检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Zhang, Yang Yu, Xin Lu, Xiaobo Liu, Ping The Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China The Australian Institute of Artificial Intelligence University of Technology Sydney UltimoNSW2007 Australia The School of Automation Southeast University Nanjing210096 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing210096 China Singapore138634 Singapore

In this paper, we study the task of hallucinating an authentic high-resolution (HR) face from an occluded thumbnail. We propose a multi-stage Progressive Upsampling and Inpainting Generative Adversarial Network, dubbed Pro-UIGAN, which exploits facial geometry priors to replenish and upsample (8×) the occluded and tiny faces (16×16 pixels). Pro-UIGAN iteratively (1) estimates facial geometry priors for low-resolution (LR) faces and (2) acquires non-occluded HR face images under the guidance of the estimated priors. Our multi-stage hallucination network upsamples and inpaints occluded LR faces via a coarse-to-fine fashion, significantly reducing undesirable artifacts and blurriness. Specifically, we design a novel cross-modal attention module for facial priors estimation, in which an input face and its landmark features are formulated as queries and keys, respectively. Such a design encourages joint feature learning across the input facial and landmark features, and deep feature correspondences will be discovered by attention. Thus, facial appearance features and facial geometry priors are learned in a mutually beneficial manner. Extensive experiments show that our Pro-UIGAN attains visually pleasing completed HR faces, thus facilitating downstream tasks, i.e., face alignment, face parsing, face recognition as well as expression classification. Copyright © 2021, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Moving object detection in framework of compressive sampling

引用

Chinese Journal of systems Engineering and Electronics 2010年第5期000卷

作者： Jing Li Junzheng Wang Wei Shen Key Laboratory of Complex System Intelligent Control and Decision School of AutomationBeijing Institute of Technology Beijing 100081 P. R. China

Compressive sensing is a revolutionary idea proposed recently to achieve much lower sampling rate for signals. In the image application with limited resources the camera data can be stored and processed in compressed form. An algorithm for moving object and region detection in video using a compressive sampling is developed. The algorithm estimates motion information of the moving object and regions in the video from the compressive measurements of the current image and background *** algorithm does not perform inverse compressive operation to obtain the actual pixels of the current image nor the estimated background. This leads to a computationally efficient method and a system compared with the existing motion estimation *** experimental results show that the sampling rate can reduce to 25% without sacrificing performance.

关键词： compressive sampling compressive measurements moving object detection

来源：评论

学校读者我要写书评

暂无评论

Multi-robot Path Planning and Trajectory Smoothing

Multi-robot Path Planning and Trajectory Smoothing

引用

IEEE International Conference on Automation science and Engineering (CASE)

作者： Hub Ali Gang Xiong Huaiyu Wu Bin Hu Zhen Shen Hongxing Bai School of Mechanical and Electrical Engineering University of Electronic Science and Technology of China State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing Cloud Computing Center Chinese Academy of Sciences Dongguan China Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation Chinese Academy of Sciences China Hubei Jointown Technology Co. Ltd Artificial Intelligence Research Institute Wuhan China

ISBN: (数字)9781728169040

ISBN: (纸本)9781728169057

In this paper we consider a problem in task execution for multi-robot trajectory planning with collision avoidance in a shared working environment. Consider two or more robots generating trajectories towards their respective goal positions. The collision may occur if their trajectory coordinates are intersecting at a point or follow the same path segment simultaneously. The central planner is introduced to control robot motion in the collision state and to reduce the complexity of the multi-robot path planning system. The global path for every robot is generated by the $\mathrm{A}^{*}$ algorithm in a grid-based environment. The path has presented a sequence of optimal grid numbers and later transformed into Cartesian coordinates for smooth trajectory generation. The central planner takes an optimal grid sequence for every robot to analyze the collision state according to its cost value. It regenerates the trajectories to minimize the complexity cost value and replaces the previous trajectory based on minimum cost value. In the collision state, the central planner allows one robot at a time to pass along the conflict path segment and hold others in queue at a safety offset distance until the previous robot passes safely. The algorithm has been applied to robots working in a shared environment in complex maps and the simulations is performed with MATLAB to calculate the efficiency of this approach for handling collision states in a multi-robot path planning system.

关键词： Robot kinematics Trajectory Collision avoidance Task analysis Resource management

来源：评论

学校读者我要写书评

暂无评论

Robust filtering for networked systems with random transmission delays and packet dropouts

Robust filtering for networked systems with random transmiss...

引用

作者： Cai, Yunze Wang, Hua O. Tanaka, Kazuo Xu, Xiaoming Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing 800 Dongchuan Rd. Shanghai 200240 China Department of Mechanical Engineering Boston University Boston MA 02215 United States Department of Mechanical Systems and Intelligent Systems University of Electro-Communications Tokyo 182-8585 Japan Department of Automation Shanghai Jiao Tong University 800 Dongchuan Rd. Shanghai 200240 China University of Shanghai for Science and Technology 16 Jun Gong Rd. Shanghai 200093 China

ISBN: (纸本)9781457700804

This paper addresses a robust H∞ filtering problem for networked systems that are subject to both random transmission delays and packet dropouts. To start with, a data transmission model is established by employing random series with Bernoulli distributions. A sufficient condition for robust stability with H∞ constraints is derived for the filtering error system. The robust filter is designed in terms of the feasibility of a linear matrix inequality (LMI). The numerical examples are provided to show the effectiveness of the data transmission model and the proposed filtering method. © 2011 AACC American Automatic control Council.

关键词： Linear matrix inequalities

来源：评论

学校读者我要写书评

暂无评论

An Anti-Rolling control Method of Rudder Fin system Based on Adrc Decoupling and Ddpg Parameter Adjustment

SSRN

引用

SSRN 2022年

作者： Sun, Mingxiao Zhang, Wenyu Zhang, Yongde Luan, Tiantian Yuan, Xiaoliang Li, Xiaogang School of Automation Harbin University of Science and Technology No.52 Xuefu Road Nangang District Heilongjiang Province Harbin City150080 China Heilongjiang Provincial Key Laboratory of Complex Intelligent System and Integration Harbin University of Science and Technology No.52 Xuefu Road Nangang District Heilongjiang Province Harbin City150080 China Key Laboratory of Advanced Manufacturing and Intelligent Technology Ministry of Education Harbin University of Science and Technology No.52 Xuefu Road Nangang District Heilongjiang Province Harbin City150080 China Wuxi CREG Urban Rail Transit Equipment Co. Ltd No. 1061 Jiaoshan Road Xishan Development Zone Jiangsu Province Wuxi214000 China

To achieve high-precision attitude control of ships, the output delay, state coupling, and controller parameter maladjustment of the rudder fin joint anti-rolling system are studied. A predictive anti-rolling method based on active disturbance rejection control (ADRC) and deep deterministic policy gradient (DDPG) is proposed. The external forces on the ship are analyzed, and a three-degree-of-freedom mathematical model considering rolling, yawing, and pitching is established. The model is decoupled using the idea of ADRC total disturbance for the state coupling problem, then the pitch ADRC controller and the roll-yaw predictive observer are designed respectively. In pitch ADRC, the nonlinear extended state observer (NLESO) is used to observe the total disturbance between models. And the total disturbance observations are feedforward compensated to the error control law. As a result, the rapidity of reference output tracking and robustness of total disturbance are realized. The roll-yaw predictive observer solves the output delay by feeding the predicted output back to the controller instead of the actual output. To ensure the accuracy of the prediction output, the DDPG algorithm is introduced to modify the parameters of the prediction observer in real-time. Finally, state constraints are added to solve the rudder angle and fin angle control laws. © 2022, The Authors. All rights reserved.

关键词： controllers

来源：评论

学校读者我要写书评

暂无评论

fMRI-based Brain Disease Diagnosis: A Graph Network Approach

TechRxiv

引用

TechRxiv 2023年

作者： Chen, Qi-Qi Gao, Yubing Tong, Wei Li, Ping Wu, Edmond Q. The Department of Automation Shanghai Jiao Tong University Shanghai200240 China The Nanjing University of Science and Technology Jiangsu210008 China The School of Biological Science and Medical Engineering Beihang University Beijing100191 China The Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Jiao Tong University Shanghai200240 China The Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University Shanghai200240 China

As a non-invasive brain imaging technology, functional magnetic resonance imaging (fMRI) provides a basic tool for brain functional network modeling and brain disease diagnosis. Problems, such as large number of parameters, low training efficiency, and poor interpretability, are encountered in mainstream models because of the high complexity of fMRI and brain networks. To solve these problems, a novel structure feature combined graph neural network (SFC-GNN) with a low number of parameters is proposed. In particular, SFC-GNN is composed of 1) the graph convolution layer of the brain region perception and 2) the node pooling layer of the graph structure feature (GSF). It also receives the sparse brain graph modeled by each subject’s fMRI as input. Especially, the GSF layer can select brain regions that are important for classification, thereby localizing all active regions related to brain disease. Moreover, a group network is constructed according to the correlation among subjects, and SFC-GNN can be extended further to a node classification model to achieve better diagnosis performance. The proposed method has been validated on the ABIDE and ADNI datasets, thereby showing the effectiveness of our proposed method in various experiments. © 2023, CC BY.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Dynamic mode decomposition for Koopman spectral analysis of elementary cellular automata

arXiv

引用

arXiv 2023年

作者： Taga, Keisuke Kato, Yuzuru Yamazaki, Yoshihiro Kawahara, Yoshinobu Nakao, Hiroya Department of Physics School of Advanced Science and Engineering Waseda University Tokyo169-8555 Japan Department of Complex and Intelligent Systems School of Systems Information Science Future University Hakodate Hokkaido041-8655 Japan Graduate School of Information Science and Technology Osaka University Osaka565-0871 Japan Center for Advanced Intelligence Project RIKEN Tokyo103-0027 Japan Department of Systems and Control Engineering School of Engineering Tokyo Institute of Technology Tokyo152-8552 Japan

We apply Dynamic Mode Decomposition (DMD) to Elementary Cellular Automata (ECA). Three types of DMD methods are considered and the reproducibility of the system dynamics and Koopman eigenvalues from observed time series are investigated. While standard DMD fails to reproduce the system dynamics and Koopman eigenvalues associated with a given periodic orbit in some cases, Hankel DMD with delay-embedded time series improves reproducibility. However, Hankel DMD can still fail to reproduce all the Koopman eigenvalues in specific cases. We propose an Extended DMD method for ECA that uses nonlinearly transformed time series with discretized Walsh functions and show that it can completely reproduce the dynamics and Koopman eigenvalues. Linear-algebraic backgrounds for the reproducibility of the system dynamics and Koopman eigenvalues are also discussed. Copyright © 2023, The Authors. All rights reserved.

关键词： Dynamic mode decomposition

来源：评论

学校读者我要写书评

暂无评论

Rules-based autonomous obstacle avoidance for mobile robots

引用

Zhongnan Daxue Xuebao (Ziran Kexue Ban)/Journal of Central South University (science and technology) 2011年第SUPPL. 1期42卷 493-497页

作者： Wang, Qi-Zhi Xu, De School of Computer Science and Information Technology Beijing Jiaotong University Beijing 100044 China Key Laboratory of Intelligent Control of Complex Systems Institute of Automation Chinese Acad. of Sci. Beijing 100080 China

A real time and autonomous obstacle avoidance method based on rules for mobile robots was presented. Wall- along algorithm was dynamically implemented in unknown environment without collision. The results show that th... 详细信息

关键词： Mobile robots

来源：评论

学校读者我要写书评

暂无评论

The new field power device based on super capacitor and it's application

引用

Binggong Xuebao/Acta Armamentarii 2012年第SUPPL2期33卷 417-422页

作者： Bai, Yong-Qiang Jin, Tian-Xu Wang, Hai-Jie School of Automation Beijing Institute of Technology Beijing 100081 China Key Laboratory of Complex System Intelligent Control and Decision Ministry of Education Beijing Institute of Technology Beijing 100081 China Harbin Jurong New Power Co. Ltd. Harbin 150078 Heilongjiang China

Based on special demand of field power for artillery electric drive system and analysis of the existing power system, a new design of hybrid power device with super capacitor is proposed to replace the traditional battery, which is more suitable to the field requirements, and has more energy efficiency, greater power ratio, and energy ratio. The design criteria and formula are presented. Test results show that the hybrid device, compared with the traditional power device, has the advantages of high efficiency, high energy volume ratio, high weight ratio, strong environmental adaptability, and good lower temperature performances, and can meet the demand of power device in the field condition.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Method for extracting edge features of welding seam based on an adaptive binary threshold

引用

Hanjie Xuebao/Transactions of the China Welding Institution 2008年第7期29卷 34-38页

作者： Yan, Zhiguo Xu, De Li, Yuan Key Laboratory of Complex System and Intelligent Sciences Institute of Automation Chinese Academy of Sciences Beijing 100190 China Graduate University Chinese Academy of Sciences Beijing 100049 China Department of Information Science and Technology Beijing Institute of Technology Beijing 100081 China

This paper presents an image processing method which can extract the edge of welding seam reliably. Histogram equalization is performed on the gradient image of the original welding image to compress the gray distribution of pixels which represent the edge information of the image. Then the global binary threshold is determined. A small window is sliding on the histogram equalized gradient image with a step equal to half-width of the window to determine the local binary threshold in the window area. The adaptive binary threshold in the window area is obtained by combining the global and the local binary threshold. The image is binarized according to the adaptive binary threshold. Moreover, an iterative method is designed to remove noises in the binary image. The testing results of practical images demonstrate the validity of the method.

关键词： Binary images

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：