检索结果-内蒙古大学图书馆

10th Asian conference on Intelligent Information and Database systems (ACIIDS)

作者： Kawulok, Michal Benecki, Pawel Nalepa, Jakub Kostrzewa, Daniel Skonieczny, Lukasz Future Proc Gliwice Poland Silesian Tech Univ Inst Informat Gliwice Poland

ISBN: (纸本)9783319754178;9783319754161

Super-resolution reconstruction (SRR) consists in processing an image or a bunch of images to generate a new image of higher spatial resolution. This problem has been intensively studied, but seldom is SRR applied in practice for satellite data. In this paper, we briefly review the state of the art on SRR algorithms and we argue that commonly adopted strategies for their evaluation do not reflect the operational conditions. We report our study on assessing the SRR outcome, relying on new quantitative measures. The obtained results allow us to outline the most important research pathways to improve the performance of SRR.

关键词： Super-resolution image processing Similarity measures

来源：评论

学校读者我要写书评

暂无评论

SAR processing UWB VHF data without a motion measurement system 25

SAR processing UWB VHF data without a motion measurement sys...

引用

conference on algorithms for Synthetic Aperture Radar imagery XXV

作者： Torgrimsson, Jan Dammert, Patrik Hellsten, Hans Ulander, Lars M. H. Ahlander, Anders Chalmers Univ Technol Gothenburg Sweden SAAB Surveillance Gothenburg Sweden

ISBN: (数字)9781510618060

ISBN: (纸本)9781510618060

SAR processing usually requires very accurate navigation data, i.e. to form a focused image. The track must be measured within fractions of the centre wavelength. For high frequencies (e.g. X-band) this condition is too strict. Even with a cutting-edge motion measurement system, autofocus is a necessity. For low frequencies (e.g. VHF-band) a differential GPS (DGPS) is often an adequate solution (alone). However, for this case, it is actually conceivable to rely on autofocus capability over the motion measurement system. This paper describes how to form a SAR image without support from navigation data. That is within the scope of factorized geometrical autofocus (FGA). The FGA algorithm is a base-2 fast factorized back-projection realization with six free geometry parameters (per sub-aperture pair). These are tuned step-by-step until a sharp image is obtained. This procedure can compensate for an erroneous geometry (from a focus perspective). The FGA algorithm has been applied successfully on an ultra-wideband (UWB) data set, acquired at VHF-band by the CARABAS 3 system. The track is measured accurately by means of a DGPS. We however adopt and modify a basic geometry model. A linear equidistant flight path at fixed altitude is assumed and adjusted at several resolution levels. With this approach, we emulate a stand-alone processing chain without support from navigation data. The resulting FGA image is compared to a reference image and verified to be focused. This indicates that it is feasible to form a VHF-band SAR image without a motion measurement system.

关键词： Autofocus Back-Projection FGA Synthetic Aperture Radar (SAR) UWB VHF

来源：评论

学校读者我要写书评

暂无评论

DEEP NEURAL NETWORKS FOR NON-LINEAR MODEL-BASED ULTRASOUND RECONSTRUCTION

DEEP NEURAL NETWORKS FOR NON-LINEAR MODEL-BASED ULTRASOUND R...

引用

IEEE Global conference on Signal and Information processing (GlobalSIP)

作者： Almansouri, H. Venkatakrishnan, S. V. Buzzard, G. T. Bouman, C. A. Santos-villalobos, H. Purdue Univ Sch Elect & Comp Engn W Lafayette IN 47907 USA Oak Ridge Natl Lab Imaging Signals & Machine Learning Grp Oak Ridge TN 37831 USA Purdue Univ Dept Math W Lafayette IN 47907 USA

ISBN: (纸本)9781728112954

Ultrasound reflection tomography is widely used to image large complex specimens that are only accessible from a single side, such as well systems and nuclear power plant containment walls. Typical methods for inverting the measurement rely on delay-and-sum algorithms that rapidly produce reconstructions but with significant artifacts. Recently, model-based reconstruction approaches using a linear forward model have been shown to significantly improve image quality compared to the conventional approach. However, even these techniques result in artifacts for complex objects because of the inherent non-linearity of the ultrasound forward model. In this paper, we propose a non-iterative model-based reconstruction method for inverting measurements that are based on non-linear forward models for ultrasound imaging. Our approach involves obtaining an approximate estimate of the reconstruction using a simple linear back-projection and training a deep neural network to refine this to the actual reconstruction. We apply our method to simulated and experimental ultrasound data to demonstrate dramatic improvements in image quality compared to the delay-and-sum approach and the linear model-based reconstruction approach.

关键词： image reconstruction Ultrasonic imaging Mathematical model Training Neural networks Imaging Transducers

来源：评论

学校读者我要写书评

暂无评论

Accelerating the Inference Phase in Ternary Convolutional Neural Networks Using Configurable Processors 12

Accelerating the Inference Phase in Ternary Convolutional Ne...

引用

12th conference on Design and Architectures for Signal and image processing, DASIP 2018

作者： Chidambaram, Sivakumar Riviello, Alexandre Pierre Langlois, J.M. David, Jean-Pierre Department of Electrical Engineering Polytechnique Montréal Canada Departement of Computer and Software Engineering Polytechnique Montréal Canada

ISBN: (纸本)9781538682371

The need to automate tasks has led to state-of-the-art algorithms such as Convolutional Neural Networks (CNNs), which can learn representations from images. CNNs are computationally expensive. Hence, they are mostly implemented on Graphical processing Units (GPU), which consume high power, a large area and have high cost. Due to these factors, it is difficult to implement CNNs in embedded systems where there are severe space and power constraints. Application Specific Instruction-Set Processors (ASIPs) provide an alternative to GPUs and are low power consuming devices. However, floating-point operations and storage are expensive and do not lend themselves well to an ASIP implementation. A more efficient approach to implement CNNs on ASIPs involves expressing the data and parameters with binary, ternary or fixed-point representations. In this paper, we discuss our implementation of the inference phase of ternary CNNs on an Xtensa LX6 ASIP and measure its performance for the MNIST dataset. The complex computations are parallelized with custom instructions developed using the TIE programming language. Compared to a sequential implementation, our results indicate a speed up of 4.7× with an added area of only 20%. © 2018 IEEE.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Classification of hazy and non-hazy images

Classification of hazy and non-hazy images

引用

2017 International conference on Recent Innovations in Signal processing and Embedded systems, RISE 2017

作者： Shrivastava, Saurabh Thakur, Ramesh Kumar Tokas, Pratibha Computer Engineering Department Smt. S. R. Patel Engineering College Unjha India Computer Engineering Department IIT Patna Patna India Engineering Department Smt. S. R. Patel Engineering College Unjha India

ISBN: (纸本)9781509047604

For defogging of pictures, initially it is investigated that if the picture is foggy or clear and for this someone cannot depend upon view of human, so for deciding the picture state as foggy or clear must be comprehended first. In this proposed work, 19 classification techniques are applied to judge whether a picture is foggy or clear. Based on characteristic difference of foggy and clear pictures, the five parameters which are area, mean, min intensity, max intensity, standard deviation are used for training the classification system. Some of the classification techniques provide very good accuracy and can be used further in defogging algorithms in basic step of image state recognition. © 2017 IEEE.

关键词： image classification

来源：评论

学校读者我要写书评

暂无评论

The technology of digital image processing in neural network control systems for pipeline welding system

The technology of digital image processing in neural network...

引用

2018 IEEE conference of Russian Young Researchers in Electrical and Electronic Engineering, ElConRus 2018

作者： Naing, Zaw Myo Htut, Ye Htet Linn Thein Department of Automatic Control System and Control National Research University of Electronic Technology Zelenograd Moscow Russia

ISBN: (纸本)9781538643396

In this paper, modern technologies of adaptive control of welding systems are described. By using robotic welding technical innovations in robotic welding and greater accessibility of sensor control have allowed manual welding with excessive heat and vapor to be replaced. In the coordinate system of the welded parts are shown that the procedures of geometric adaptation based on algorithms and data from laser profilers for calculating of the path of movement of the welding torch. The structure of the control system based on the model of the neural network prediction is considered. The simulation results of the controller neural network positioning system of the welding torch are considered. This article approaches the familiarity with robotic welding and the roles of sensors in robotic welding and their related problems. © 2018 IEEE.

关键词： image processing

来源：评论

学校读者我要写书评

暂无评论

A Configurable Pruning Gaussian image Filter for Energy-Efficient Edge Detection

A Configurable Pruning Gaussian Image Filter for Energy-Effi...

引用

IEEE International conference on Electronics, Circuits and systems

作者： Leonardo Bandeira Soares Eduardo Antonio Cesar da Costa Sergio Bampi Federal Institute of Technology of Rio Grande do Sul (IFRS) Brazil Graduate Program on Electronic Engineering and Computing Catholic University of Pelotas (UCPel) Pelotas Brazil Graduate Program on Microelectronics Federal University of Rio Grande do Sul (UFRGS) Porto Alegre Brazil

This paper presents a new configurable pruning Gaussian image filter CMOS architecture to address energy efficiency requirements regarding edge detection applications. Low-energy consumption is key for Internet of Things (IoT) devices. Many emerging IoT applications rely on cameras to extract video or image features by running power-hungry computer vision algorithms. The Gaussian image filter is one of the most compute intensive tasks for pre-processing edge detection techniques which are widely adopted in the computer vision domain. Therefore, our proposed 2D Gaussian filter architecture enables: i) a low power and low area overhead runtime configuration scheme based on clock gating technique to prune the Gaussian filter (GF) window size, and ii) run-time capability to balance the tradeoff between edge detection quality and energy efficiency. Our proposed configurable architecture is synthesized and mapped onto 45 nm technology for an ASIC implementation. Results show that for 6 different run-time profiles our proposed configurable architecture provides power dissipation reduction of up to 64% with multiple levels of edge detection quality, which is assessed by considering the performance conformance metric.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Topology-Aware Task Allocation for Distributed Stream processing with Latency Guarantee 18

Topology-Aware Task Allocation for Distributed Stream Proces...

引用

2nd International conference on Advances in image processing (ICAIP) / 2nd International conference on Software Engineering and Development (ICSED

作者： Wei, Xiaohui Wei, Xun Li, Hongliang Zhuang, Yuan Yue, Hengshan Jilin Univ Coll Comp Sci & Technol Changchun Peoples R China Minist Educ Key Lab Symbol Computat & Knowledge Engn Changchun Peoples R China

ISBN: (纸本)9781450364607

Nowadays it becomes more and more critical to process the increasingly large amounts of data in timely manner. In order to meet this requirement and ensure the reliable processing of streaming data, a variety of distributed stream processing architectures and platforms have been developed, which handles the fundamental task of allocating processing tasks to the currently available physical resources and routing streaming data between these resources. However, many stream processing systems lack an intelligent scheduling mechanism, in which their default schedulers allocate tasks without taking resource demands and availability, or the transfer latency between resources into consideration. Besides stream processing has a strict request for latency. Thus it's important to give latency guarantee for distributed stream processing. In this paper, we propose a new algorithm for stream processing with latency guarantee, the algorithm both consider transfer latency and resource demand in the process of task allocation. Extensive experiments verify the correctness and effectiveness of our approach. Under the condition of satisfying the latency constraints, the heuristic algorithm AHA on average, reduce more than 21.3% and 58.9% resources compared with the greedy and the round-robin algorithms.

关键词： Distributed stream processing Task allocation Transfer latency

来源：评论

学校读者我要写书评

暂无评论

Transmitting image in 3D Wireless Channel using Adaptive Algorithm processing with MMSE based on MIMO principles

引用

Journal of Physics: conference Series 2021年第1期1973卷

作者： V.P. Fedosov J.S. Jameel S.V. Kucheryavenko Institute for Radiotechnical Systems and Control Southern Federal University 105/42 Bolshaya Sadovaya Str. Rostov-on-Don 344006 Russia

With the growing evolution of wireless communication technologies, there is still a need for higher data rates, increased system capacity, and improved service quality. OFDM WiMAX technology is now regarded as one of the most common solutions for Broadband Wireless Connectivity in Urban Areas, capable of offering faster implementation and lower costs than standard wired options. This paper proposes effective adaptive algorithm processing with MMSE for use in wireless networks based on SISO and MIMO OFDM WiMAX, enabling network performance to be enhanced in the case of non-LOS wireless communications, which are standard in urban conditions. On the performance of the system, signal attenuation, the effects of several paths l, different mobility speeds and Doppler shift were studied. Combines the adaptive algorithm with MMSE, achieves improved joint channel estimation and signal detection which performs the technique effectively mobile. SNR, MSE and noise components are used to analyses mathematical models of adaptive modulation for transmitting images in SISO and MIMO systems. Simulation results show that the adaptive algorithm with MMSE would improve throughput. For example, when SNR equal 15 dB, the probability of MSE for BPSK based on MIMO principle is equal to 0.0016 with adaptive algorithm. Also, for the same value of SNR, the probability of MSE for BPSK based on MIMO principle is equal to 0.164 without adaptive algorithm. It can also be concluded that when processing signals in a receiving system under conditions of multi-path signal propagation, the use of adaptive algorithms with MMSE has a positive effect on noise immunity.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Subjective Evaluation of Compressed SAR images using JPEG and HEVC intra coding: Sometimes, Compression Improves Usability 15

Subjective Evaluation of Compressed SAR Images using JPEG an...

引用

15th European Radar conference (EuRAD)

作者： Pestel-Schiller, Ulrike Ostermann, Joern Leibniz Univ Hannover Inst Informat Verarbeitung Hannover Germany

ISBN: (纸本)9782874870538

Human evaluation of SAR is time-consuming and costly. Typically it requires the indirect usability-based assessment of SAR system components or SAR systems from which the images arose. We investigate an assessment system which aims at finding digital signal processing algorithms to simulate, complement and partly replace the human evaluation of SAR images. To better understand the human evaluation, expert SAR interpreters have been asked to solve tasks on SAR images whose different image qualities result from a specific SAR system by varying the parameter settings of one SAR system component. The SAR system component investigated first is the coding system where the spatial and the amplitude resolution are fundamental parameters. In this paper, we describe first results of a human evaluation with expert interpreters where the two coding standards JPEG and HEVC intra coding were evaluated at different spatial resolutions and data rates. The SAR image quality preferred to work with was identified by the interpreters.

关键词： image quality synthetic aperture radar data compression image coding

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：