检索结果-内蒙古大学图书馆

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Changsong Shen Sidney S. Fels James J. Little Department of Electrical and Computer Engineering University of British Columbia Canada Department of Computer Science University of British Columbia Canada

This paper presents our progress on OpenVL -a novel software architecture to address efficiency through facilitating hardware acceleration, reusability and scalability for computer vision. A logical image understanding pipeline is introduced to allow parallel processing. As well, we discuss our middleware -VLUT that enables applications to operate transparently over a heterogeneous collection of hardware implementations. OpenVL works as a state machine, with an event-driven mechanism to provide users with application-level interaction. Various explicit or implicit synchronization and communication methods are supported among distributed processes in the logical pipelines. The intent of OpenVL is to allow users to quickly and easily recover useful information from multiple scenes across various software environments and hardware platforms. We implement two different human tracking systems to validate the critical underlying concepts of OpenVL.

关键词： Software architecture Computer vision Hardware Pipelines Acceleration Scalability parallel processing Middleware Application software Layout

来源：评论

学校读者我要写书评

暂无评论

Evolving Fuzzy Rule-based Classifiers

Evolving Fuzzy Rule-based Classifiers

引用

IEEE Symposium on Computational Intelligence in image and Signal processing, CiiSP

作者： Plamen Angelov Xiaowei Zhou Frank Klawonn Department of Communication Systems InfoLab21 Lancaster University Lancaster UK Department of Computer Science University of Applied Sciences Wolfenbuettel Germany

A novel approach to on-line classification based on fuzzy rules with an open/evolving structure is introduced in this paper. This classifier can start `from scratch', learning and adapting to the new data samples or from an initial rule-based classifier that can be updated based on the new information contained in the new samples. It is suitable for real-time applications such as classification streaming data, robotic applications, e.g., target and landmark recognition, real-time machine health monitoring and prognostics, fault detection and diagnostics, etc. Each prototype is a data sample that represents the focal point of a fuzzy rule per class and is selected based on the data density by an incremental and evolving procedure. This approach is transparent, linguistically interpretable, and applicable to both fully unsupervised and partially supervised learning. It has been validated by two well known benchmark problems and by real-life data in a parallel paper. The contributions of this paper are: i) introduction of the concept of evolving (open structure) classification (eClass) of streaming data; ii) experiments with well known benchmark classification problems (Iris and wine reproduction data sets)

关键词： Fuzzy systems Data mining Knowledge based systems Fault detection Classification tree analysis Signal processing Learning systems Decision trees Bayesian methods Evolution (biology)

来源：评论

学校读者我要写书评

暂无评论

ASIC: Supervised Multi-class Classification using Adaptive Selection of Information Components

ASIC: Supervised Multi-class Classification using Adaptive S...

引用

International Conference on Semantic Computing

作者： Zongxing Xie Thiago Quirino Mei-Ling Shyu Shu-Ching Chen Department of Electrical and Computer Engineering University of Miami Coral Gables FL USA Distributed Multimedia Information System Laboratory School of Computing and Information Sciences Florida International University Miami FL USA

In this paper, a supervised multi-class classification approach called Adaptive Selection of Information Components (ASIC) is presented. ASIC has the facilities to (i) handle both numerical and nominal features in a data set, (ii) pre-process the training data set to accentuate the spatial differences among the classes in the training data set to reduce further computational load requirements, and (iii) conduct supervised classification with the C-RSPM (Collateral Representative Subspace Projection Modeling) approach. Experimental results on a variety of data sets have shown that the proposed ASIC approach outperforms other well-known supervised classification methods such as C4.5, KNN, SVM, MLP, BN, RF, Logistic, and C-RSPM, with higher classification accuracy, lower training and classification times, and reduced memory storage and processing power requirements.

关键词： Application specific integrated circuits Principal component analysis Support vector machines Support vector machine classification distributed computing Training data Radio frequency Logistics Data mining image retrieval

来源：评论

学校读者我要写书评

暂无评论

基于网格采样的深度图像表面特征提取算法

引用

中国图象图形学报 2007年第6期12卷 1091-1097页

作者：孙晓兰赵慧洁北京航空航天大学仪器科学与光电工程学院北京100083

深度图像的高级特征提取是3维视觉一个重要研究领域。为了提高对大量离散3维数据的处理速度,简化算子结构,本文提出一种新的方法,将单目或多目结构光传感器采集的离散3维数据点云转换成深度图像形式,使z方向代表深度,并实现x、y方向数... 详细信息

深度图像的高级特征提取是3维视觉一个重要研究领域。为了提高对大量离散3维数据的处理速度,简化算子结构,本文提出一种新的方法,将单目或多目结构光传感器采集的离散3维数据点云转换成深度图像形式,使z方向代表深度,并实现x、y方向数据的规则网格采样。接着提出一种深度图像分割算法,先对整幅图像进行边缘提取,得到阶跃和褶皱两种边缘,采用主成分分析法(PCA)通过计算欧氏距离得到面的法线方向和方向间的夹角。经过两类传感器采集到的大量图像实验证明,该算法明显优于单纯的边缘或者区域算法,具有良好的抗噪声性能,满足并行在线测量的要求,并且不受物体形状的约束,可以应用于3D模型重建、机器人自主导航、逆向工程、文物数字化等多个3维视觉领域。

关键词：网格化深度图像分割特征提取主成分分析

来源：评论

学校读者我要写书评

暂无评论

An on-sensor bit-serial column-parallel processing architecture for high-speed discrete Fourier transform

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS ii-EXPRESS BRIEFS 2006年第8期53卷 642-646页

作者： Eki, Tatsuya Kawahito, Shoji Tadokoro, Yoshiaki Yamatake Corp Adv Automat Co Fujisawa 2518522 Japan Shizuoka Univ Elect Res Inst Hamamatsu Shizuoka 4328011 Japan Toyohashi Univ Technol Dept Informat & Comp Sci Toyohashi Aichi 4418580 Japan

This brief presents a discrete Fourier transform (DFT) processor based on a bit-serial column-parallel processing architecture suitable for integrating it on CMOS image sensors. Using a column-parallel A/D converter (ADC) array, column-line sensor outputs of the two-dimensional image array are digitized. The ADC outputs are sliced to one bit and are given to the bit-serial column-parallel DFT processor from the MSB to the LSB. A high-speed and cost-effective implementation can be expected. In the case of 256 x 256-point DFT for 8-b image data, the processing time is estimated to be 2 ins at a clock frequency of 100 MHz, which corresponds to the 500-frames/s real-time processing.

关键词： CMOS image sensor discrete Fourier transform (DFT) distributed arithmetic functional image sensor

来源：评论

学校读者我要写书评

暂无评论

Area efficient FIR filters for high speed FPGA implementation

引用

IEE PROCEEDINGS-VISION image AND SIGNAL processing 2006年第6期153卷 711-720页

作者： Macpherson, K. N. Stewart, R. W. Univ Strathclyde Dept Elect & Elect Engn Glasgow G1 1XW Lanark Scotland

A new algorithm that synthesises multiplier blocks with low hardware requirement suitable for implementation as part of full-parallel finite impulse response (FIR) filters is presented. Although the techniques in use are applicable to implementation on application-specific integrated circuit (ASIC) and Structured ASIC technologies, analysis is performed using field programmable gate array (FPGA) hardware. Fully pipelined, full-parallel transposed-form FIR filters with multiplier block were generated using the new and previous algorithms, implemented on an FPGA target and the results compared. Previous research in this field has concentrated on minimising multiplier block adder cost but the results presented here demonstrate that this optimisation goal does not minimise FPGA hardware. Minimising multiplier block logic depth and pipeline registers is shown to have the greatest influence in reducing FPGA area cost. In addition to providing lower area solutions than existing algorithms, comparisons with equivalent filters generated using the distributed arithmetic technique demonstrate further area advantages of the new algorithm.

关键词： full-parallel finite impulse response filters FPGA implementation Digital arithmetic methods field programmable gate arrays field programmable gate array hardware adders multiplier block logic FIR filters pipeline arithmetic pipeline registers logic circuits Digital filters multiplying circuits Logic and switching circuits Logic circuits multiplier block adder distributed arithmetic technique

来源：评论

学校读者我要写书评

暂无评论

A parallel mutual information based image registration algorithm for applications in remote sensing 4th

引用

4th International Symposium on parallel and distributed processing and Applications

作者： Du, Yunfei Zhou, Haifang Wang, Panfeng Yang, Xuejun Liu, Hengzhu Natl Univ Def Technol Sch Comp Changsha 410073 Hunan Peoples R China

ISBN: (纸本)9783540680673

image registration is a classical problem that addresses the problem of finding a geometric transformation that best aligns two images. Since the amount of multisensor remote sensing imagery are growing tremendously, the search for matching transformation with mutual information is very time-consuming and tedious, and fast and automatic registration of images from different sensors has become critical in the remote sensing framework. So the implementation of automatic mutual information based image registration methods on high performance machines needs to be investigated. First, this paper presents a parallel implementation of a mutual information based image registration algorithm. It takes advantage of cluster machines by partitioning of data depending on the algorithm's peculiarity. Then, the evaluation of the parallel registration method has been presented in theory and in experiments and shows that the parallel algorithm has good parallel performance and scalability.

关键词： image registration

来源：评论

学校读者我要写书评

暂无评论

parallel implementation of MPEG-2 Video decoder

Parallel implementation of MPEG-2 Video decoder

引用

Conference on Multimedia on Mobile Devices ii

作者： Sarkar, A Saha, K Maiti, S North Carolina State Univ Raleigh NC 27695 USA STMicroelect Pvt Ltd Greater Noida Uttar Pradesh India

ISBN: (纸本)0819461148

The demand for real-time MPEG decoding is growing in multimedia applications. This paper discusses a hardware-software co-design for MPEG-2 Video decoding and describes an efficient parallel implementation of the software module. We have advocated the usage of hardware for VLD since it is inherently serial and efficient hardware implementations are available. The software module is a macro-block level parallel implementation of the IDCT and Motion Compensation. The parallel implementation has been achieved by dividing the picture, into two halves for 2-processor implementation and into four quadrants for 4-processor implementation, and assigning the macro-blocks present in each partition to a processor. The processors perform IDCT and Motion Compensation in parallel for the macro-blocks present in their allotted sections. Thus each processor displays 1/no_of_processors of a picture frame. This implementation minimizes the data dependency among processors while performing the Motion Compensation since data dependencies occur only at the edges of the divided sections. Load balancing among the processors has also been achieved, as all the processors perform computation on an equal number of macro-blocks. Apart from these, the major advantage is that the time taken to perform the IDCT and Motion Compensation reduces linearly with an increase in number of processors.

关键词： Data communications Video image processing Telecommunications Data processing distributed computing Video processing Computing systems Computer simulations Multimedia

来源：评论

学校读者我要写书评

暂无评论

A parallel unmixing algorithm for hyperspectral images

A parallel unmixing algorithm for hyperspectral images

引用

Conference on Intelligent Robots and Computer Vision XXIV - Algorithms, Techniques, and Active Vision

作者： Robila, Stefan A. Maciak, Lukasz G. Montclair State Univ Dept Comp Sci Ctr Imaging & Opt RI 301 Montclair NJ 07043 USA

ISBN: (纸本)0819464821

We present a new algorithm for feature extraction in hyperspectral images based on source separation and parallel computing. In source separation, given a linear mixture of sources, the goal is to recover the components by producing an unmixing matrix. In hyperspectral imagery, the mixing transform and the separated components can be associated with endmembers and their abundances. Source separation based methods have been employed for target detection and classification of hyperspectral images. However, these methods usually involve restrictive conditions on the nature of the results such as orthogonality (in Principal Component Analysis - PCA and Orthogonal Subspace Projection - OSP) of the endmembers or statistical independence (in Independent Component Analysis - ICA) of the abundances nor do they fully satisfy all the conditions included in the Linear Mixing Model. Compared to this, our approach is based on the Nonnegative Matrix Factorization (NMF), a less constraining uninixing method. NMF has the advantage of producing positively defined data, and, with several modifications that we introduce also ensures addition to one. The endmember vectors and the abundances are obtained through a gradient based optimization approach. The algorithm is further modified to run in a parallel environment. The parallel NMF (P-NMF) significantly reduces the time complexity and is shown to also easily port to a distributed environment. Experiments with in-house and Hydice data suggest that NMF outperforms ICA, PCA and OSP for unsupervised endmember extraction. Coupled with its parallel implementation, the new method provides an efficient way for unsupervised unmixing further supporting our efforts in the development of a real time hyperspectral sensing environment with applications to industry and life sciences.

关键词： hyperspectral images blind source separation Nonnegative Matrix Factorization Linear Mixing Model parallel processing image processing

来源：评论

学校读者我要写书评

暂无评论

parallelization of a discrete radiosity method using scene division

引用

On the Move Confederated International Conference on CoopIS/DOA/GADA, and ODBASE

作者： Zrour, Rita Feschet, Fabien Malgouyres, Remy Univ Auvergne IUT LAIC F-63172 Aubiere France

ISBN: (纸本)3540482741

We present in this article a parallelization of a discrete radiosity method, based on scene division and achieved on a cluster of workstations. This method is based on discretization of surfaces into voxels and not into patches like most of the radiosity methods do. Voxels are stocked into visibility lists representing the space partition into discrete lines and allowing mutually visible neighbour voxels to exchange their radiosities. The parallelization distributes the scene among the processors by dividing it into parts. Exchanges of radiosity values are accomplished between neighbourhood voxels belonging to a same list but located on different processors. This parallelization improved time and distributed memory offering thus the capability to deal with large scenes.

关键词： parallel processing systems

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：