检索结果-内蒙古大学图书馆

International Conference on Pattern Analysis and Intelligent Robotics (ICPAIR)

作者： Seyed Mehdi Moghadas Hossein Pourghasem Rasoul Amirfattahi Department of Electrical Engineering Islamic Azad University Najafabad Iran Digital Signal Processing Research Laboratory Department of Electrical and Computer Engineering Isfahan University of Technology Isfahan Iran

A new quantization method is proposed in this paper. This method is useful for enhancement of compression quality when each kind of neural network is used to compress the image. By quantizing the image with the proposed method, the numbers of samples which must be reconstructed by neural network is reduced. This causes a remarkable increase in quality of the reconstructed image. For testing the proposed method we use autoassociative transform coding and by merging it with the proposed quantization method a new compression algorithm is obtained. Then results of compression by the merged method are compared with some previous works. Obtained results show that the proposed compression algorithm increases the compression quality of the images remarkably. Compression time and complexity in the merged method is also better than JPEG and make it suitable for the systems with low processor and hardware implementation.

关键词： Image coding Biological neural networks Image reconstruction Transform coding Neurons PSNR Training

来源：评论

学校读者我要写书评

暂无评论

Bayesian Spatiotemporal Multitask Learning for Radar HRRP Target Recognition

引用

IEEE Transactions on Signal processing 2011年第7期59卷 3182-3196页

作者： Lan Du Penghui Wang Hongwei Liu Mian Pan Feng Chen Zheng Bao Department of Electrical and Computer Engineering Duke University Durham NC USA National Laboratory of Radar Signal Processing Xidian University Xi'an China School of Electronic Information and Electrical Engineering Shanghai Jiaotong University Shanghai China

A Bayesian dynamic model based on multitask learning (MTL) is developed for radar automatic target recognition (RATR) using high-resolution range profile (HRRP). The aspect-dependent HRRP sequence is modeled using a truncated stick-breaking hidden Markov model (TSB-HMM) with time-evolving transition probabilities, in which the spatial structure across range cells is described by the hidden Markov structure and the temporal dependence between HRRP samples is described by the time evolution of the transition probabilities. This framework imposes the belief that temporally proximate HRRPs are more likely to be drawn from similar HMMs, while also allowing for possible distant repetition or “innovation”. In addition, as formulated the stick-breaking prior and MTL mechanism are employed to infer the number of hidden states in an HMM and learn the target-dependent states collectively for all targets. The form of the proposed hierarchical model allows efficient variational Bayesian (VB) inference, of interest for large-scale problems. To validate the formulation, example results are presented for an illustrative synthesized dataset and our main application-RATR, for which we consider the measured HRRP data. For the latter, we also make comparisons to the model with the independent state-transition statistics and some other existing statistical models for radar HRRP data.

关键词： Hidden Markov models Data models Radar Bayesian methods Target recognition Analytical models

来源：评论

学校读者我要写书评

暂无评论

Toward Optimal Deployment of Communication-Intensive Cloud Applications

Toward Optimal Deployment of Communication-Intensive Cloud A...

引用

IEEE International Conference on Cloud Computing, CLOUD

作者： Pei Fan Ji Wang Zibin Zheng Michael R. Lyu National Laboratory for Parallel & Distributed Processing National University of Defense Technology Changsha China Department of Computer Science & Engineering Chinese University of Hong Kong Hong Kong China

Strongly promoted by the leading industrial companies, cloud computing becomes increasingly popular in re-cent years. The growth rate of cloud computing surpasses even the most optimistic predictions. A cloud application is a large-scale distributed system that consist a lot of distributed cloud nodes. How to make optimal deployment of cloud applications is a challenging research problem. When deploying a cloud application to the cloud environment, cloud node ranking is one of the most important approaches for selecting optimal cloud nodes for the cloud application. Traditional ranking methods usually rank the cloud nodes based on their QoS values, without considering the communication performance between cloud nodes. However, such kind of node relationship is very important for the communication-intensive cloud applications (e.g., Message Passing Interface (MPI) programs), which have a lot of communications between the selected cloud nodes. In this paper, we propose a novel clustering-based method for selecting optimal cloud nodes for deploying communication-intensive applications to the cloud environment. Our method not only takes into account the cloud node qualities, but also the communication performance between different nodes. We deploy several well-known MPI programs on a real-world cloud and compare our method with other methods. The experimental results show the effectiveness of our cluster-based method.

关键词： Time factors Cloud computing Benchmark testing Quality of service Servers Clustering algorithms Databases

来源：评论

学校读者我要写书评

暂无评论

Model-based multiview stereo via level sets with statistical shape prior

Model-based multiview stereo via level sets with statistical...

引用

IEEE International Conference on Image processing

作者： Moumen El-Melegy Nagi Al-Ashwal Aly A. Farag Electrical Engineering Department Assiut University Asyut Egypt Computer Vision and Image Processing Laboratory University of Louisville KY USA

In this paper, we propose a methodology to incorporate 3D shape prior information in multi-view stereo. This is important for applications that deal with specific category of objects. The methodology is based on a new formulation of a level-set based energy functional. Shape prior model is then embedded in the energy functional to allow the reconstruction of an object with shape variations consistent with the training model examples. Several experiments to evaluate the proposed methodology are presented.

关键词： Shape Image reconstruction Level set Stereo vision Solid modeling Training Ellipsoids

来源：评论

学校读者我要写书评

暂无评论

LD: A Polynomial Time Algorithm for Tree Isomorphism

引用

Procedia engineering 2011年 15卷 2015-2020页

作者： Baida Zhang Yuhua Tang Junjie Wu Shuai Xu National laboratory for Parallel and Distributed Processing School of Computer National University of Defense Technology Changsha Hunan 410073 P. R. China Department of Information Engineering Academy of Armored Force Engineering Beijing 100000 P.R.China

Graph isomorphism problem has always been mathematics and engineering technology community concern, the reason mainly from two aspects: First, in theory, is generally believed that the problem is NP-complete problem; Second, the graph isomorphism the problem with good prospects, in chemistry, operations research, computer science, electronics, network theory has applications in many fields, but the exponential complexity of the algorithm and the algorithm itself makes the limitations applicable to the object involved with complex graphics the application of structure is difficult to determine the start. In this paper, class tree is proposed based on the node to delete the exact graph isomorphism problem, you can quickly determine the graph isomorphism problem, and theoretical analysis and experiments show that the algorithm can determine the class in polynomial time tree isomorphism problem.

关键词： Graph Isomorphism LD algorithm

来源：评论

学校读者我要写书评

暂无评论

Depth estimation in integral images by anchoring optimization techniques

Depth estimation in integral images by anchoring optimizatio...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： D. Zarpalas I. Biperis E. Fotiadou E. Lyka P. Daras M. G. Strintzis Informatics and Telematics Institute Thessaloniki Greece Information Processing Laboratory Department of Electrical and Computer Engineering Aristotle University of Thessaloniki Thessaloniki Greece

This paper presents two algorithms for estimating depth from integral images, which capture a scene by using multiple lenses, offering anaglyph depictions. The first algorithm involves the 3-D integral imaging grid formed by casting rays inversely through the lenses used to capture the integral image. In this formulation, depth estimation is equivalent to finding correspondences on the ray-crossing points. The second algorithm follows the depth-through disparity approach. In this case, a stereo-like minimization problem is formulated which is handled by the graph cuts method. The novelty of the proposed paper lies in constraining the optimization procedures with the “anchor points”. This results in enhanced estimation accuracy, while eliminating the optimization complexity. Anchor points is a set of reliable reference points, detected by applying a robust local image descriptor to viewpoint images, called self-similarity descriptor. The performance of both algorithms is evaluated on a synthetic integral image database in comparison with another state-of-the-art algorithm.

关键词： Lenses Estimation Imaging Arrays Optimization Reliability Accuracy

来源：评论

学校读者我要写书评

暂无评论

On gas detection and concentration estimation via mid-IR-based gas detection system analysis model

On gas detection and concentration estimation via mid-IR-bas...

引用

Annual Conference on Information Sciences and Systems (CISS)

作者： Yi Xin Joel M. Morris Communications and Signal Processing Laboratory (CSPL) Computer Science and Electrical Engineering Department University of Maryland Baltimore County Catonsville MD USA

In recent decades, Laser-based spectroscopy (LAS) has been used in a wide range of research and application fields due to developments in laser technology and infrared spectroscopy. A particular application of interest is mid-IR laser-based gas detection systems for health and environment assessment. In this paper, we use our statistical analysis model for a generic mid-IR pulsed-laser gas detection system to predict trace gas detection and concentration estimation performance, and their sensitivity to system parameters. Based on PNNL data and the Beer-Lambert law, we use the three main spectral peaks of a trace gas, as the basis for gas detection, and use the relationship between gas transmittance β, molar absorptivity ε, concentration, and the sample-mean measurement, x N , from the photodetector, as the basis for concentration estimation using a standard confidence interval method.

关键词： Gas lasers Estimation Optical pulses Photodetectors Laser modes Cavity resonators

来源：评论

学校读者我要写书评

暂无评论

Combining global and local features for food identification in dietary assessment

Combining global and local features for food identification ...

引用

IEEE International Conference on Image processing

作者： Marc Bosch Fengqing Zhu Nitin Khanna Carol J. Boushey Edward J. Delp School of Electrical and Computer Engineering Video and Image Processing Laboratory USA Department of Foods and Nutrition Purdue University West Lafayette IN USA

Many chronic diseases, such as heart diseases, diabetes, and obesity, can be related to diet. Hence, the need to accurately measure diet becomes imperative. We are developing methods to use image analysis tools for the identification and quantification of food consumed at a meal. In this paper we describe a new approach to food identification using several features based on local and global measures and a “voting” based late decision fusion classifier to identify the food items. Experimental results on a wide variety of food items are presented.

关键词： Image color analysis Visualization Feature extraction Image segmentation Color Conferences Vectors

来源：评论

学校读者我要写书评

暂无评论

Social focus of attention as a time function derived from multimodal signals

Social focus of attention as a time function derived from mu...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Danil Korchagin Hamid Reza Abutalebi Idiap Research Institute Martigny Switzerland Speech Processing Research Laboratory (SPRL) Electrical and Computer Engineering Department Yazd University Yazd Iran

In this paper, we present the results of a study on the social focus of attention as a time function derived from the multisource multimodal signals, recorded by different personal capturing devices during social events. The core of the approach is based on fission and fusion of multichannel audio, video and social modalities to derive the social focus of attention. The results achieved to date on 16+ hours of real-life data prove the feasibility of the approach.

关键词： Media Estimation Signal processing Correlation Delay effects Conferences Synchronization

来源：评论

学校读者我要写书评

暂无评论

Localization of multiple simultaneous sound sources in reverberant conditions using blind source separation methods

Localization of multiple simultaneous sound sources in rever...

引用

International Symposium on Artificial Intelligence and Signal processing (AISP)

作者： Hedieh Heli Hamid Reza Abutalebi Speech Processing Research Laboratory (SPRL) Electrical and Computer Engineering Department Yazd University Yazd Iran Elec and Computer Engineering Department Yazd University Yazd Iran Idiap Research Institute Martigny Switzerland

In this paper, we address the problem of multiple simultaneous sources localization by means of Blind Source Separation (BSS)-based algorithms. Considering BSS demixing filters as some blind null beamformer and producing an acoustical map from them, source localization can then be achieved by identifying the local minima of this acoustical map. To improve the performance of this method in reverberant environments, we have proposed to replace the demixing filter with one corresponds to only the direct path. This is done by keeping only the largest coefficient in each demixing filter and neglecting the other coefficients. Furthermore, the proposed method reduces the computational complexity. Our experiments demonstrate the efficiency of the proposed method in the localization of multiple simultaneous sound sources in reverberant environments.

关键词： Source separation Sensors Microphones Arrays Finite impulse response filter Reverberation Frequency domain analysis

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：