检索结果-内蒙古大学图书馆

International conference on 3D Imaging, Modeling, processing, visualization and Transmission (3DIMPVT)

作者： Changjiang Cai Philippos Mordohai Stevens Institute of Technology

ISBN: (数字)9781728181288

ISBN: (纸本)9781728181295

Deep networks for stereo matching typically leverage 2D or 3D convolutional encoder-decoder architectures to aggregate cost and regularize the cost volume for accurate disparity estimation. Due to content-insensitive convolutions and down-sampling and up-sampling operations, these cost aggregation mechanisms do not take full advantage of the information available in the images. Disparity maps suffer from over-smoothing near occlusion boundaries, and erroneous predictions in thin structures. In this paper, we show how deep adaptive filtering and differentiable semi-global aggregation can be integrated in existing 2D and 3D convolutional networks for end-to-end stereo matching, leading to improved accuracy. The improvements are due to utilizing RGB information from the images as a signal to dynamically guide the matching process, in addition to being the signal we attempt to match across the images. We show extensive experimental results on the KITTI 2015 and virtual KITTI 2 datasets comparing four stereo networks (DispNetC, GCNet, PSMNet and GANet) after integrating four adaptive filters (segmentation-aware bilateral filtering, dynamic filtering networks, pixel adaptive convolution and semi-global aggregation) into their architectures. Our code is available at https://***/ccj5351/DAFStereoNets.

关键词： Three-dimensional displays Two dimensional displays Picture archiving and communication systems image segmentation Convolution Semantics Motion segmentation

来源：评论

学校读者我要写书评

暂无评论

Software Oriented Approach in Providing and processing of Signals with Real Power Quality Problems 25

Software Oriented Approach in Providing and Processing of Si...

引用

25th International conference on systems, Signals and image processing (IWSSIP)

作者： Simic, Milan Zivanovic, Dragan Kokolanski, Zivko Dincic, Milan Denic, Dragan Miljkovic, Goran Dimcev, Vladimir Univ Nis Fac Elect Engn Aleksandra Medvedeva 14 Nish Serbia Ss Cyril & Methodius Univ Fac Elect Engn & Informat Technol Skopje Macedonia

ISBN: (纸本)9781538669792

Software oriented approach in generation and analysis of complex signal waveforms, suitable for testing the instruments for detection of typical power quality (PQ) problems, is presented in this paper. This approach is based on virtual instrumentation software for definition of signal parameters, data acquisition card NI PCI 6343 for signal generation and power amplifier for amplification of output voltage level to the nominal RMS value of 230 V. Definition of basic signal parameters is enabled using LabviEW software support, which allows simple repetition of test signals and various combinations of more test sequences in final complex test signals. The basic advantage of this approach compared to similar solution for signal generation is possibility for providing test signal sequences according to the predefined algorithms, including variations of real PQ disturbances and problems in accordance with the European standard EN 50 1 60. Experimental confirmation of presented approach is performed using reference instrument - PQ analyzer Fluke 435 Series II.

关键词： Signal generation and processing Standard power quality problems virtual instrumentation software

来源：评论

学校读者我要写书评

暂无评论

Improving Efficency of Mathematical Functions in image processing by Loop Fusion 5

Improving Efficency of Mathematical Functions in Image Proce...

引用

5th International conference on Electrical and Electronics Engineering (ICEEE)

作者： Bigdello, Shapour Joudi Bigdello, Manoochehr Joodi Mohammadzadeh, Hekmat Islamic Azad Univ Dept Comp Engn Parsabad Moghan Branch Parsabad Iran Guilan Univ Software Engn Rasht Iran Gazi Univ Comp Engn Ankara Turkey

ISBN: (纸本)9781538663929

Compiler optimization, reducing data load from memory and not using off-line data are issues that effective in enhancing energy retention of multimedia, embedded and general-purpose systems. In these systems most programs are comprised from loops, and this shows the importance of compiler optimization. In this paper we have carried out loop reduction using calculation and fusing two loops and transforming them to one loop that caused data locality increase and reusability, and decreased loading data from memory, thus increase speedup. We have applied this technique on several feature extraction algorithms, such as mean and variance and some similar algorithms like covariance and third moment that are used in content-based image retrieval systems. This technique approximately increases efficiency of two loops method twice. In addition, we have calculated the combination of these three functions. In this way, we have observed that the combined version also increases the efficiency twice.

关键词： compilers optimization embedded systems locality reusability loop fusion

来源：评论

学校读者我要写书评

暂无评论

Automotive Brake Part Inspection and Fault Localization using Deep Learning

引用

IOP conference Series: Materials Science and Engineering 2021年第1期1059卷

作者： Santhiya Rajan R. Rameswari Suresh Gunasekaran PG Scholar Embedded Systems Dept of EIE Bannari Amman Institute of Technology Assistant Professor Dept. of EIE Bannari Amman Institute of Technology Assistant Professor Dept. of ECE Bannari Amman Institute of Technology

Inspection of brake components is very essential to detect the damaged manufactured parts before it is assembled in any vehicle. Manual inspection of brakes is extremely difficult since most of defects are very minute and cannot be identified by human eyes. Therefore, automatic inspection of manufactured brakes is indispensible to prevent failure of brakes and accidents. Previously, various research articles perform inspection of brake through conventional image processing and traditional image processing algorithms. However, these techniques are capable of identifying a single fault only and are less robust to detecting numerous faults. Further, the existing techniques hardly localize the exact location of faults in the surface of brake. In order to over these drawbacks, in this research we utilize deep learning object detection algorithms namely Single Shot Detector and Faster RCNN to identify and localize the exact location of fault on the brake surface. Furthermore, the proposed system is capable to detect different types of faults in a single algorithm and is robust to brake's material surface, environmental and lightening factors. The deep learning algorithms are trained using transfer learning on custom collected dataset. The proposed algorithms deliver an accuracy of 95.64% and mAP of 73.2% on cylindrical grey shade brakes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Model-Based System Design and Evaluation of image processing Architectures with SimTAny Framework 19th

Model-Based System Design and Evaluation of Image Processing...

引用

19th International GI/ITG conference on Measurement, Modelling and Evaluation of Computing systems (MMB)

作者： Deitsch, Anna Schneider, vitali Friedrich Alexander Univ Erlangen Nuremberg Dept Comp Sci 7 Martensstr 3 D-91058 Erlangen Germany

ISBN: (纸本)9783319749471;9783319749464

Becoming a ubiquitous part of a huge number of various applications, image processing algorithms and underling architectures have to meet many different requirements. Some have real-time performance constraints combined with demands on efficient implementation for limited or various hardware resources. This poses particular challenges for design, implementation, and evaluation of efficient image processing systems. In this paper, we present a model-based approach to address these issues using our framework SimTAny. Founded on the standard modeling language UML, we propose the UML image Proccessing Language (UIPL) to facilitate expressing image processing application algorithms directly in UML, which is especially beneficial for rapid modeling. With the help of SimTAny, such design models can be simulated in order to investigate the performance of a modeled system, to determine optimal design solutions, and to validate the required properties. We extend SimTAny to enable the generation of efficient implementation code of image processing algorithms for different target architectures. The code generated is then directly integrated in the simulation environment to increase the accuracy of our performance evaluations.

关键词： Model driven engineering UML SysML MARTE image processing applications High-level synthesis

来源：评论

学校读者我要写书评

暂无评论

A Novel Remote Sensing image Classification Method Based on Semi-supervised Fuzzy C-Means 4th

A Novel Remote Sensing Image Classification Method Based on ...

引用

4th International conference on Cognitive systems and Information processing, ICCSIP 2018

作者： Feng, Guozheng Xu, Jindong Fan, Baode Zhao, Tianyu Sun, Xiao Zhu, Meng School of Computer and Control Engineering Yantai University Yantai China

ISBN: (纸本)9789811379826

Because of the uncertainty of remote sensing image and ill-posedness for model, the traditional unsupervised classification algorithm is difficult to model accurately in the classification process. The pattern recognition methods based on fuzzy set theory can manage the fuzziness of data effectively, such as fuzzy c-means clustering algorithm. Among them, the type-2 fuzzy c-means algorithm has better ability to control uncertainty. However, the semi-supervised method can use prior knowledge to deal with ill-posedness of algorithms more suitable. This paper proposes the method based on the semi-supervised adaptive interval type-2 fuzzy c-means (SS-AIT2FCM). In the interval type-2 fuzzy algorithm, soft constraint supervision is performed by a small number of labeled samples, which optimizes the iterative process of the algorithm and mines the optimal expression of the data, and reduces the ill-posedness of the algorithm itself. Experimental results indicate that SS-AIT2FCM can get more accurate clusters and more clear boundaries in the remote sensing image of serious mixed pixels, have an effective results to suppress the phenomenon of “isomorphic spectrum”. © 2019, Springer Nature Singapore Pte Ltd.

关键词： Fuzzy set theory

来源：评论

学校读者我要写书评

暂无评论

Genetic and practical swarm optimisation algorithms for patient-specific seizure detection systems 4

Genetic and practical swarm optimisation algorithms for pati...

引用

4th International conference on Advanced Technologies for Signal and image processing (ATSIP)

作者： Ammar, Sabrina Trigui, Omar Senouci, Mohamed Ibn Khaldoun Univ Tiaret LIM Tiaret Algeria Sfax Univ ENIS ATMS Sfax Tunisia Oran Univ Ahmed Ben Bella Lab Parallel & Embedded Architectures & Intens Co Oran Algeria

ISBN: (纸本)9781538652398

The automatic seizure detection system is designed to aid the physician's decision-making process with recognizing the sought EEG segments. Increasing the system sensitivity is the goal of several studies. In fact, ameliorating this criterion allows to find the same interpretations as found with a visual scanning A patient-specific system is able to set its optimal parameters according to the patient which makes it more accurate than non patient-specific system. This paper introduces a new patient specific system with genetic and practical swarm optimisation algorithms. The results show that the proposed system is able to reach acceptable performances. Moreover, the use of the genetic algorithm improves the system sensitivity (95%) more than the practical swarm optimization (91%) which makes it a better method for the system parameter optimisation.

关键词： Epilepsy Seizures Detection Patient-Specific Seizure Detection systems Genetic Algorithm Swarm Optimisation Algorithm

来源：评论

学校读者我要写书评

暂无评论

2nd international conference on data engineering and communication technology, ICDECT 2017

2nd international conference on data engineering and communi...

引用

2nd International conference on Data Engineering and Communication Technology, ICDECT 2017

ISBN: (纸本)9789811316098

The proceedings contain 71 papers. The special focus in this conference is on Data Engineering and Communication Technology. The topics include: S-LSTM-GAN: Shared Recurrent Neural Networks with Adversarial Training;hybrid Approach for Recommendation System;discussion on Problems and Solutions in Hardware Implementation of algorithms for a Car-type Autonomous Vehicle;software Test Case Allocation;seamless Vertical Handover for Efficient Mobility Management in Cooperative Heterogeneous Networks;sentence Similarity Estimation for Text Summarization Using Deep Learning;minimization of Clearance Variation of a Radial Selective Assembly Using Cohort Intelligence Algorithm;m-Wallet Technology Acceptance by Street Vendors in India;explore-Exploit-Explore in Ant Colony Optimization;application of Blowfish Algorithm for Secure Transactions in Decentralized Disruption-Tolerant Networks;an Attention-Based Approach to Text Summarization;enhancement of Security for Cloud Data Using Partition-Based Steganography;large Scale P2P Cloud of Underutilized Computing Resources for Providing MapReduce as a Service;topic Modelling for Aspect-Level Sentiment Analysis;an image Deblocking Approach Based on Non-subsampled Shearlet Transform;an Effective video Surveillance Framework for Ragging/violence Recognition;DoT: A New Ultra-lightweight SP Network Encryption Design for Resource-Constrained Environment;a Distributed Application to Maximize the Rate of File Sharing in and Across Local Networks;obstacle Detection for Auto-Driving Using Convolutional Neural Network;Leakage Power Improvement in SRAM Cell with Clamping Diode Using Reverse Body Bias Technique;a Rig-Based Formulation and a League Championship Algorithm for Helicopter Routing in Offshore Transportation;an Investigation of Burr Formation and Cutting Parameter Optimization in Micro-drilling of Brass C-360 Using image processing;emotion Recognition from Sensory and Bio-Signals: A Survey.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Digital recognition based on sewing method

Digital recognition based on sewing method

引用

International conference on Advanced Mechatronic systems (ICAMechS)

作者： Dong, Nan Zhang, Yong Zhao, Qinjun Univ Jinan Sch Elect Engn Jinan Shandong Peoples R China

ISBN: (纸本)9781538671740

When people can't get close to identify the number of instruments, the digital area on the display screen can only be transmitted to the computer by the camera, and the digital recognition is realized through the computer's related software and algorithms. After image pre-processing operations, such as geometric correction, gray-scale, threshold and corrosion expansion, the projection method is used to segment the image and the number is identified by the sewing method. Compared with the traditional method of digital recognition, the efficiency of the sewing method is very high. The combination features of the horizontal and vertical thread of the image is used to complete the cascade classification after the character preprocessing operation. In the digital image acquisition and recognition system based on sewing method, 4320 numbers are identified and tested, of which an average of 122 digits can be handled per second. This method performs well in processing speed, recognition accuracy and anti-interference.

关键词： image acquisition preprocessing method of projection sewing method

来源：评论

学校读者我要写书评

暂无评论

Residual Dense Information Distillation Network for Single image Super-Resolution

Residual Dense Information Distillation Network for Single I...

引用

IEEE International conference on systems, Man and Cybernetics

作者： Qiaosong Chen Jinxin Li Bolin Duan Liu Pu Xin Deng Jin Wang Key Laboratory of Data Engineering and Visual Computing Chongqing University of Posts and Telecommunications Chongqing China

In recent years, Convolutional Neural Networks (CNNs) have achieved excellent results in the study of single image super-resolution. However, super-resolution algorithms based on CNNs still face serious challenges, such as poor detail reconstruction, numerous parameters, and difficulty of training. A Residual Dense Information Distillation Network (RD-IDN) is proposed in this paper which uses dense skip connections and residual structure to solve the problems of difficult training and low utilization of features in Information Distillation Network. Experimental results show that the proposed method is superior to many other Super Resolution algorithms in terms of reconstruction performance and computational comsumption.

关键词： Training Feature extraction image reconstruction Convolution Graphics processing units Interpolation

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：