检索结果-内蒙古大学图书馆

International Siberian Conference on Control and Communications

作者： Daniil A. Loktev Alexey A. Loktev Department of Information Systems and Telecommunications Bauman Moscow State Technical University Moscow Russia Department of Transport Construction Moscow State University of Railway Engineering Moscow Russia

ISBN: (纸本)9781467383844

An important element of the modern automated control systems, monitoring and remote access is to obtain primary information about the state and behavior of static or moving objects. To obtain such information we propose to use photo and video detectors, which could provide images of objects with high resolution in the system. Thus, the possibility of determining the geometric and kinematic parameters of the moving object are significantly reduced because of the different aspects of producing an image, one of these aspects is the blur. The geometric parameters of the object are determined by analyzing the blur of its images obtained at different settings of the photodetector. In this paper, algorithms of processing of primary information are improved by the use of methods and procedures of statistical analysis and probabilistic approach. It increases the accuracy of determined characteristics, the applicability of procedures for the calculation of state parameters (size, shape, distance from observer) and behavior parameters of the object (speed and direction) and reduces the computational complexity of the final algorithm. The research allows not only determine the geometric parameters of the object, but also to evaluate their accuracy and to develop elements of the algorithm that can be used in real systems of video monitoring

关键词： image blur video monitoring system method of least squares method of least modules object geometric parameters Bayesian estimation loss function distribution function of errors

来源：评论

学校读者我要写书评

暂无评论

HW-SW codesign of a positioning system. From UML to implementation case study

HW-SW codesign of a positioning system. From UML to implemen...

引用

Conference on Design of Circuits and Integrated Circuits (DCIS)

作者： Ángel Álvarez Íñigo Ugarte Patricia Martínez víctor Fernández TEISA Department University of Cantabria Santander Spain

During the last years, there has been a growing interest in systems related to the location of objects into three-dimensional environments and virtual reality applications. These systems, based on high-performance video-processing, have a big computational load, specially on image analysis phases. This work presents the process of HW-SW co-design and implementation of a positioning system. A methodology was applied in which the requirements and initial functionality was captured in UML-MARTE. After a high-level profiling of the system, an acceleration of most time-demanding stages is achieved by combining the hardware and software capabilities of Zynq platform targeting a low power embedded system. The performance obtained through hardware acceleration of critical parts of the application leads to a significant improvement in the throughput of the whole system. On the other hand, the presented work can also be seen as a proof of concept of the followed methodology.

关键词： Hardware Unified modeling language IP networks Software Acceleration Software algorithms C++ languages

来源：评论

学校读者我要写书评

暂无评论

Simple Robust and Adaptive Tracking Control for Mobile Robots

引用

IFAC-PapersOnLine 2015年第11 11期48卷 143-149页

作者： Pyrkin, Anton A. Bobtsov, Alexey A. Kolyubin, Sergey A. Faronov, Maxim v. Borisov, Oleg I. Gromov, vladislav S. vlasov, Sergey M. Nikolaev, Nikolay A. Department of Control Systems and Informatics ITMO University St. Petersburg Russia Department of Engineering Cybernetics Norwegian University of Science and Technology TrondheimNO-7491 Norway Laboratory “Control of Complex Systems” Institute for Problems of Mechanical Engineering St. Petersburg Russia

The problem of simple adaptive and robust control is studied for the case of parametric and dynamic dimension uncertainties: only the maximum possible relative degree of the plant model is known. The control approach “consecutive compensator” is investigated. To illustrate the eficiency of proposed approach an example with the mobile robot motion control using computer vision system is considered. Some remarks about mapping algorithms using stereo cameras and laser scanner for implementation in new home robots are considered. © 2015

关键词： visual servoing Computer control systems Conformal mapping Mobile robots Robust control Stereo image processing Adaptive tracking control Computer vision system Control approach Mapping algorithms Mobile robot motion Relative degrees Robust and adaptive control Simple adaptive

来源：评论

学校读者我要写书评

暂无评论

Numerical Comparison of Mono-static and Multi-static Array Performance in Personnel Screening systems

Numerical Comparison of Mono-static and Multi-static Array P...

引用

Progress in Electromagnetic Research Symposium

作者： vladimir v. Razevig Margarita A. Chizh valery v. Chapursky Sergey I. Ivashov Andrey v. Zhuravlev Remote Sensing Laboratory Bauman Moscow State Technical University 5 2nd Baumanskaya Str. 105005 Russia

ISBN: (纸本)9781509060948

The comparison of the modern microwave screening systems is given in this paper in the aspect of employing mono-static or multi-static antenna configuration, with their numerical models described and applied in the presented numerical experiments. The phenomenological model of scattering from human body and foreign objects is used to obtain the radar signal, which is processed according to the given mono-static or multi-static signal processing algorithms. The model of scattering objects is based on point scatterer approximation of their surfaces. The numerical simulations are performed for human body and foreign objects to obtain detailed radar images for mono-static and two multi-static antenna configurations at a single and multiple frequencies. According to the results of numerical simulations, the same quality of radar images, visually assessed by achievable plan view resolution and the level of artifacts, can be obtained by significantly lesser number of antenna elements in the case of multi-static antenna configuration. It was shown that extending the frequency band from 10 to 16 GHz substantially increases the contrast of the foreign objects placed over the human body.

关键词： Radar antennas image reconstruction Receiving antennas Linear antenna arrays Radar imaging

来源：评论

学校读者我要写书评

暂无评论

A New image Segmentation Approach using Community Detection algorithms 15

A New Image Segmentation Approach using Community Detection ...

引用

15th International Conference on Intelligent systems Design and Applications (ISDA)

作者： Mourchidl, Youssef El Hassouni, Mohammed Cherifi, Hocine Univ Mohammed V Agdal LRIT URAC 29 Rabat Morocco Univ Burgundy CNRS UMR 6306 LE2I Dijon France

ISBN: (纸本)9781467387095

image segmentation has an important role in many image processing applications. Several methods exist for segmenting an image. However, this technique is still a relatively open topic for which various research works are regularly presented. With the recent developments on complex networks theory, image segmentation techniques based on graphs has considerably improved. In this paper, we present a new perspective of image segmentation, by applying three of the most efficient community detection algorithms, Louvain, infomap and stability optimization based on the louvain algorithm, and we extract communities in which the highest modularity feature is achieved. After we show that this measure is invariant to non-structural change on image, which mean that the image segmentation is also invariant to rotation. Finally we evaluate the three proposed algorithms for Berkeley database images, and we show that our results can outperform other segmentation methods in terms of accuracy and can achieve much better segmentation results.

关键词： image segmentation complex networks community detection modularity

来源：评论

学校读者我要写书评

暂无评论

Resource-awareness on heterogeneous MPSoCs for image processing

引用

JOURNAL OF systems ARCHITECTURE 2015年第10期61卷 668-680页

作者： Paul, Johny Stechele, Walter Oechslein, Benjamin Erhardt, Christoph Schedel, Jens Lohmann, Daniel Schroeder-Preikschat, Wolfgang Kroehnert, Manfred Asfour, Tamim Sousa, Ericles Lari, vahid Hannig, Frank Teich, Juergen Grudnitsky, Artjom Bauer, Lars Henkel, Joerg Tech Univ Munich Inst Integrated Syst LIS D-80290 Munich Germany Tech Univ Munich D-80290 Munich Germany Karlsruhe Inst Technol D-76021 Karlsruhe Germany Karlsruhe Inst Technol High Performance Humanoid Technol Lab D-76021 Karlsruhe Germany Karlsruhe Inst Technol Inst Anthropomat D-76021 Karlsruhe Germany Karlsruhe Inst Technol Chair Embedded Syst D-76021 Karlsruhe Germany Friedrich Alexander Univ Erlangen Nurnberg FAU Nurnberg Germany Friedrich Alexander Univ Erlangen Nurnberg FAU Dept Comp Sci Nurnberg Germany Friedrich Alexander Univ Erlangen Nurnberg FAU CS Dept Architecture & Compiler Design Grp Nurnberg Germany

Multiprocessor system-on-chip (MPSoC) designs offer a lot of computational power assembled in a compact design. The computing power of MPSoCs can be further augmented by adding massively parallel processor arrays (MPPA) and specialized hardware with instruction-set extensions. On-chip MPPAs can be used to accelerate low-level image-processing algorithms with massive inherent parallelism. However, the presence of multiple processing elements (PEs) with different characteristics raises issues related to programming and application mapping, among others. The conventional approach used for programming heterogeneous MPSoCs results in a static mapping of various parts of the application to different PE types, based on the nature of the algorithm and the structure of the PEs. Yet, such a mapping scheme independent of the instantaneous load on the PEs may lead to under-utilization of some type of PEs while overloading others. In this work, we investigate the benefits of using a heterogeneous MPSoC for accelerating various stages within a real-world image-processing algorithm for object-recognition. A case study demonstrates that a resource-aware programming model called Invasive Computing helps to improve the throughput and worst observed latency of the application program, by dynamically mapping applications to different types of PEs available on a heterogeneous MPSoC. (C) 2015 Elsevier B.v. All rights reserved.

关键词： Resource awareness Invasive Computing image processing Computer vision MPSoC Heterogeneous processor

来源：评论

学校读者我要写书评

暂无评论

CS-Based Secured Big Data processing on FPGA

CS-Based Secured Big Data Processing on FPGA

引用

Annual IEEE Symposium on Field-Programmable Custom Computing Machines (FCCM)

作者： Amey Kulkarni Ali Jafari Colin Shea Tinoosh Mohsenin Department of Computer Science & Electrical Engineering University of Maryland Baltimore County

ISBN: (纸本)9781509023578

The four v's in Big data sets, volume, velocity, variety, and veracity, provides challenges in many different aspects of real-time systems. Out of these areas securing big data sets, reduction in processing time and communication bandwidth are of utmost importance. In this paper we adopt Compressive Sensing (CS) based framework to address all three issues. We implement compressive Sensing using Deterministic Random Matrix (DRM) on Artix-7 FPGA, and CS reconstruction using Orthogonal Matching Pursuit (OMP) algorithm on virtex-7 FPGA. The results show that our implementations for CS sampling and reconstruction are 183x and 2.7x respectively faster when compared to previously published work. We also perform case study of two different applications i.e. multi-channel Seizure Detection and image processing to demonstrate the efficiency of our proposed CS-based framework. CS-based framework allows us to reduce communication transfers up to 75% while achieving satisfactory range of quality. The results show that our proposed framework is 290x faster and has 7.9x less resource utilization as compared to previously published AES based encryption.

关键词： image reconstruction Big data Field programmable gate arrays Compressed sensing Matching pursuit algorithms Kernel Encryption

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised Sequence Learning 29

Semi-supervised Sequence Learning

引用

29th Annual Conference on Neural Information processing systems (NIPS)

作者： Dai, Andrew M. Le, Quoc v. Google Inc Mountain View CA 94043 USA

We present two approaches to use unlabeled data to improve Sequence Learning with recurrent networks. The first approach is to predict what comes next in a sequence, which is a language model in NLP. The second approach is to use a sequence autoencoder, which reads the input sequence into a vector and predicts the input sequence again. These two algorithms can be used as a "pretraining" algorithm for a later supervised sequence learning algorithm. In other words, the parameters obtained from the pretraining step can then be used as a starting point for other supervised training models. In our experiments, we find that long short term memory recurrent networks after pretrained with the two approaches become more stable to train and generalize better. With pretraining, we were able to achieve strong performance in many classification tasks, such as text classification with IMDB, DBpedia or image recognition in CIFAR-10.

关键词： image recognition

来源：评论

学校读者我要写书评

暂无评论

A Method for Predicting DCT-based denoising efficiency for grayscale images corrupted by AWGN and additive spatially correlated noise 13

A Method for Predicting DCT-based denoising efficiency for g...

引用

Conference on image processing - algorithms and systems XIII

作者： Rubel, Aleksey S. Lukin, vladimir v. Egiazarian, Karen O. Natl Aerosp Univ UA-61070 Kharkov Ukraine Tampere Univ Technol FIN-33101 Tampere Finland

ISBN: (纸本)9781628414899

Results of denoising based on discrete cosine transform for a wide class of images corrupted by additive noise are obtained. Three types of noise are analyzed: additive white Gaussian noise and additive spatially correlated Gaussian noise with middle and high correlation levels. TID2013 image database and some additional images are taken as test images. Conventional DCT filter and BM3D are used as denoising techniques. Denoising efficiency is described by PSNR and PSNR-HvS-M metrics. Within hard-thresholding denoising mechanism, DCT-spectrum coefficient statistics are used to characterize images and, subsequently, denoising efficiency for them. Results of denoising efficiency are fitted for such statistics and efficient approximations are obtained. It is shown that the obtained approximations provide high accuracy of prediction of denoising efficiency.

关键词： denoising prediction grayscale images DCT and BM3D filter fitting

来源：评论

学校读者我要写书评

暂无评论

Comparison of Citrus Fruit Diseases Revealing with Data Mining and image processing Techniques based on Assorted Parameters 5

Comparison of Citrus Fruit Diseases Revealing with Data Mini...

引用

International Conference on Computer Communication and Informatics ICCCI

作者： Devi, M. Renuka Kavitha, v. SNS Coll Technol Coimbatore Tamil Nadu India Bharathiar Univ Coimbatore Tamil Nadu India

ISBN: (纸本)9781479968053

Machine vision has become a key technology in the area of quality control. "vision systems" is primarily focused on computer vision in the context of inspection of the products such as food, pharmaceuticals. The system can consist of a number of cameras all capturing, interpreting and signaling individually with a control system related to some predefined algorithms. The analysis of citrus fruits using various assorted parameters revealing the diseases afflicting Citrus fruits and isolation of the same using image processing and Data Mining Techniques is the core area discussed here with.

关键词： Citrus Fruit Machine vision Computer vision image processing Data Mining

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：