检索结果-内蒙古大学图书馆

Asilomar Conference on Signals, systems & Computers

作者： Marcelo A. Daher Carlos A. Prete vítor H. Nascimento Bruno S. Masiero Dept. of Electronic Systems Engineering University of São Paulo São Paulo Brazil Dept. of Communications University of Campinas Campinas Brazil

ISBN: (数字)9781728143002

ISBN: (纸本)9781728143019

The Kronecker array transform (KAT) was introduced to reduce the computational burden in acoustic image estimation and other 2-dimensional array processing applications. The KAT can be applied only when the planar microphone array is separable. In this paper we study the performance of separable arrays using compressive beamforming algorithms to estimate the direction of arrival (DOA) of far-field sources and to recover the signal arriving from a particular direction. Our analysis extends previous studies based on mutual coherence to separable arrays, and shows that non-redundant separable arrays have better mutual coherence than can be obtained using 2D random arrays. We also derive the space discretization that yields the minimum coherence, and study the influence of frequency and the spatial resolution on the coherence. In order to verify the results, we present the performance of a separable array in two problems: DOA estimation and signal recovery using sparse reconstruction, and compare its performance with classical beamforming techniques. The sparsity-based approach shows better performance in DOA estimation and great improvement in time-domain signal recovery.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Real-time Depth Map Processor for Offset Aperture based Single Camera System 18

Real-time Depth Map Processor for Offset Aperture based Sing...

引用

23rd Asia and South Pacific Design Automation Conference (ASP-DAC)

作者： Kim, Hyeji Lim, Jinyeon Lee, Yeongmin Yun, Woojin Kim, Young-Gyu Choi, Wonseok Khan, Asim Khan, Muhammad Umar Karim Homidov, Said Park, Hyun Sang Kyung, Chong-Min Korea Adv Inst Sci & Technol Sch Elect Engn Daejeon South Korea Ctr Integrated Smart Sensors Daejeon South Korea Kongju Natl Univ Div Elect Engn Cheonan South Korea

ISBN: (纸本)9781509006021

This paper presents a Offset Aperture (OA) based single camera system and proposes a optimized vision processor, a new hardware architecture for fast, low-energy, and low-complexity depth extraction. The proposed design was fabricated in 110nm CMOS image sensor technology and supports 32-level depth resolution on 1920 x 1080 full HD image with 30fps, consuming 280.53mW from 1.5v supply and a mere 2.8% of bad classification. The low-complexity algorithms are employed to eliminate the DRAM access, thereby the proposed OA architecture can be directly embedded with the CMOS image sensor and commercial image processing chip.

关键词： Cameras Apertures Hardware High definition video Real-time systems Computer architecture Power demand

来源：评论

学校读者我要写书评

暂无评论

LABA: Logical Layout Analysis of Book Page images in Arabic Using Multiple Support vector Machines 2

LABA: Logical Layout Analysis of Book Page Images in Arabic ...

引用

2nd IEEE International Workshop on Arabic and Derived Script Analysis and Recognition (IEEE ASAR)

作者： Qin, Wenda Elanwar, Randa Betke, Margrit Boston Univ Dept Comp Sci 111 Cummington St Boston MA 02215 USA Elect Res Inst Cairo Egypt Boston Univ Boston MA 02215 USA

ISBN: (纸本)9781538614594

Logical layout analysis, which determines the function of a document region, for example, whether it is a title, paragraph, or caption, is an indispensable part in a document understanding system. Rule-based algorithms have long been used for such systems. The datasets available have been small, and so the generalization of the performance of these systems is difficult to assess. In this paper, we present LABA, a supervised machine learning system based on multiple support vector machines for conducting a logical Layout Analysis of scanned pages of Books in Arabic. Our system labels the function (class) of a document(scanned book pages) region, based on its position on the page and other features. We evaluated LABA with the benchmark "BCE-Arabic-v1" dataset, which contains scanned pages of illustrated Arabic books. We obtained high recall and precision values, and found that the F-measure of LABA is higher for all classes except the "noise" class compared to a neural network method that was based on prior work.

关键词： Document image processing text analysis multi-classifier system Arabic text documents logical layout analysis functional layout analysis

来源：评论

学校读者我要写书评

暂无评论

Deep learning in ophthalmology: The technical and clinical considerations

引用

PROGRESS IN RETINAL AND EYE RESEARCH 2019年 72卷 100759页

作者： Ting, Daniel S. W. Peng, Lily varadarajan, Avinash v. Keane, Pearse A. Burlina, Philippe M. Chiang, Michael F. Schmetterer, Leopold Pasquale, Louis R. Bressler, Neil M. Webster, Dale R. Abramoff, Michael Wong, Tien Y. Natl Univ Singapore Duke NUS Med Sch Singapore Natl Eye Ctr Singapore Eye Res Inst Singapore Singapore Google AI Healthcare Mountain View CA USA Moorfields Eye Hosp London England Johns Hopkins Univ Sch Med Wilmer Eye Inst Baltimore MD 21205 USA Johns Hopkins Univ Appl Phys Lab Baltimore MD 21218 USA Johns Hopkins Univ Malone Ctr Engn Healthcare Baltimore MD USA Oregon Hlth & Sci Univ Casey Eye Inst Dept Ophthalmol & Med Informat Portland OR 97201 USA Oregon Hlth & Sci Univ Casey Eye Inst Dept Med Informat & Clin Epidemiol Portland OR 97201 USA Nanyang Technol Univ Lee Kong Chian Sch Med Dept Ophthalmol Singapore Singapore Med Univ Vienna Dept Clin Pharmacol Vienna Austria Med Univ Vienna Ctr Med Phys & Biomed Engn Vienna Austria Icahn Sch Med Mt Sinai Dept Ophthalmol New York NY 10029 USA Univ Iowa Hlth Care Dept Ophthalmol & Visual Sci Iowa City IA USA

The advent of computer graphic processing units, improvement in mathematical models and availability of big data has allowed artificial intelligence (AI) using machine learning (ML) and deep learning (DL) techniques to achieve robust performance for broad applications in social-media, the intemet of things, the automotive industry and healthcare. DL systems in particular provide improved capability in image, speech and motion recognition as well as in natural language processing. In medicine, significant progress of AI and DL systems has been demonstrated in image-centric specialties such as radiology, dermatology, pathology and ophthalmology. New studies, including pre-registered prospective clinical trials, have shown DL systems are accurate and effective in detecting diabetic retinopathy (DR), glaucoma, age-related macular degeneration (AMD), retinopathy of prematurity, refractive error and in identifying cardiovascular risk factors and diseases, from digital fundus photographs. There is also increasing attention on the use of AI and DL systems in identifying disease features, progression and treatment response for retinal diseases such as neovascular AMD and diabetic macular edema using optical coherence tomography (OCT). Additionally, the application of ML to visual fields may be useful in detecting glaucoma progression. There are limited studies that incorporate clinical data including electronic health records, in AL and DL algorithms, and no prospective studies to demonstrate that AI and DL algorithms can predict the development of clinical eye disease. This article describes global eye disease burden, unmet needs and common conditions of public health importance for which AI and DL systems may be applicable. Technical and clinical aspects to build a DL system to address those needs, and the potential challenges for clinical adoption are discussed. AI, ML and DL will likely play a crucial role in clinical ophthalmology practice, with implications for screeni

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improved ORB Algorithm Based on Binocular vision

Improved ORB Algorithm Based on Binocular Vision

引用

IEEE International Conference on Computer and Communications

作者： Chao Li Yongxing Jia Huali Wang Chuanzhen Rong Ying Zhu Coege of Counicions Engineering Ary Engineering Universiy of PLACoege of Counicions Engineering Ary Engineering Universiy of PLACoege of Counicions Engineering Ary Engineering Universiy of PLACoege of Counicions Engineering Ary Engineering Universiy of PLACoege of Counicions Engineering Ary Engineering Universiy of PLA

ISBN: (数字)9781728147437

ISBN: (纸本)9781728147444

In digital image processing, feature extraction is a very important step, and ORB algorithm is the best one in realtime performance, but it is not up to the standard in the system with higher real-time requirements. Through binocular vision calibration, we will delve into how to speed up the operation of ORB algorithm with ensuring accuracy. First, the overlapping regions of the left and right images are extracted, and then the images are subjected to morphological operations, and corner detection is performed at the edges. Secondly, the original description method is improved, and the description sub-selects the window value based on the area ring, which is more in line with the characteristics of the human eye and improves the operation speed. Then, a hierarchical matching strategy is adopted, combined with binocular visual constraints, the matching range is defined, and the accuracy is effectively improved. Finally, construct an experimental platform to process two images and compare them with existing algorithms. The experimental results show that the proposed method has much less computational time consumption than the original algorithm under the condition of improved accuracy, and is suitable for fast matching environment.

关键词： Feature extraction image edge detection Real-time systems Calibration Cameras Morphological operations Robustness

来源：评论

学校读者我要写书评

暂无评论

E-discover State-of-the-art Research Trends of Deep Learning for Computer vision

E-discover State-of-the-art Research Trends of Deep Learning...

引用

IEEE International Conference on systems, Man and Cybernetics

作者： Annie A. S. Li Amy J. C. Trappey Charles v. Trappey C. Y. Fan Department of Industrial Engineering and Engineering Management National Tsing Hua University Hsinchu Taiwan Distinguished Professor in the Department of Industrial Engineering and Engineering Management National Tsing Hua University Hsinchu Taiwan Department of Management Science National Chiao Chiao Tung Tung University Hsinchu Taiwan Science and Technology Policy and Information Center National Applied Research Laboratory Taipei Taiwan

Computer vision (Cv) attempts to mimic human eyes for image processing and identifications of detailed visual information, such as object positions, features of appearances, and even human emotions and behaviors. In this research, more than one hundred literatures, relating to applying deep learning (DL) methodologies in advanced computer visions (2010~2018), are reviewed and analyzed. The objective is to discover the state-of-the-art DL methods, topics, and trends for Cv and their practical applications. DL algorithms aim at representing multi-levels of distributed neural networks. Because of the enhancement of high speed computational power, DL modeling, based on accumulated big data analytics, has found practical applications for non-supervised intelligent decision supports, such as detection of product defects and prognosis of machine malfunctions based on real-time signal or feature data analyses. There are a vast number of literature, describing DL related researches, developments, and implementations for problem solving. For the comprehensive mining of the related literature, we integrate Latent Dirichlet Allocation (LDA), K-means (Clustering), and normalized term frequency-inverse document frequency (NTF-IDF) approaches to discover, or called technology mining, of the major trends in DL for computer visions, specifically for key applications in object detection, semantic segmentation, image retrieval, and human pose estimation.

关键词： Machine learning Computer vision Market research Text mining Resource management Radio spectrum management

来源：评论

学校读者我要写书评

暂无评论

Application of Constrained Energy Minimization (CEM) algorithm to ASTER data for alteration mineral mapping

Application of Constrained Energy Minimization (CEM) algorit...

引用

IEEE International Geoscience and Remote Sensing Symposium

作者： Amin Beiranvand Pour Tae-Yoon S. Park Yongcheol Park Jong Kuk Hong Biswajeet Pradhan Korea Polar Research Institute (KOPRI) Incheon Republic of Korea Centre for Advanced Modelling and Geospatial Information Systems (CAMGIS) Faculty of Engineering and Information Technology University of Technology Sydney New South Wales Australia

Several regions remain poorly studied in terms of geological mapping and mineral exploration in inaccessible regions especially in the Arctic and Antarctica due to harsh conditions and logistical difficulties. Application of specialized image processing techniques is capable of revealing the hidden linearly mixed spectral sources in multispectral and hyperspectral satellite images. In this study, the application of Constrained Energy Minimization (CEM) algorithm was evaluated for the Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) remote sensing data for geological mapping in Morozumi Range and Helliwell Hills areas, Northern victoria Land (NvL), Antarctica. The results of this investigation demonstrate the capability of the algorithms in distinguishing subpixel targets in the multispectral satellite data. The application of the method for identifying poorly exposed geologic materials and subpixel exposures of alteration minerals has invaluable implications for geological mapping and mineral exploration in inaccessible regions.

关键词： Minerals Remote sensing Antarctica Rocks Finite impulse response filters Minimization

来源：评论

学校读者我要写书评

暂无评论

Shooting impact detection system on a fixed target using a dynamic video frame reference.

Shooting impact detection system on a fixed target using a d...

引用

IEEE International Autumn Meeting on Power, Electronics and Computing (ROPEC)

作者： Miguel A. Borja-Benítez Jose A. Tirado-Mendez Luis A. vásquez-Toledo Department of Electrical Engineering Instituto Politécnico Nacional (SEPI-Zacatenco) CDMX México Department of Electrical Engineering UAM Iztapalapa CDMX México

ISBN: (数字)9781728128986

ISBN: (纸本)9781728128993

Nowadays, virtual simulators are playing a crucial role in the training of the armed forces of a country. Proof of this, is that most First World countries have developments of virtual simulation systems and virtual environments concentrated on military training. Due to the growing demand for this type of systems, virtual shooting simulators based on digital image processing (DIP) have been developed in recent years. In this paper, a DIP algorithm focused on the detection of impacts on a fixed target aided by a laser attachment is proposed. The operation of the algorithm is based on the Euclidean distance metric, generating a decorrelation in the area of interest when an impact of the laser light beam occurs, and maintaining a high correlation in areas of no interest between adjacent video frames. Significant gains are achieved by the proposed algorithm against the typical DIP algorithms found in the literature, which were measured quantitatively by the peak-to-average power ratio (PAPR) metric, obtaining a gain of more than one order of magnitude. Finally, the rms error performance of the detection system was obtained by real fire in a shooting stand.

关键词： Euclidean distance Electronics packaging Laser beams Training Measurement by laser beam Correlation Phase frequency detector

来源：评论

学校读者我要写书评

暂无评论

Dynamic Adaptive Network Edge Service Migration Method Based on a Docker Container

Dynamic Adaptive Network Edge Service Migration Method Based...

引用

IEEE International Conference on Computer and Communications

作者： Xiangjun Zhang Weiguo Wu Chi Zhang Wei Song Schoo of Couer Science nd Technoogy Xi'n Jioong UniversiySchoo of Couer Science nd Technoogy Xi'n Jioong UniversiySchoo of Couer Science nd Technoogy Xi'n Jioong UniversiySchoo of Couer Science nd Technoogy Xi'n Jioong Universiy

ISBN: (数字)9781728147437

ISBN: (纸本)9781728147444

With the development and maturity of 5G technology, edge networks have become more suitable for moving many low-latency cloud services to the edges of networks, thus significantly improving user service quality. Since mobile terminal users move with their location, the edge computing platform needs to seamlessly migrate services using users' mobile devices. However, the network environment of an edge network is complex, and service migration faces many challenges, such as how to overcome network delays and reduce the service interruption time. In this paper, we propose a service migration method based on Docker base image and design a compression algorithm for an adaptive network environment to compress images and other data. This method balances the multi-core processor computing power and network bandwidth resources. We implement pipeline parallel processing of each process and build a model to handle the situation. The results show that our method is more adaptable to changing network environments, and the migration time is reduced by 45.4%, on average, compared with the traditional uncompressed service switching method.

关键词： Containers Servers Compression algorithms Cloud computing Bandwidth Adaptive systems File systems

来源：评论

学校读者我要写书评

暂无评论

Offloading SLAM for Indoor Mobile Robots with Edge-Fog-Cloud Computing

Offloading SLAM for Indoor Mobile Robots with Edge-Fog-Cloud...

引用

International Conference on Advances in Science, Engineering and Robotics Technology

作者： v. K. Sarker J. Pena Queralta T. N. Gia H. Tenhunen T. Westerlund Department of Future Technologies University of Turku Turku Finland Department of Electronics KTH Royal Institute of Technology Stockholm Sweden

Indoor mobile robots are widely used in industrial environments such as large logistic warehouses. They are often in charge of collecting or sorting products. For such robots, computation-intensive operations account for a significant percentage of the total energy consumption and consequently affect battery life. Besides, in order to keep both the power consumption and hardware complexity low, simple micro-controllers or single-board computers are used as onboard local control units. This limits the computational capabilities of robots and consequently their performance. Offloading heavy computation to Cloud servers has been a widely used approach to solve this problem for cases where large amounts of sensor data such as real-time video feeds need to be analyzed. More recently, Fog and Edge computing are being leveraged for offloading tasks such as image processing and complex navigation algorithms involving non-linear mathematical operations. In this paper, we present a system architecture for offloading computationally expensive localization and mapping tasks to smart Edge gateways which use Fog services. We show how Edge computing brings computational capabilities of the Cloud to the robot environment without compromising operational reliability due to connection issues. Furthermore, we analyze the power consumption of a prototype robot vehicle in different modes and show how battery life can be significantly improved by moving the processing of data to the Edge layer.

关键词： Robot sensing systems Logic gates Cloud computing Robot kinematics Task analysis Edge computing

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：