检索结果-内蒙古大学图书馆

15th International Conference on Artificial Intelligence and Soft Computing (ICAISC)

作者： Qiao, Wenbao Creput, Jean-Charles Univ Technol Belfort Montbeliard IRTES SET Belfort France

ISBN: (纸本)9783319393841

As an extension of using image segmentation to do stereo matching, firstly, by using self-organizing map (som) and K-means algorithms, this paper provides a self-distributed segmentation method that allocates segments according to image's texture changement where in most cases depth discontinuities appear. Then, for stereo, under the fact that the segmentation of left image is not exactly same with the segmentation of right image, we provide a matching strategy that matches segments of left image to pixels of right image as well as taking advantage of border information from these segments. Also, to help detect occluded regions, an improved aggregation cost that considers neighbor valid segments and their matching characteristics is provided. For post processing, a gradient border based median filter that considers the closest adjacent valid disparity values instead of all pixels' disparity values within a rectangle window is provided. As we focus on real-time execution, these time-consumming works for segmentation and stereo matching are executed on a massively parallel cellular matrix GPU computing model. Finaly, we provide our visual dense disparity maps before post processing and final evaluation of sparse results after post-processing to allow comparison with several ranking methods top listed on Middlebury.

关键词： Stereo image segmentation SOM Self-distributed segments

来源：评论

学校读者我要写书评

暂无评论

SCALEDEEP: A Scalable Compute Architecture for Learning and Evaluating Deep Networks 17

SCALEDEEP: A Scalable Compute Architecture for Learning and ...

引用

44th Annual International Symposium on Computer Architecture (ISCA)

作者： Venkataramani, Swagath Ranjan, Ashish Banerjee, Subarno Das, Dipankar Avancha, Sasikanth Jagannathan, Ashok Durg, Ajaya Nagaraj, Dheemanth Kaul, Bharat Dubey, Pradeep Raghunathan, Anand Purdue Univ Sch ECE W Lafayette IN 47907 USA Intel Corp Parallel Comp Lab Santa Clara CA 95051 USA IBM Corp TJ Watson Res Ctr Yorktown Hts NY 10598 USA Univ Michigan Ann Arbor MI 48109 USA

ISBN: (纸本)9781450348928

Deep Neural Networks (DNNs) have demonstrated state-of-the-art performance on a broad range of tasks involving natural language, speech, image, and video processing, and are deployed in many real world applications. However, DNNs impose significant computational challenges owing to the complexity of the networks and the amount of data they process, both of which are projected to grow in the future. To improve the efficiency of DNNs, we propose SCALEDEEP, a dense, scalable server architecture, whose processing, memory and interconnect subsystems are specialized to leverage the compute and communication characteristics of DNNs. While several DNN accelerator designs have been proposed in recent years, the key difference is that SCALEDEEP primarily targets DNN training, as opposed to only inference or evaluation. The key architectural features from which SCALEDEEP derives its efficiency are: (i) heterogeneous processing tiles and chips to match the wide diversity in computational characteristics (FLOPs and Bytes/FLOP ratio) that manifest at different levels of granularity in DNNs, (ii) a memory hierarchy and 3-tiered interconnect topology that is suited to the memory access and communication patterns in DNNs, (iii) a low-overhead synchronization mechanism based on hardware data-flow trackers, and (iv) methods to map DNNs to the proposed architecture that minimize data movement and improve core utilization through nested pipelining. We have developed a compiler to allow any DNN topology to be programmed onto SCALEDEEP, and a detailed architectural simulator to estimate performance and energy. The simulator incorporates timing and power models of SCALEDEEP's components based on synthesis to Intel's 14nm technology. We evaluate an embodiment of SCALEDEEP with 7032 processing tiles that operates at 600 MHz and has a peak performance of 680 TFLOPs (single precision) and 1.35 PFLOPs (half-precision) at 1.4KW. Across 11 state-of-the-art DNNs containing 0.65M-14.9M neurons and

关键词： Deep Neural Networks Hardware Accelerators System Architecture

来源：评论

学校读者我要写书评

暂无评论

On-Demand processing for Remote Sensing Big Data Analysis

On-Demand Processing for Remote Sensing Big Data Analysis

引用

IEEE International Symposium on parallel and distributed processing with Applications and IEEE International Conference on Ubiquitous Computing and Communications (ISPA/IUCC)

作者： Zhenchun Huang Anrun Zhong Guoqing Li Department of Computer Science and Technology Tsinghua University Beijing China

ISBN: (纸本)9781538637913

In the recent decades, remote sensing data are rapidly growing in size and variety, and considered as “big geo data” because of their huge data volume, significant heterogeneity and challenge of fast analysis. In the traditional remote sensing analysis workflows, the data transfer for downloading raw image files to local workstations often costs a lot of time and slows down the data analysis workflows. Because results of remote sensing data analysis models are usually much smaller than raw data to be processed, “on-demand processing”, which tries to upload data analysis models and execute them “near” where data stores, can significantly accelerate the execution of remote sensing analysis workflows. In this paper, a framework for on-demand remote sensing data analysis is proposed based on three-layered architecture; XML/JSON based runtime environment description; and on-demand model deployment methods. The evaluation on a prototype system shows that on-demand processing framework accelerates the execution of analysis models in 2.8 ~ 12.7 times by reducing data transfers, especially for those analysis workflows which transfer data through low bandwidth Internet. By on-demand processing, classical remote sensing data service systems can evolve into remote sensing data processing infrastructures, which provide IaaS (Infrastructure-as-a-Service) and PaaS (Platform-as-a-Service) services, and make it possible to exchange knowledge among scientists by sharing models. Furthermore, a remote sensing data analysis platform for carbon satellites is designed based on the on-demand processing proposed by this paper and will soon be implemented under the support of SunWay-TaihuLight, the world's most powerful super computer.

关键词： Tools XML distributed processing Conferences Ubiquitous computing Sensors Data analysis

来源：评论

学校读者我要写书评

暂无评论

parallel nonparametric binarization for degraded document images

引用

NEUROCOMPUTING 2016年 189卷 43-52页

作者： Chen, Xin Lin, Liang Gao, Yuefang NovuMind Inc 5201 Great Amer Pkwy Santa Clara CA 95054 USA Sun Yat Sen Univ Sch Adv Comp Guangzhou Higher Educ Mega Ctr Guangzhou 510006 Guangdong Peoples R China South China Agr Univ Coll Informat 483 Wushan Rd Guangzhou 510642 Guangdong Peoples R China

Adaptive binarization has been widely used in binarizing degraded document images. Most of the adaptive methods, however, face two challenging problems: expensive computation and sensitivity to introduced parameters. To solve the two challenges, we propose a novel parallel nonparametric method consisting of three steps: (i) achieving a number of binary images using Sauvola's method with different parameters;(ii) recognizing each pixel of these binary images using linear SVMs, and (iii) reconstructing a binary image on the basis of the recognized binary images. Our method therefore is a new concept to binarize an image. Instead of computing appropriate thresholding values, we generate a new binary image in term of numerous recognized binary images. The prerequisite of this idea is big enough data generated, and the modern CUDA-enabled GPUs provide the powerful computation capacity. In our work, we develop a CUDA well-suited parallel algorithm of Sauvola's method and implement it on Kepler GPUs with CUDA 5.0. Overall, our proposed method is highly parallelized as well and easily implemented on distributed systems if higher performance required. Experimental results on four public challenging datasets have shown that our proposed method outperforms the state-of-the-art methods. (C) 2015 Elsevier B.V. All rights reserved.

关键词： Binarization Sauvola's method GPU CUDA parallel algorithm Degraded document image

来源：评论

学校读者我要写书评

暂无评论

Direct Numerical Computation of the Stationary Radiative Transport Equation on Modern parallel Architectures

Direct Numerical Computation of the Stationary Radiative Tra...

引用

International Symposium on distributed Computing and Applications to Business, Engineering and Science (DCABES)

作者： Hiroshi Fujiwara Naoya Oishi Graduate School of Informatics Kyoto University Kyoto Japan Graduate School of Medicine Kyoto University Kyoto Japan

ISBN: (纸本)9781538621639

We study direct numerical computations of the stationary radiative transport equation for light propagation in tissue with a three dimensional MR image and bio-optical parameters. We employ an upwind finite difference scheme which has mathematical reliability. The computational times in modern three parallel architectures are compared. Although its discretization is a large scale problem with several billions unknowns, our result shows practicality of direct numerical computation from viewpoints of computational time and modern computer resources.

关键词： Mathematical model Scattering Iterative methods Graphics processing units Biomedical imaging Reliability Jacobian matrices

来源：评论

学校读者我要写书评

暂无评论

Simulation of parallel processing for distributed Multi-Target Tracking in Smart Camera Networks 16

Simulation of Parallel Processing for Distributed Multi-Targ...

引用

10th International Conference on distributed Smart Cameras (ICDSC)

作者： Jafarizadeh, Mehdi YadollahPour, Naeeme Shahid Beheshti Univ Comp Engn Dept Tehran Iran Univ Tehran Dept Management & Accounting Tehran Iran

ISBN: (纸本)9781450347860

In order to reduce the real-time processing gap of distributed algorithms on smart camera networks, we have evaluated a parallel processing method which exploits the processing capabilities of free cameras as auxiliary for busy ones. The communication infrastructure or camera processing capabilities are not included in the traditional evaluation methods like datasets or even virtual reality tools, so they are not suitable to analyze the complexity of distributed algorithms. For this purpose, we have developed a modular framework based on OMNET++ simulation environment named CAM-DIST, in which the velocity model of soccer players are emulated. Simulation results show that parallel processing improves overall efficiency, but could have side effects on individual camera estimations;so choosing optimal sharing value and destinations will enhance the performance.

关键词： Smart camera networks OMNET plus complexity analysis of distributed algorithms

来源：评论

学校读者我要写书评

暂无评论

便携式温室植物叶面积测量方法研究

引用

现代农业科技 2018年第1期 168-170页

作者：黄胜一李东郦志浩华中农业大学湖北武汉430000

为了快速、准确地测量植物叶面积,本文提出了一种基于可编程片上系统技术和图像处理技术的便携式叶面积测量方法。该系统通过摄像头采集叶面积数据,利用FPGA特有的并行工作方式对原始数据进行图像处理,提高叶面积测量精度和速度,采用具... 详细信息

为了快速、准确地测量植物叶面积,本文提出了一种基于可编程片上系统技术和图像处理技术的便携式叶面积测量方法。该系统通过摄像头采集叶面积数据,利用FPGA特有的并行工作方式对原始数据进行图像处理,提高叶面积测量精度和速度,采用具有Nios ii嵌入式软核处理器的现场可编程门阵列控制系统,提高整个系统的管理效率。田间实地测量表明该系统能够有效地采集叶面积数据,并具有测量速度快、可扩展性强和携带方便等优点。

关键词：温室植物叶面积 FPGA 测量图像处理

来源：评论

学校读者我要写书评

暂无评论

distributed travel-time seismic tomography in large-scale sensor networks

引用

JOURNAL OF parallel AND distributed COMPUTING 2016年 89卷 50-64页

作者： Kamath, Goutham Shi, Lei Song, Wen-Zhan Lees, Jonathan Georgia State Univ Dept Comp Sci Atlanta GA 30303 USA Univ N Carolina Dept Geol Sci Chapel Hill NC USA

Current geophysical techniques for visualizing seismic activity employ image reconstruction methods that rely on a centralized approach for processing the raw data captured by seismic sensors. The data is either gathered manually, or relayed by expensive broadband stations, and then processed at a base station. This approach is time-consuming (weeks to months) and hazardous as the task involves manual data gathering in extreme conditions. Also, raw seismic samples are typically in the range of 16-24 bit, sampled at 50-200 Hz and transferring this high fidelity sample from large number of sensors to a centralized station results in a bottleneck due to bandwidth limitations. To avoid these issues, a new distributed method is required which processes raw seismic samples inside each node and obtains a high resolution seismic tomography in real time. In this paper, we present a component-averaged distributed multi-resolution evolving tomography algorithm for processing data and inverting volcano tomography in the network while avoiding centralized computation and costly data collection. The algorithm is first evaluated for the correctness using a synthetic model in a CORE emulator. Later, our proposed algorithm runs using the real data obtained from Mt. St. Helens, WA, USA. The results validate that our distributed algorithm is able to obtain a satisfactory image similar to centralized computation under constraints of network resources, while distributing the computational burden to sensor nodes. (C) 2015 Elsevier Inc. All rights reserved.

关键词： distributed computing Seismic tomography Sensor network Mt. St. Helens

来源：评论

学校读者我要写书评

暂无评论

Location-Based parallel Tag Completion for Geo-Tagged Social image Retrieval

引用

ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY 2017年第3期8卷 38-38页

作者： Zhang, Jiaming Wang, Shuhui Huang, Qingming Chinese Acad Sci Key Lab Intellectual Informat Proc Inst Comp Technol Beijing Peoples R China Univ Chinese Acad Sci Beijing Peoples R China

Having benefited from tremendous growth of user-generated content, social annotated tags get higher importance in the organization and retrieval of large-scale image databases on Online Sharing Websites (OSW). To obtain high-quality tags from existing community contributed tags with missing information and noise, tag-based annotation or recommendation methods have been proposed for performance promotion of tag prediction. While images from OSW contain rich social attributes, they have not taken full advantage of rich social attributes and auxiliary information associated with social images to construct global information completion models. In this article, beyond the image-tag relation, we take full advantage of the ubiquitous GPS locations and image-user relationship to enhance the accuracy of tag prediction and improve the computational efficiency. For GPS locations, we define the popular geo-locations where people tend to take more images as Points of Interests (POI), which are discovered by mean shift approach. For image-user relationship, we integrate a localized prior constraint, expecting the completed tag sub-matrix in each POI to maintain consistency with users' tagging behaviors. Based on these two key issues, we propose a unified tag matrix completion framework, which learns the image-tag relation within each POI. To solve the optimization problem, an efficient proximal sub-gradient descent algorithm is designed. The model optimization can be easily parallelized and distributed to learn the tag sub-matrix for each POI. Extensive experimental results reveal that the learned tag sub-matrix of each POI reflects the major trend of users' tagging results with respect to different POIs and users, and the parallel learning process provides strong support for processing large-scale online image databases. To fit the response time requirement and storage limitations of Tag-based image Retrieval (TBIR) on mobile devices, we introduce Asymmetric Locality Sensitive H

关键词： Tag matrix completion geo-location information social image retrieval asymmetric locality sensitive hashing

来源：评论

学校读者我要写书评

暂无评论

适宜于高清监控视频的多ROI背景建模方法

引用

小型微型计算机系统 2018年第6期39卷 1190-1194页

作者：汪舟何军胡昭华南京信息工程大学电子与信息工程学院江苏省气象探测与信息处理重点实验室南京210044

针对智能监控领域精确运动检测的高实时性的需求,本文提出两种基于RPCA背景建模方法.方法 I提出平均网格化背景建模法,该方法通过对视频每帧图像进行网格化切分,对每一网格视频帧图像运用多线程并行进行背景建模;方法 ii提出基于RPCA的... 详细信息

针对智能监控领域精确运动检测的高实时性的需求,本文提出两种基于RPCA背景建模方法.方法 I提出平均网格化背景建模法,该方法通过对视频每帧图像进行网格化切分,对每一网格视频帧图像运用多线程并行进行背景建模;方法 ii提出基于RPCA的多ROI背景建模法,由于视频监控中,往往只有几处感兴趣的目标区域,该方法通过设定多ROI区域级联后进行背景建模,则无须对整个视频帧图像进行背景建模.实验表明,两种方法检测时间上相较与Online RPCA背景建模方法时间大大减少,并且检测效果上保证目标检测的精确度,能够满足对于高清视频的实时监控.

关键词：视频监控鲁棒性主成分分析背景建模运动目标检测

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：