检索结果-内蒙古大学图书馆

Chinese Automation Congress (CAC)

作者： Hao Zhu Fangrong Chen Bin Guo Automotive Electronics and Embedded System Engineering Research Center Chongqing University of Posts and Telecommunications Chongqing China Automotive Electronics and Embedded System Engineering Research Center and Key Laboratory of Industrial Internet of Things & Networked Control Ministry of Education College of Automation Chongqing University of Posts and Telecommunications Chongqing P. R. China

This paper presents a robust and real-time guardrail detection and tracking algorithm, based on the three-dimensional information obtained from lidar sensor. Height feature and corner feature are used to extract guardrail feature points out in guardrail detection process, while a cluster method is used to filter the useless guardrail points. Furthermore, an adaptive region of interest (AROI) is proposed to improve the efficiency and accuracy of the detection algorithm. To determine the boundary of AROI, an improved Kalman filter algorithm is proposed to track the feature point set on both sides of the road at the same time in each frame. The whole system works in real-time and achieves detection accuracy above 96% on a test database.

关键词： Feature extraction Laser radar Clustering algorithms Radar tracking Roads Prediction algorithms Real-time systems

来源：评论

学校读者我要写书评

暂无评论

An Incremental Learning Framework for Skeletal-based Hand Gesture Recognition with Leap Motion

An Incremental Learning Framework for Skeletal-based Hand Ge...

引用

IEEE International Conference on Cyber Technology in Automation, control, and Intelligent systems

作者： Jie Li Junpei Zhong Fei Chen Chenguang Yang Key Laboratory of Autonomous Systems and Networked Control School of Automation Science and Engineering South China University of Technology Guangzhou China School of Science and Technology Nottingham Trent University Nottingham UK Istituto Italiano di Tecnologia via Morego 30 Genova Italy Bristol Robotics Laboratory University of the West of England Bristol UK

ISBN: (数字)9781728107707

ISBN: (纸本)9781728107714

Hand gesture recognition has become the focus of researchers lately because of its manifold applications in various fields. Leap Motion (LM) is a device to obtain useful and accurate information of the hand action, which is suitable for collecting the three-dimensional (3D) human hand gesture. In this paper, a novel framework which consists of an incremental learning (IL) algorithm without deep structure is proposed and applied to hand gestures classification that explicitly aimed to the LM data. The same datasets are used to train the proposed framework and the conventional Long Short Term Memory Recurrent Neural Network (LSTM-RNN). Due to the structural advantage of the proposed model, the recognition performance is improved distinctly in robustness and training time than the LSTM network. Moreover, convincing experiment results are given to illustrate that the solution is more efficient in static gesture classification.

关键词： Logic gates Computer architecture Gesture recognition Training Feature extraction Microprocessors Three-dimensional displays

来源：评论

学校读者我要写书评

暂无评论

Parameter Identification of JONSWAP Spectrum Acquired by Airborne LIDAR

引用

Journal of Ocean University of China 2017年第6期16卷 998-1002页

作者： YU Yang PEI Hailong XU Chengzhong Key Laboratory of Autonomous Systems and Networked Control Ministry of EducationSouth China University of Technology LAGEP Batiment CPEUniversité Claude Bernard Lyon 1

In this study, we developed the first linear Joint North Sea Wave Project(JONSWAP) spectrum(JS), which involves a transformation from the JS solution to the natural logarithmic scale. This transformation is convenient for defining the least squares function in terms of the scale and shape parameters. We identified these two wind-dependent parameters to better understand the wind effect on surface waves. Due to its efficiency and high-resolution, we employed the airborne Light Detection and Ranging(LIDAR) system for our measurements. Due to the lack of actual data, we simulated ocean waves in the MATLAB environment, which can be easily translated into industrial programming language. We utilized the Longuet-Higgin(LH) random-phase method to generate the time series of wave records and used the fast Fourier transform(FFT) technique to compute the power spectra density. After validating these procedures, we identified the JS parameters by minimizing the mean-square error of the target spectrum to that of the estimated spectrum obtained by FFT. We determined that the estimation error is relative to the amount of available wave record data. Finally, we found the inverse computation of wind factors(wind speed and wind fetch length) to be robust and sufficiently precise for wave forecasting.

关键词： JONSWAP spectrum parameter identification least square method airborne LIDAR

来源：评论

学校读者我要写书评

暂无评论

Omnidirectional Mobile Robot control based on Mixed Reality and sEMG Signals

Omnidirectional Mobile Robot Control based on Mixed Reality ...

引用

Chinese Automation Congress

作者： Mulun Wu Yanbin Xu Chenguang Yang Ying Feng Key Laboratory of Autonomous Systems and Networked Control college of Automation Scienceand Engineering South China University of Technology Guangzhou China

Robots are an important part of social production now, and their control methods have become an important research topic. There is a greater need for remote control and richer ways of interacting. In this paper, virtual reality and the surface electromyography (sEMG) signals are combined with the control of the omnidirectional mobile robot (OMR), and the programs of two devices, the HoloLens and the MYO armband, are respectively programmed and developed, so that they can work together to control the OMR. The basic control method is that HoloLens wearer controls the movement direction of the OMR through gesture or gaze. MYO armband wearer generate different sEMG signals through different gesture to control the velocity of the OMR. When two devices are used together, they can control all the motion of the OMR.

关键词： Omnidirectional mobile robot Virtual reality Surface electromyography Teleoperation

来源：评论

学校读者我要写书评

暂无评论

Dynamic Surface control of Shape Memory Alloy Actuating systems with Inverse Duhem Hysteresis Compensation

Dynamic Surface Control of Shape Memory Alloy Actuating Syst...

引用

IEEE International Conference on Mechatronics and Automation

作者： Rui Li Ying Feng Zedong Hu School of Automation Science and Engineering Key Laboratory of Autonomous Systems and Networked Control South China University of Technology Guangzhou China

Shape Memory Alloys actuators are a class of smart materials-based actuators, and show a good output performance with high force to mass ratio, biocompatibility and small size. However, the internal hysteresis nonlinearities between the input temperature and output displacement adversely affect the output accuracy and they cannot be mitigated directly because of the strong non-smooth feature of SMA materials. To improve the actuating ability of SMA system, an estimated hysteresis inverse is employed based on Duhem model as the compensation of SMA actuator in this paper. Considering the dynamics of the SMA actuating system and the compensation error, a dynamic surface controller (DSC) is designed. The simulation results validate the effectiveness of the proposed approach.

关键词： Hysteresis Actuators Wires Couplers Mathematical model Pulse width modulation Force

来源：评论

学校读者我要写书评

暂无评论

Encoding Space to Count Multi-Targets with Multiplexed Binary Infrared Sensors

Encoding Space to Count Multi-Targets with Multiplexed Binar...

引用

International Conference on Mobile Ad-hoc and Sensor Networks, MSN

作者： Longxiang Luo Yang Xiao Wei Liang Key Laboratory of Networked Control System Shenyang Institute of Automation Chinese Academy of Sciences Shenyang State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang Chinese Academy of Sciences Institutes for Robotics and Intelligent Manufacturing Shenyang China University of Chinese Academy of Sciences Beijing China Department of Computer Science The University of Alabama Tuscaloosa AL USA

ISBN: (数字)9781728152127

ISBN: (纸本)9781728152134

Recently, many researchers multiplex binary infrared sensors in object tracking, habitat monitoring, and atypical behavior detection. Due to the binary digit output of binary sensors, multiplex binary sensors may lead to count the wrong number of targets when three or more targets present in the field of interest (FOI). We call this as the invisible targets' problem. To enhance the sensing results of sensors, a reference structure tomography technique is used to segment and code the FOI by modulating the sensing view of sensors. In this paper, we propose a subregion coding method to count targets moving in the FOI. Hexagon modulators are designed to make their projections segment the FOI into hexagon cells. We also propose a signature construct scheme to code cells and a encoder to count the number of targets in the FOI. Experiment results show that the accuracy to correctly count targets of our method is around 90% which is much better than 45% of a conventional method.

关键词： Modulation Monitoring Shape Sensor systems Encoding Intelligent sensors

来源：评论

学校读者我要写书评

暂无评论

Corrigendum to "Intravenous immunoglobulin alleviates Japanese encephalitis virus-induced peripheral neuropathy by inhibiting the ASM/ceramide pathway" [Int. Immunopharmacol. 133 (2024) 112083]

引用

International immunopharmacology 2024年 134卷 112270页

作者： Na Zhang Guowei Wang Liping Yang Jinyuan Zhang YanPing Yuan Lijun Ma Huanyu Wang Zhenhai Wang School of Clinical Medicine Ningxia Medical University Yinchuan Ningxia China Neurology Center General Hospital of Ningxia Medical University Yinchuan Ningxia China. School of Clinical Medicine Ningxia Medical University Yinchuan Ningxia China. Department of Human Anatomy Histology and Embryology School of Basic Medicine Ningxia Medical University Yinchuan Ningxia China. National Key Laboratory of Intelligent Tracking and Forecasting for Infectious Diseases National Institute for Viral Disease Control and Prevention Chinese Center for Disease Control and Prevention Beijing China. Electronic address: wanghy@***. Neurology Center General Hospital of Ningxia Medical University Yinchuan Ningxia China Institute of Medical Sciences General Hospital of Ningxia Medical University Diagnosis and Treatment Engineering Technology Research Center of Nervous System Diseases of Ningxia Hui Autonomous Region Yinchuan China. Electronic address: wangzhenhai1968@***.

来源：评论

学校读者我要写书评

暂无评论

IMU Preintegration for Visual-Inertial Odometry Pose Estimation

IMU Preintegration for Visual-Inertial Odometry Pose Estimat...

引用

第37届中国控制会议

作者： Fuchun Liu Xuan Su Yun He Fei Luo Huanli Gao College of Automation Science and Engineering The Key Laboratory of Autonomous Systems and Networked Control（ASNC） Ministry of Education South China University of Technology

In this paper,based on Inertial Measurement Unit（IMU） preintegration,a pose estimation algorithm for Visual-Inertial Odometry（VIO） system has been ***,we developed the kinematic equation of acceleration and angular velocity of *** avoid the re-integration caused by the change of the system states,the IMU measurements are preintegrated on the Riemannian manifold of ***,we studied the propagation characteristic of noise and derived the state transition equation of the *** the influence of noise on pose estimation can be dramatically *** with the famous Okvis algorithm,experimental results on two public datasets of EuRoC show that the proposed IMU preintegration algorithm achieves good estimation median of translation error with 0.14 m,which is better than Okvis with 0.24 m,

关键词： IMU Preintegration Manifold Kinematic Equation VIO Noise Propagation

来源：评论

学校读者我要写书评

暂无评论

Active Disturbance Rejection Based Iterative Learning control for Variable Air Volume Central Air-Conditioning system

Active Disturbance Rejection Based Iterative Learning Contro...

引用

Data Driven control and Learning systems (DDCLS)

作者： Shiying Lu Wei Ai Xiangyang Li Key Laboratory of Autonomous Systems and Networked Control Ministry of Education School of Automation Science and Engineering South China University of Technology Guangzhou China

ISBN: (纸本)9781538626191

The Variable Air Volume (VAV) Central Air-Conditioning system is a complicated system with non-linearity, large-time delay and strong inertia, thus it is difficult to design an effective controller. Iterative Learning control (ILC) takes good effect in controlled process with repeatability and periodicity, but it cannot cope with uncertain disturbance explicitly. A creative algorithm, Active Disturbance Rejection based Iterative Learning control (ADR-Based ILC), is proposed to improve ILC's performance in VAV control system. ADR-Based ILC compensates the disturbance explicitly caused by ambient temperature, heat from people and machines, and makes it higher control precision and higher energy-efficiency. An accurate model of VAV system is built in TRNSYS platform, and ADR-Based ILC is proved to be more effective than fuzzy PID and ILC.

关键词： Uncertainty Iterative learning control Buildings Cooling Heating systems Time-domain analysis

来源：评论

学校读者我要写书评

暂无评论

Discrete Time-Varying Four Fundamental Operations Implemented by Euler Forward Difference 36

Discrete Time-Varying Four Fundamental Operations Implemente...

引用

第36届中国控制会议

作者： Yunong Zhang Huihui Gong Jian Li Binbin Qiu Min Yang School of Information Science and Technology Sun Yat-sen University Key Laboratory of Autonomous Systems and Networked Control Ministry of Education

ISBN: (纸本)9781538629185

Time-varying problems are widely encountered in various engineering fields,such as signal processing,construction monitoring,and ***,traditional arithmetics intrinsically aim at time-invariant problems *** running on relatively low-speed processing units,traditional arithmetics may generate quite large and unacceptable lagging *** this paper,the problems of discrete time-varying four fundamental operations(TVFFO) are *** order to eliminate the lagging errors,based on Zhang dynamics(ZD) and Euler forward difference(EFD) formula,discrete computing models,which are named Euler-implemented discrete ZD(EIDZD) models,are proposed and *** that the EIDZD models are with an error pattern 0(g),where g denotes the sampling ***,illustrative numerical experiments of EIDZD models are also conducted,which show the high accuracy of EIDZD models.

关键词： Time-varying four fundamental operations（TVFFO） Zhang dynamics（ZD） Continuous time-varying models Euler forward difference（EFD） Euler-implemented discrete ZD（EIDZD） models Numerical experiments

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：