN (k-nearest neighbour). In this paper, we propose the dimensionality reduction of SIFT using principal component analysis (PCA) on each object category to reduce computational complexity and memory requirement during training process. Experimental results show that our proposed technique can reduce the dimension of SIFT up to around 80% with the same average precision compared to baseline technique without our proposed method.

关键词： Principal component analysis computer vision Histograms Digital signal processing Computational complexity Video compression Testing Training data Vocabulary Feature extraction

来源：评论

学校读者我要写书评

暂无评论

On the absolute orientation problem in computer vision

On the absolute orientation problem in computer vision

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Rodney G. Roberts Daniel W. Repperger Department of Electrical and Computer Engineering Florida State University Tallahassee FL USA 711 HPW AFRL/RHCV Air Force Research Laboratory OH USA

An important problem in computer vision is to determine the orientation of a rigid body in an image. This can be accomplished by matching points or line segments that naturally appear on the object. Several elegant and computationally fast algorithms based on the singular value decomposition and quaternions have been introduced to solve this problem. In this article, the authors first examine the important special case of identifying the attitude of 2D objects and introduce a particularly elegant solution based on the mathematical structure of the complex plane. Motivated by this simple solution to the 2D case, a new derivation of the 3D case based on the polar decomposition is presented. This derivation is in many ways more natural than previous derivations, particularly when the model and data contain no noise.

关键词： computer vision Singular value decomposition Transmission line matrix methods Cybernetics Military computing Laboratories Image segmentation Quaternions Object recognition Least squares methods

来源：评论

学校读者我要写书评

暂无评论

A vision of smart transmission grids

A vision of smart transmission grids

引用

IEEE General Meeting Power& Energy Society

作者： Zhenhua Jiang Fangxing Li Wei Qiao Hongbin Sun Hui Wan Jianhui Wang Yan Xia Zhao Xu Pei Zhang Department of Electrical and Computer Engineering University of Miami Coral Gables FL USA Department of Electrical Engineering and Computer Science University of Tennessee Knoxville TN USA Department of Electrical Engineering University of Nebraska Lincoln Lincolnshire NE USA Department of Electrical Engineering Tsinghua University Beijing China Lane Department of Computer Science and Electrical Engineering West Virginia University Morgantown WV USA Decision and Information Sciences Division Argonne National Laboratory Argonne IL USA Department of Electrical Engineering Howard University College of Medicine Washington D.C. DC USA Centre of Electric Technology Technical University of Denmark Lyngby Denmark Electric Power Research Institute Inc. USA

Modern power grid is required to become smarter in order to provide an affordable, reliable, and sustainable supply of electricity. Under such circumstances, considerable activities have been carried out in the U.S. and Europe to formulate and promote a vision for the development of the future smart power grids. However, the majority of these activities only placed emphasis on the distribution grid and demand side; while the big picture of the transmission grid in the context of smart grids is still unclear. This paper presents a unique vision for the future smart transmission grids in which the major features that these grids must have are clearly identified. In this vision, each smart transmission grid is regarded as an integrated system that functionally consists of three interactive, smart components, i.e., smart control centers, smart transmission networks, and smart substations. The features and functions of each of the three functional components as well as the enabling technologies to achieve these features and functions are discussed in detail in the paper.

关键词： Smart grids Power systems Sun Communication system control Substations Production Solids Pollution Energy resources Hurricanes

来源：评论

学校读者我要写书评

暂无评论

Large scale natural image classification by sparsity exploration

Large scale natural image classification by sparsity explora...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Changhu Wang Shuicheng Yan Hong-Jiang Zhang MOE-MS Key Laboratory of MCC University of Science and Technology China Department of Electrical and Computer Engineering National University of Singapore Singapore Microsoft Research Advanced Technology Center Beijing China

We consider in this paper the problem of large scale natural image classification. As the explosion and popularity of images in the Internet, there are increasing attentions to utilize millions of or even billions of these images for helping image related research. Beyond the opportunities brought by unlimited data, a great challenge is how to design more effective classification methods under these large scale scenarios. Most of existing attempts are based on k-nearest-neighbor method. However, in spite of the optimistic performance in some tasks, this strategy still suffers from that, one single fixed global parameter k is not robust for different object classes from different semantic levels. In this paper, we propose an alternative method, called lscr 1 -nearest-neighbor, based on a sparse representation computed by lscr 1 -minimization. We first treat a testing sample as a sparse linear combination of all training samples, and then consider the related samples as the nearest neighbors of the testing sample. Finally, we classify the testing sample based on the majority of these neighbors' classes. We conduct extensive experiments on a 1.6 million natural image database on different semantic levels defined based on WordNet, which demonstrate that the proposed lscr 1 -nearest-neighbor algorithm outperforms k-nearest-neighbor in two aspects: 1) the robustness of parameter selection for different semantic levels, and 2) the discriminative capability for large scale image classification task.

关键词： Large-scale systems Image classification Robustness computer vision Signal processing Testing Signal processing algorithms Layout Image recognition Information retrieval

来源：评论

学校读者我要写书评

暂无评论

Multi-label sparse coding for automatic image annotation

Multi-label sparse coding for automatic image annotation

引用

Conference on computer vision and Pattern Recognition (CVPR)

作者： Changhu Wang Shuicheng Yan Lei Zhang Hong-Jiang Zhang MOE-MS Key Laboratory of MCC University of Science and Technology China Department of Electrical and Computer Engineering National University of Singapore Singapore Microsoft Research Asia China Microsoft Advanced Technology Center Beijing China

In this paper, we present a multi-label sparse coding framework for feature extraction and classification within the context of automatic image annotation. First, each image is encoded into a so-called supervector, derived from the universal Gaussian Mixture Models on orderless image patches. Then, a label sparse coding based subspace learning algorithm is derived to effectively harness multi-label information for dimensionality reduction. Finally, the sparse coding method for multi-label data is proposed to propagate the multi-labels of the training images to the query image with the sparse ℓ 1 reconstruction coefficients. Extensive image annotation experiments on the Corel5k and Corel30k databases both show the superior performance of the proposed multi-label sparse coding framework over the state-of-the-art algorithms.

关键词： Image coding Image reconstruction Feature extraction Image databases Image retrieval Humans Image segmentation Asia Scattering Image representation

来源：评论

学校读者我要写书评

暂无评论

Multiplicative nonnegative greph embedding

Multiplicative nonnegative greph embedding

引用

Conference on computer vision and Pattern Recognition (CVPR)

作者： Changhu Wang Zheng Song Shuicheng Yan Lei Zhang Hong-Jiang Zhang MOE-MS Key Laboratory of MCC University of Science and Technology China Department of Electrical and Computer Engineering National University of Singapore Singapore Microsoft Research Asia China Microsoft Advanced Technology Center Beijing China

In this paper, we study the problem of nonnegative graph embedding, originally investigated in [J. Yang et al., 2008] for reaping the benefits from both nonnegative data factorization and the specific purpose characterized by the intrinsic and penalty graphs. Our contributions are two-fold. On the one hand, we present a multiplicative iterative procedure for nonnegative graph embedding, which significantly reduces the computational cost compared with the iterative procedure in [14] involving the matrix inverse calculation of an M-matrix. On the other hand, the nonnegative graph embedding framework is expressed in a more general way by encoding each datum as a tensor of arbitrary order, which brings a group of byproducts, e.g., nonnegative discriminative tensor factorization algorithm, with admissible time and memory cost. Extensive experiments compared with the state-of-the-art algorithms on nonnegative data factorization, graph embedding, and tensor representation demonstrate the algorithmic properties in computation speed, sparsity, discriminating power, and robustness to realistic image occlusions.

关键词： Tensile stress Asia Computational efficiency Encoding Iterative algorithms Costs Embedded computing Robustness Psychology Humans

来源：评论

学校读者我要写书评

暂无评论

computer vision localization based on pseudo-satellites

Computer vision localization based on pseudo-satellites

引用

IEEE National Conference on Aerospace and Electronics (NAECON)

作者： Kevin R. Huggins Michael A. McGrath Yuan F. Zheng Robert L. Ewing Ohio State Uinversity Columbus OH USA Ohio State University Columbus OH US Department of Electrical and Computer Engineering Ohio State Uinversity Columbus OH USA US Air Force Research Laboratory OH USA

ISBN: (纸本)9781424444946

In following the ¿Signals of Opportunity¿ theme of the NAECON '09 Grand Challenge, we explore using computer-vision techniques for localization and orientation techniques to complement navigation via the pseudo-satellite technique proposed in. The proposed approach is not affected by the strength of the microwave, and is more accurate than the conventional time of arrival approaches. Methods based on limited and varying information of markers is discussed. Simple applications and experimentation based on augmenting a motorized wheelchair for vision applications is discussed.

关键词： computer vision Global Positioning System Satellite broadcasting Orbital calculations Navigation Receivers Clocks Force sensors Application software Cameras

来源：评论

学校读者我要写书评

暂无评论

Meeting report: the terabase metagenomics workshop and the vision of an Earth microbiome project

引用

Standards in genomic sciences 2010年第3期3卷 243-8页

作者： Jack A Gilbert Folker Meyer Dion Antonopoulos Pavan Balaji C Titus Brown Christopher T Brown Narayan Desai Jonathan A Eisen Dirk Evers Dawn Field Wu Feng Daniel Huson Janet Jansson Rob Knight James Knight Eugene Kolker Kostas Konstantindis Joel Kostka Nikos Kyrpides Rachel Mackelprang Alice McHardy Christopher Quince Jeroen Raes Alexander Sczyrba Ashley Shade Rick Stevens Argonne National Laboratory Argonne USA Department of Ecology and Evolution University of Chicago Chicago USA College of Engineering Michigan State University East Lansing USA Department of Microbiology and Cell Science University of Florida Gainesville USA Department of Evolution and Ecology University of California Davis USA DOE Joint Genome Institute Walnut Creek USA Illumina Saffron Walden UK NERC Centre for Ecology and Hydrology UK Department of Computer Science and Department of Electrical & Computer Engineering Virginia Tech Blacksburg USA Department of Cancer Biology and Translational Science Institute Wake Forest University Winston-Salem USA Center for Bioinformatics ZBIT Tübingen University Tübingen Germany Earth Sciences Division Lawrence Berkeley National Laboratory Berkeley USA Department of Chemistry and Biochemistry Boulder USA Roche-454 Branford USA Seattle Children’s Hospital Seattle USA School of Civil and Environmental Engineering and School of Biology Georgia Institute of Technology Atlanta USA The Florida State University Tallahassee USA Department of Algorithmic Bioinformatics Heinrich-Heine University Düsseldorf Germany Max-Planck Research Group for Computational Genomics and Epidemiology Max-Planck-Institut fur Informatik Saarbrücken Germany Department of Civil Engineering University of Glasgow Glasgow UK Department of Molecular and Cellular Interactions VIB - University of Brussels Brussels Belgium Department of Molecular Cellular and Developmental Biology Yale University New Haven USA

Between July 18(th) and 24(th) 2010, 26 leading microbial ecology, computation, bioinformatics and statistics researchers came together in Snowbird, Utah (USA) to discuss the challenge of how to best characterize the microbial world using next-generation sequencing technologies. The meeting was entitled "Terabase Metagenomics" and was sponsored by the Institute for Computing in Science (ICiS) summer 2010 workshop program. The aim of the workshop was to explore the fundamental questions relating to microbial ecology that could be addressed using advances in sequencing potential. Technological advances in next-generation sequencing platforms such as the Illumina HiSeq 2000 can generate in excess of 250 billion base pairs of genetic information in 8 days. Thus, the generation of a trillion base pairs of genetic information is becoming a routine matter. The main outcome from this meeting was the birth of a concept and practical approach to exploring microbial life on earth, the Earth Microbiome Project (EMP). Here we briefly describe the highlights of this meeting and provide an overview of the EMP concept and how it can be applied to exploration of the microbiome of each ecosystem on this planet.

关键词： Microbial Community Microbial Genome Metabolic Flux Analysis Metagenomic Data Human Microbiome Project

来源：评论

学校读者我要写书评

暂无评论

Building detection from aerial images using invariant color features and shadow information

Building detection from aerial images using invariant color ...

引用

2008 23rd International Symposium on computer and Information Sciences, ISCIS 2008

作者： Sirmaçek, Beril Ünsalan, Cem Computer Vision Research Laboratory Department of Electrical and Electronics Engineering Yeditepe University Istanbul 34755 Turkey

ISBN: (纸本)9781424428816

Robust detection of buildings is an important part of the automated aerial image interpretation problem. Automatic detection of buildings enables creation of maps, detecting changes, and monitoring urbanization. Due to the complexity and uncontrolled appearance of the scene, an intelligent fusion of different methods gives better results. In this study, we present a novel approach for building detection using multiple cues. We benefit from segmentation of aerial images using invariant color features. Besides, we use the edge and shadow information for building detection. We also determine the shape of the building by a novel method. © 2008 IEEE.

关键词： Buildings

来源：评论

学校读者我要写书评

暂无评论

Efficient three-view triangulation based on 3D optimization

Efficient three-view triangulation based on 3D optimization

引用

2008 19th British Machine vision Conference, BMVC 2008

作者： Nordberg, Klas Computer Vision Laboratory Department of Electrical Engineering Linköping University Sweden

ISBN: (纸本)9781901725360

Triangulation of a 3D point from two or more views can be solved in several ways depending on how perturbations in the image coordinates are dealt with. A common approach is optimal triangulation which minimizes the total L2 reprojection error in the images, corresponding to finding a maximum likelihood estimate of the 3D point assuming independent Gaussian noise in the image spaces. Computational approaches for optimal triangulation have been published for the stereo case and, recently, also for the three-view case. In short, they solve an independent optimization problem for each 3D point, using relatively complex computations such as finding roots of high order polynomials or matrix decompositions. This paper discuss three-view triangulation and reports the following results: (1) the 3D point can be computed as multi-linear mapping (tensor) applied on the homogeneous image coordinates, (2) the set of triangulation tensors forms a 7-dimensional space determined by the camera matrices, (3) given a set of corresponding 3D/2D calibration points, the 3D residual L1 errors can be optimized over the elements in the 7-dimensional space, (4) using the resulting tensor as initial value, the error can be further reduced by tuning the tensor in a two-step iterative process, (5) the 3D residual L1 error for a set of evaluation points which lie close to the calibration set is comparable to the three-view optimal method. In summary, three-view triangulation can be done by first performing an optimization of the triangulation tensor and once this is done, triangulation can be made with 3D residual error at the same level as the optimal method, but at a much lower computational cost. This makes the proposed method attractive for real-time three-view triangulation of large data sets provided that the necessary calibration process can be performed.

关键词： Tensors

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：