检索结果-内蒙古大学图书馆

X-Ray Computed Tomography Applied to Objects of Cultural Heritage: Porting and Testing the Filtered Back-Projection Reconstruction Algorithm on Low Power systems-on-Chip

X-Ray Computed Tomography Applied to Objects of Cultural Her...

引用

Euromicro Conference on Parallel, Distributed and Network-Based processing

作者： Elena Corni Lucia Morganti Maria Pia Morigi Rosa Brancaccio Matteo Bettuzzi Giuseppe Levi Eva Peccenini Daniele Cesini Andrea Ferraro Department of Physics and Astronomy University of Bologna Bologna Italy Bologna Section Italian Institute for Nuclear Physics (INFN) Bologna Italy Enrico Fermi Center for Study and Research Roma Italy CNAF Section Italian Institute for Nuclear Physics (INFN) Bologna Italy

The embedded and high-performance computing (HPC) sectors, that in the past were completely separated, are now somehow converging under the pressure of two driving forces: the release of less power consuming server processors and the increased performance of the new low power systems-on-Chip (SoCs) developed to meet the requirements of the demanding mobile market. This convergence allows the porting to low power embedded architectures of applications that were originally confined to traditional HPC systems. In this paper, we present our experience of porting the Filtered Back-projection Algorithm to a low power, low cost system-on-chip, the NVIDIA Tegra K1, which is based on a quad core ARM CPU and on a NVIDIA Kepler GPU. This Filtered Back-projection Algorithm is heavily used in 3D Tomography reconstruction software. The porting has been done exploiting various programming languages (i.e. OpenMP, CUDA) and multiple versions of the application have been developed to exploit both the SoC CPU and GPU. The performances have been measured in terms of 2D slices (of a 3D volume) reconstructed per time unit and per energy unit. The results obtained with all the developed versions are reported and compared with those obtained on a typical x86 HPC node accelerated with a recent NVIDIA GPU. The best performances are achieved combining the OpenMP version and the CUDA version of the algorithm. In particular, we discovered that only three Jetson TK1 boards, equipped with Giga Ethernet interconnections, allow to reconstruct as many images per time unit as a traditional server, using one order of magnitude less energy. The results of this work can be applied for instance to the construction of an energy-efficient computing system of a portable tomographic apparatus.

关键词： Graphics processing units image reconstruction Computer architecture Filtering algorithms Computed tomography Radiography

来源：评论

学校读者我要写书评

暂无评论

Maturity and disease detection in tomato using computer vision

Maturity and disease detection in tomato using computer visi...

引用

International Conference on Parallel Distributed and Grid Computing (PDGC)

作者： Tanvi Mehra Vinay Kumar Pragya Gupta Dept. of Electronics and Communication Engineering Thapar University Patiala India Dept. of Electronics and Communication Engineering Jaypee University of Information Technology Waknaghat Himachal Pradesh India

ISBN: (纸本)9781509036707

Our country has vast potential to come up as a cardinal exporter of agricultural produce, but lack of quick quality evaluation techniques, huge losses in processing and handling after harvesting, diseased crop etc. result in a lower contribution to global market. The tomato crop is often infected by a disease, where plant's leaves get covered with spots of colors dark brown with purple border and light grey center; termed as Septoria Leaf Spot. It causes the leaves to turn yellow, but most damage occurs due to loss of leaves by infection. In this paper, tomato maturity based on color and fungal infection in the tomato leaves is determined. Initially thresholding algorithm was performed to determine the maturity of tomato. To make the system more generalized and self-adapting a shift to k-means clustering algorithm is made. Finally a comparative analysis of both the methods was done to analyze which method is more suitable in different conditions. Also an unconventional machine vision system has been suggested that scrutinizes the leaves emerging out of the soil and depending upon leaf spots, it analyzes the nature of fungus and its depth into the stem of tomato. k-means algorithm along with thresholding is used for segmentation of image and eventually identifying fungus. The fungus part that is segmented, is then studied to derive the percentage of presence.

关键词： Decision support systems Clustering algorithms Diseases Agriculture image color analysis Algorithm design and analysis image segmentation

来源：评论

学校读者我要写书评

暂无评论

Detection of abnormal moving vehicles for intelligent driver assistance system

Detection of abnormal moving vehicles for intelligent driver...

引用

International Conference on Electronics, Information and Communications (ICEIC)

作者： Cuong Nguyen Khac Ju H. Park Ho-Youl Jung Yeungnam University Gyeongsan Gyeongsangbuk-do KR Yeungnam University South Korea

ISBN: (纸本)9781467380171

Driving in nighttime environment is a difficult work due to low visibility, drowsy and impaired drivers. It is crucial to make a good algorithm to detect automatically abnormal moving vehicles surrounding the host vehicle to indicate early collision warning. This paper proposes an efficient approach to detect on-road abnormal moving vehicles in nighttime. Oncoming, change speed, change lane, roadside parking, and overtaking vehicles are detected. The proposal method is useful for vehicle behavior analysis system of IDAS (Intelligent Driver Assistance System). Firstly, all motion vectors of moving objects are estimated from frames. Most of safety moving vehicles are eliminated by using a new proposal threshold range and ROI setting. The remaining motion vectors are grouped by using K-means clustering algorithm to obtain segment abnormal vehicle candidates. The segmented candidates are classified using learning algorithm Support Vector Machines (SVMs) and various features to eliminate non-vehicle candidates. The experimental results show that the proposal method is high ability to detect the abnormal moving vehicles in front of the host vehicle in nighttime driving. It is useful to be the first processing step for behavior analysis systems in Intelligent Driver Assistance systems.

关键词： Vehicles Feature extraction Proposals Optical imaging image motion analysis Computer vision Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Inertial Sensors Strapdown Approach for Hybrid Cameras and MEMS Positioning

Inertial Sensors Strapdown Approach for Hybrid Cameras and M...

引用

IEEE/ION Position, Location and Navigation Symposium

作者： Paolo Dabove Irene Aicardi Nives Grasso Andrea Lingua Giorgio Ghinamo Cecilia Corbi Politecnico di Torino Environment Land and Infrastructure Department (DIATI) 10129 Turin (Italy)

ISBN: (纸本)9781509020430

In this paper the performances (in terms of accuracy) of an hybrid positioning technique, that brings together an image based recognition approach and MEMS (Micro Electro-Mechanical systems) technology, will be investigated. The image recognition based (IRB) positioning has already been well investigated in the past and represents a good technology for navigation in GNSS denied environment, like indoor or urban canyon, where GNSS accuracy is poor (tens of meters accuracy). However, for practical exploitation of IRB positioning with smartphones the following main problems must be taken into account. The first one is the optimization of the battery, that implies a proper use of the frame rate. A second main issue is represented by latencies due to image processing algorithms and visual search solutions that may require a cloud architecture to manage the size of the database. To overcome the above problems in IRB, reduction of the frame rate and latencies compensation, inertial platform built with MEMS technology may be exploited. Two different approaches are taken into account for IRB positioning: the first one is represented by a real-time solution obtainable through single images;the second one is achieved from a commercial software that locates all the frames (not suitable for real time applications). The paper presents a methodology that fuses IRB with MEMS measurements. Results have shown that with single IRB fixes fused together with inertial navigation the standard errors with the 95~(th) percentile are about 1.66 m, 2.36 m and 3.16 m if the interval between two IRB localizations are 1, 2 and 5 sec respectively, while these errors decrease up to 0.64 m, 1.79 m and 2.05 m if the commercial hybrid absolute and relative orientation solution is considered. We can affirm that the weakness in single photograms positioning approach resides in poor orientation estimation of photograms that can grow up to some tens of degrees when poor geometry is picked in the camera s

关键词： smartphones MEMS inertial sensors image based navigation indoor positioning

来源：评论

学校读者我要写书评

暂无评论

A Distinguishing Arterial Pulse Waves Approach by Using image processing and Feature Extraction Technique

引用

JOURNAL OF MEDICAL systems 2016年第10期40卷 215-215页

作者： Chen, Hsing-Chung Kuo, Shyi-Shiun Sun, Shen-Ching Chang, Chia-Hui Asia Univ Dept Comp Sci & Informat Engn Taichung Taiwan China Med Univ China Med Univ Hosp Dept Med Res Taichung Taiwan Nan Kai Univ Technol Dept Multimedia Animat & Applicat Caotun Nantou County Taiwan Show Chwan Mem Hosp Dept Chinese Med Changhua Taiwan Asia Univ Dept Int Business Taichung Taiwan

Traditional Chinese Medicine (TCM) is based on five main types of diagnoses methods consisting of inspection, auscultation, olfaction, inquiry, and palpation. The most important one is palpation also called pulse diagnosis which is to measure wrist artery pulse by doctor's fingers for detecting patient's health state. In this paper, it is carried out by using a specialized pulse measuring instrument to classify one's pulse type. The measured pulse waves (MPWs) were segmented into the arterial pulse wave curve (APWC) by image proposing method. The slopes and periods among four specific points on the APWC were taken to be the pulse features. Three algorithms are proposed in this paper, which could extract these features from the APWCs and compared their differences between each of them to the average feature matrix, individually. These results show that the method proposed in this study is superior and more accurate than the previous studies. The proposed method could significantly save doctors a large amount of time, increase accuracy and decrease data volume.

关键词： Pulse diagnosis TCM pulse diagnosis Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Privacy-preserving, indoor occupant localization using a network of single-pixel sensors

Privacy-preserving, indoor occupant localization using a net...

引用

IEEE Conference on Advanced Video and Signal Based Surveillance (AVSS)

作者： Douglas Roeper Jiawei Chen Janusz Konrad Prakash Ishwar Department of Electrical and Computer Engineering Boston University Boston MA Boston University Boston MA US

ISBN: (纸本)9781509038121

We propose an approach to indoor occupant localization using a network of single-pixel, visible-light sensors. In addition to preserving privacy, our approach vastly reduces data transmission rate and is agnostic to eavesdropping. We develop two purely data-driven localization algorithms and study their performance using a network of 6 such sensors. In one algorithm, we divide the monitored floor area (2.37m×2.72m) into a 3×3 grid of cells and classify location of a single person as belonging to one of the 9 cells using a support vector machine classifier. In the second algorithm, we estimate person's coordinates using support vector regression. In cross-validation tests in public (e.g., conference room) and private (e.g., home) scenarios, we obtain 67-72% correct classification rate for cells and 0.31-0.35m mean absolute distance error within the monitored space. Given the simplicity of sensors and processing, these are encouraging results and can lead to useful applications today.

关键词： Support vector machines Cameras Kernel Sensor systems image color analysis Intelligent sensors

来源：评论

学校读者我要写书评

暂无评论

Exploiting topological structures for graph compression based on quadtrees

Exploiting topological structures for graph compression base...

引用

IEEE International Conference on Research in Computational Intelligence and Communication Networks (ICRCICN)

作者： A. Chatterjee M. Levan C. Lanham M. Zerrudo M. Nelson S. Radhakrishnan California State University Dominguez Hills Carson CA US Department of Computer Science California State University Dominguez Hills Carson CA USA School of Computer Science University of Oklahoma Norman OK USA

ISBN: (纸本)9781509010486

In the age of big data, the need for efficient data processing and computation has been in the forefront of research endeavors. The process of extracting information from huge data sets require novel storage techniques to aid the computing devices to perform necessary computation. With pervasive use of heterogeneous systems and advent of non-traditional computing units like GPUs, with limited memory, it has become relevant to underline the relevance of data storage, especially to utilize such computing devices. Graphs contain a plethora of information, and also can be used to represent data from a broad range of domains; real-world big data sets are effectively represented by graphs. Efficient graph compression is therefore essential for performing computations on large data sets. Quadtrees, generally used to represent images, can be used as an effective technique to perform compression. Using additional topological information that depict certain patterns for the data sets, further improvements can be made to the space complexity of storing graph data. In this paper we describe algorithms that take into consideration the properties of graphs, and perform compression based on quadtrees. The introduced techniques achieve up to 70% compression as compared to adjacency matrix representation; when compared to existing quadtree based compression method, the proposed algorithms achieve an additional 50% improvement. Techniques to both compress data and also perform queries on the compressed data itself are introduced and discussed in detail.

关键词： image coding Data structures Big data Social network services Computer science Performance evaluation Complexity theory

来源：评论

学校读者我要写书评

暂无评论

Building a research data science platform from industrial machines

Building a research data science platform from industrial ma...

引用

IEEE International Conference on Big Data

作者： Fang Cherry Liu Fu Shen Duen Horng Chau Neil Bright Mehmet Belgin Partnership for An Advanced Computing Environment (PACE) Georgia Institute of Technology Atlanta Georgia School of Computational Science and Engineering Georgia Institute of Technology Atlanta Georgia

ISBN: (纸本)9781467390064

Data Science research has a long history in academia which spans from large-scale data management, to data mining and data analysis using technologies from database management systems (DBMS's). While traditional HPC offers tools on leveraging existing technologies with data processing needs, the large volume of data and the speed of data generation pose significant challenges. Using the Hadoop platform and tools built on top of it drew immense interest from academia after it gained success in industry. Georgia Institute of Technology received a donation of 200 compute nodes from Yahoo. Turning these industrial machines into a research Data Science Platform (DSP) poses unique challenges, such as: nontrivial hardware design decisions, configuration tool choices, node integration into existing HPC infrastructure, partitioning resource to meet different application needs, software stack choices, etc. We have 40 nodes up and running, 24 running as a Hadoop and Spark cluster, 12 running as a HBase and OpenTSDB cluster, the others running as service nodes. We successfully tested it against Spark Machine Learning algorithms using a 88GB image dataset, Spark DataFrame and GraphFrame with a Wikipedia dataset, and Hadoop MapReduce wordcount on a 300GB dataset. The OpenTSDB cluster is for real-time time series data ingestion and storage for sensor data. We are working on bringing up more nodes. We share our first-hand experience gained in our journey, which we believe will benefit and inspire other academic institutions.

关键词： Hardware Sparks Digital signal processing Ecosystems Distributed databases Cloud computing

来源：评论

学校读者我要写书评

暂无评论

基于引导滤波和NSST的工业CT图像边缘检测

引用

应用科学学报 2016年第4期34卷 405-416页

作者：孟天亮吴一全吴诗婳南京航空航天大学电子信息工程学院南京211106 华中科技大学数字制造装备与技术国家重点实验室武汉430074 南昌航空大学江西省图像处理与模式识别重点实验室南昌330063

针对传统边缘检测算法不能准确检测有噪工业CT图像边缘的问题,提出一种鲁棒性好、能有效保持细小边缘的边缘检测算法.用引导滤波取代高斯滤波作为边缘检测的预处理,避免Canny算法对边缘的损坏,得到初步检测结果.在此基础上采用非下采样S... 详细信息

针对传统边缘检测算法不能准确检测有噪工业CT图像边缘的问题,提出一种鲁棒性好、能有效保持细小边缘的边缘检测算法.用引导滤波取代高斯滤波作为边缘检测的预处理,避免Canny算法对边缘的损坏,得到初步检测结果.在此基础上采用非下采样Shearlet变换分解图像,提取包含图像边缘细节信息的各尺度不同方向的高频系数.对每个方向的系数进行模极大值检测,并结合不同分解程度下边缘像素处的系数关系进一步调整模极大值,低频置零并通过反变换得到高频边缘检测结果.将初步检测结果与高频检测结果进行融合,经数学形态学处理得到最终边缘检测图像.实验对比了Canny算子以及近年来提出的同类边缘检测算法的结果,所提算法表现出更好的边缘保持特性,检测的完整性和准确性更高,品质因数比实验中的其他算法平均高出12%,边缘检测效果优越,为工业CT无损检测系统提供了更好的边缘检测方案.

关键词：工业CT图像边缘检测非下采样Shearlet变换引导滤波

来源：评论

学校读者我要写书评

暂无评论

图像显著性区域检测算法的软硬件协同设计及SoC实现

引用

小型微型计算机系统 2016年第9期37卷 2114-2119页

作者：黄张祥白瑞林吉峰江南大学轻工过程先进控制教育部重点实验室江苏无锡214122 无锡信捷电气股份有限公司江苏无锡214072

针对目前基于图像底层特征的显著性区域检测算法存在准确度不高、分辨率较低、边界信息丢失、实时性不强等问题,提出一种基于RGB和CIE LAB颜色特征、边缘特征的显著性区域检测算法.算法对测试图像进行高斯差分处理,提取基于RGB空间的显... 详细信息

针对目前基于图像底层特征的显著性区域检测算法存在准确度不高、分辨率较低、边界信息丢失、实时性不强等问题,提出一种基于RGB和CIE LAB颜色特征、边缘特征的显著性区域检测算法.算法对测试图像进行高斯差分处理,提取基于RGB空间的显著图,并与RGB各通道进行Sign DCT、IDCT处理得到的边缘显著图线性加权合成;利用子图像对称包围区域计算LAB空间中的显著图,并与RGB边缘合成显著图进行相关归一化融合得到最终的显著性区域图.利用软硬件协同技术优化设计基于FPGA的Do G、颜色空间转换、DCT/IDCT等模块,并固化为IP核,算法其它部分及控制流程类基于ARM软件实现.实验表明,该算法与5种流行算法对比能够更好地抑制背景,且效果更加接近于人工精确标注的显著图,具有较高的有效性和快速性.

关键词：显著性检测 RGB空间 LAB空间边缘特征软硬件协同设计

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：