检索结果-内蒙古大学图书馆

International Conference on Computer Vision (ICCV)

作者： Chensheng Peng Guangming Wang Xian Wan Lo Xinrui Wu Chenfeng Xu Masayoshi Tomizuka Wei Zhan Hesheng Wang Department of Automation Key Laboratory of System Control and Information Processing of Ministry of Education Shanghai Jiao Tong University Mechanical Systems Control Laboratory University of California Berkeley

Point clouds are naturally sparse, while image pixels are dense. The inconsistency limits feature fusion from both modalities for point-wise scene flow estimation. Previous methods rarely predict scene flow from the entire point clouds of the scene with one-time inference due to the memory inefficiency and heavy overhead from distance calculation and sorting involved in commonly used farthest point sampling, KNN, and ball query algorithms for local feature aggregation. To mitigate these issues in scene flow learning, we regularize raw points to a dense format by storing 3D coordinates in 2D grids. Unlike the sampling operation commonly used in existing works, the dense 2D representation 1) preserves most points in the given scene, 2) brings in a significant boost of efficiency, and 3) eliminates the density gap between points and pixels, allowing us to perform effective feature fusion. We also present a novel warping projection technique to alleviate the information loss problem resulting from the fact that multiple points could be mapped into one grid during projection when computing cost volume. Sufficient experiments demonstrate the efficiency and effectiveness of our method, outperforming the prior-arts on the FlyingThings3D and KITTI dataset. Our source codes will be released on https://***/IRMVLab/DELFlow.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimization of Synchronization in Monitoring and control systems

Optimization of Synchronization in Monitoring and Control Sy...

引用

Siberian Conference on control and Communications (SIBCON)

作者： Aleksandr Nikonov Galina Nikonova Lev Pavlov Automated information processing and control systems Omsk State Technical University Omsk Russia

The results of work on optimization of parameters of synchronization subsystems of high-speed monitoring and control systems based on phase principles are presented. The efficiency of synchronization in the region of ultrahigh frequencies is determined by the optimal structure of the subsystem and the parameters of the phase-locked loop. The influence of the dynamic characteristics of the subsystem, inertia of elements and signal delays on the capture bandwidth is shown. Optimization of the subsystem structure, correct selection of phase-locked parameters, and minimization of phase noise increase synchronization accuracy. Taking into account the influence of the inertia of the elements and signal delays in the control circuit allows selecting the parameters of the subsystem and provide necessary dynamic properties.

关键词： Particle beams Uncertainty Atmospheric measurements control systems Particle measurements Time measurement Delays

来源：评论

学校读者我要写书评

暂无评论

On the Segmentation of Sunflower Plants in UAV Photos

On the Segmentation of Sunflower Plants in UAV Photos

引用

Digital Signal processing and its Applications (DSPA), International Conference on

作者： Dmitriy Poleshchenko Ilia Mikhailov Vladislav Petrov Automated and information control systems department Stary Oskol Technological Institute n.a. A.A. Ugarov (branch) National University of Science and Technology MISIS Stary Oskol Russia

In precision farming, it is important to assess indicators such as seedling density, leaf area index (LAI), and to identify plant growth stages for yield prediction. Plant detection can provide a measure of crop density. Calculation of segmented pixel area in an image can be used to determine crop development and LAI. In this paper, an approach to solve the sunflower plant segmentation problem from photos produced by a UAV is considered. The problem is complicated by the limited size of the training sample. Unet and Feature Pyramid Network (FPN) are considered for segmentation. The result is that FPN is on average 1.05% more accurate than Unet and the average mIoU of the three classes is 1.26% higher. The effect of image brightness and contrast on accuracy in the case of different photo capture conditions is considered.

关键词： Training Image segmentation Brightness Crops Training data Signal processing algorithms Digital signal processing

来源：评论

学校读者我要写书评

暂无评论

automated Human Facial Emotion Recognition System Using Depthwise Separable Convolutional Neural Network

Automated Human Facial Emotion Recognition System Using Dept...

引用

2023 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology, IAICT 2023

作者： Hashan, Antor Mahamudul Al-Saeedi Adnan Adhab, K. Islam, Rizu Md Rakib Ul Avinash, Kumar Dey, Subhankar Ural Federal University Named after the First President of Russia B. N. Yeltsin Department of Intelligent Information Technologies Yekaterinburg Russia National University of Science and Technology 'MISiS' Department of Automated Control Systems Moscow Russia Ural Federal University Named after the First President of Russia B. N Yeltsin Department of Information Technology and Management Systems Yekaterinburg Russia Ural Federal University Named after the First President of Russia B. N. Yeltsin Department of Big Data Analytics and Video Analysis Methods Yekaterinburg Russia

ISBN: (纸本)9798350313635

The automatic human facial emotion recognition (AHFER) system has its wide significant contribution in several disciplines, such as human-computer collaboration, human-robot interaction, and so on. Multiple research projects have been conducted regarding this topic because it is a challenging and interesting task, especially in the area of computer vision. The purpose of the work is to recognize facial emotions using a depthwise separable convolutional neural network (DS-CNN). Apart from that, a facial emotion dataset has been proposed, and splitting functions, intensity normalization, image cropping, and grayscale conversion have been used in data pre-processing. The AHFER system is capable of recognizing four types of emotions: happy, sad, angry, and neutral. The results of the experiment showed that the AHFER method is 99 percent accurate when training and 93 percent accurate when validating. Additionally, we determined the confusion matrix with precision, recall, and fl-score. A comparison between the DS-CNN and DNN models was performed. The DS-CNN model performed significantly better than the DNN model. The DS-CNN model could be improved in the future by including more facial emotion categories. © 2023 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Development of a System for automated control of Planting Density, Leaf Area Index and Crop Development Phases by UAV Photos

Development of a System for Automated Control of Planting De...

引用

information, control, and Communication Technologies (ICCT), International Conference on

作者： Dmitriy Poleshchenko Vladislav Petrov Ilia Mikhailov Automated and information control systems department “MISIS” Stary Oskol Technological Institute n.a. A.A. Ugarov (branch) National University of Science and Technology Stary Oskol Russia

The paper describes the results of research into the possibility of creating a system for automated control of crop development indicators using UAV images and neural networks. Such architectures as YOLOv5, U-Net and FPN (Feature Pyramid Network) are considered. It is found out that YOLOv5m neural network is able to qualitatively detect plants on a sample of 363 images with an accuracy AP@.5:.95 of 92.4 %. The detection efficiency can be improved both by adding original images to the training sample and by increasing it artificially. Plant detection will help to determine the density of crops. It is shown that the calculation of the area of segmented pixels in an image can be used to determine crop development and leaf area index. FPNs are used for segmentation and it is obtained that FPNs are on average 1.05% more accurate than Unet and the average mIoU across the three classes is 1.26% larger.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Two-Stage Robust Optimization Under Decision Dependent Uncertainty

引用

IEEE/CAA Journal of Automatica Sinica 2022年第7期9卷 1295-1306页

作者： Yunfan Zhang Feng Liu Yifan Su Yue Chen Zhaojian Wang João P.S.Catalão State Key Laboratory of Power System and Generation Equipment the Department of Electrical EngineeringTsinghua UniversityBeijing 100084China Department of Mechanical and Automation Engineering the Chinese University of Hong KongHong Kong SARChina Ministry of Education Key Laboratory of System Control and Information Processing the Department of AutomationShanghai Jiao Tong Universityand also with Shanghai Engineering Research Center of Intelligent Control and ManagementShanghai 200240China Faculty of Engineering of the University of Porto and Institute for Systems and Computer Engineering Technology and Science(INESC TEC)Porto 4200-465Portugal IEEE

In the conventional robust optimization(RO)context,the uncertainty is regarded as residing in a predetermined and fixed uncertainty *** many applications,however,uncertainties are affected by decisions,making the current RO framework *** paper investigates a class of two-stage RO problems that involve decision-dependent *** introduce a class of polyhedral uncertainty sets whose right-hand-side vector has a dependency on the here-and-now decisions and seek to derive the exact optimal wait-and-see decisions for the second-stage problem.A novel iterative algorithm based on the Benders dual decomposition is proposed where advanced optimality cuts and feasibility cuts are designed to incorporate the uncertainty-decision *** computational tractability,robust feasibility and optimality,and convergence performance of the proposed algorithm are guaranteed with theoretical *** motivating application examples that feature the decision-dependent uncertainties are ***,the proposed solution methodology is verified by conducting case studies on the pre-disaster highway investment problem.

关键词： Benders decomposition decision-dependent uncertainty endogenous uncertainty robust optimization(RO)

来源：评论

学校读者我要写书评

暂无评论

Simulation Model of Cryptographic Data Protection Based on a Neural-Like Network with Nonlinear Synaptic Connections

Simulation Model of Cryptographic Data Protection Based on a...

引用

International Conference on Modern Problems of Radio Engineering, Telecommunications and Computer Science

作者： Ivan Tsmots Roman Tkachenko Vasyl Teslyuk Vasyl Rabyk Yurii Opotyak Department of Automated Control Systems Lviv Polytechnic National University Lviv Ukraine Department of Publishing Information Technologies Lviv Polytechnic National University Lviv Ukraine Department of Radiophysics and Computer Technologies Ivan Franko National University of Lviv Lviv Ukraine

ISBN: (数字)9798331520564

ISBN: (纸本)9798331520571

A method of cryptographic data protection using neural-like networks based on the model of geometric transformations is proposed. Algorithms for non-iterative training of neural-like structures based on a model of geometric transformations and for nonlinear data encryption based on neural-like structures with nonlinear synaptic connections are implemented in C language on a Raspberry Pi microcomputer. The formation of data, necessary for designing neural-like structures of a given architecture for nonlinear encryption and decryption, with the subsequent possibility of their use in hardware implementation on FPGA, is carried out. An example of training a neural-like structure and nonlinear neural-like cryptographic data protection by this structure is considered.

关键词： Training Software algorithms Data protection Computer architecture Microcomputers Data models Polynomials Hardware Encryption Field programmable gate arrays

来源：评论

学校读者我要写书评

暂无评论

Synthesis of Temporally-Robust Policies for Signal Temporal Logic Tasks using Reinforcement Learning

Synthesis of Temporally-Robust Policies for Signal Temporal ...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Siqi Wang Shaoyuan Li Li Yin Xiang Yin Department of Automation and Key Laboratory of System Control and Information Processing Shanghai Jiao Tong University Shanghai China Institute of Systems Engineering Macau University of Science and Technology Taipa China

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

This paper investigates the problem of designing control policies that satisfy high-level specifications described by signal temporal logic (STL) in unknown, stochastic environments. While many existing works concentrate on optimizing the spatial robustness of a system, our work takes a step further by also considering temporal robustness as a critical metric to quantify the tolerance of time uncertainty in STL. To this end, we formulate two relevant control objectives to enhance the temporal robustness of the synthesized policies. The first objective is to maximize the probability of being temporally robust for a given threshold. The second objective is to maximize the worst-case spatial robustness value within a bounded time shift. We use reinforcement learning to solve both control synthesis problems for unknown systems. Specifically, we approximate both control objectives in a way that enables us to apply the standard Q-learning algorithm. Theoretical bounds in terms of the approximations are also derived. We present case studies to demonstrate the feasibility of our approach.

关键词： Measurement Uncertainty Q-learning Approximation algorithms Robustness Logic Task analysis

来源：评论

学校读者我要写书评

暂无评论

Analysis of Methods of Augmentation of Images of the Branding of Cast Billet at A. A. Ugarov Oskol Electrometallurgical Plant

Analysis of Methods of Augmentation of Images of the Brandin...

引用

International Conference on control systems, Mathematical Modelling, Automation and Energy Efficiency (SUMMA)

作者： Dmitriy Poleshchenko Ivan Zorin Automated and Information Control Systems Department Stary Oskol Technological Institute n.a. A.A. Ugarov (Branch) National University of Science and Technology MISIS Stary Oskol Russia

The paper deals with the procedure of increasing the training sample size using augmentation methods. The paper considers the main methods of image augmentation, selects the most suitable ones for solving the presented class of problems, and approbation of these methods with testing on the deep learning neural network Faster R-CNN. It is shown that the use of augmentation methods to increase the image base allows to raise the quality of training of the neural network by 1%. It is also found that the type of augmentation should correlate with the prevailing type of disturbance affecting the image quality.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Spectral Approach to Solving the Problem of Bithreshold Separability

Spectral Approach to Solving the Problem of Bithreshold Sepa...

引用

International Computer Sciences and information Technologies (CSIT)

作者： Vladyslav Kotsovsky Anatoliy Batyuk Department of Information Management Systems and Technologies Uzhhorod National University Uzhhorod Ukraine Department of Automated Control Systems Lviv Polytechnic National University Lviv Ukraine

ISBN: (纸本)9798350334326

The paper deals with the issues concerning the application of methods of harmonic analysis in the theory of bithreshold neural units. We show that the values of spectral coefficients of first two orders of a dichotomy function of the finite set in n-dimensional space give answer to the question of the bithreshold separability of two subsets in which this dichotomy results. The established properties of bithreshold neurons can be useful in the design of off-line learning algorithms developed on the base of the spectral approach.

关键词： Neurons Harmonic analysis Classification algorithms information technology

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：