检索结果-内蒙古大学图书馆

International IEEE Conference on Intelligent Systems, IS

作者： Geesara Prathap Ilya Afanasyev Center for Technologies in Robotics and Mechatronics Components Innopolis University Innopolis Russia Institute of Robotics Innopolis University Innopolis Russia

ISBN: (纸本)9781538670989;9781538670972

Building detection from satellite multispectral imagery data is being a fundamental but a challenging problem mainly because it requires correct recovery of building footprints from high-resolution images. In this work, we propose a deep learning approach for building detection by applying numerous enhancements throughout the process. Initial dataset is preprocessed by 2-sigma percentile normalization. Then data preparation includes ensemble modelling where 3 models were created while incorporating OpenStreetMap data. Binary Distance Transformation (BDT) is used for improving data labeling process and the U-Net (Convolutional Networks for Biomedical Image Segmentation) is modified by adding batch normalization wrappers. Afterwards, it is explained how each component of our approach is correlated with the final detection accuracy. Finally, we compare our results with winning solutions of SpaceNet 2 competition for real satellite multispectral images of Vegas, Paris, Shanghai and Khartoum, demonstrating the importance of our solution for achieving higher building detection accuracy.

关键词： Buildings Image resolution Training Labeling Satellite broadcasting Data models Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Deep learning approach for building detection in satellite multispectral imagery

arXiv

引用

arXiv 2018年

作者： Prathap, Geesara Afanasyev, Ilya Center for Technologies in Robotics and Mechatronics Components Innopolis University Innopolis Russia Institute of Robotics Innopolis University Innopolis Russia

Building detection from satellite multispectral imagery data is being a fundamental but a challenging problem mainly because it requires correct recovery of building footprints from high-resolution images. In this work, we propose a deep learning approach for building detection by applying numerous enhancements throughout the process. Initial dataset is preprocessed by 2-sigma percentile normalization. Then data preparation includes ensemble modelling where 3 models were created while incorporating Open Street Map data. Binary Distance Transformation (BDT) is used for improving data labeling process and the U-Net (Convolutional Networks for Biomedical Image Segmentation) is modified by adding batch normalization wrappers. Afterwards, it is explained how each component of our approach is correlated with the final detection accuracy. Finally, we compare our results with winning solutions of Space Net 2 competition for real satellite multispectral images of Vegas, Paris, Shanghai and Khartoum, demonstrating the importance of our solution for achieving higher building detection accuracy. Copyright © 2018, The Authors. All rights reserved.

关键词： Metadata

来源：评论

学校读者我要写书评

暂无评论

Map Comparison of Lidar-based 2D SLAM Algorithms Using Precise Ground Truth

Map Comparison of Lidar-based 2D SLAM Algorithms Using Preci...

引用

International Conference on Control, Automation, robotics and Vision (ICARCV)

作者： Rauf Yagfarov Mikhail Ivanou Ilya Afanasyev Center for Technologies in Robotics and Mechatronics Components Innopolis University Innopolis Russia Institute of Robotics Innopolis University Innopolis Russia

This paper presents a comparative analysis of three most common ROS-based 2D Simultaneous Localization and Mapping (SLAM) libraries: Google Cartographer, Gmapping and Hector SLAM, using a metrics of average distance to the nearest neighbor (ADNN). Each library was applied to construct a map using data from 2D lidar that was placed on an autonomous mobile robot. All the approaches have been evaluated and compared in terms of inaccuracy constructed maps against the precise ground truth presented by FARO laser tracker in static indoor environment.

关键词： Simultaneous localization and mapping Two dimensional displays Measurement Mobile robots Laser radar

来源：评论

学校读者我要写书评

暂无评论

Autonomous Drifting Control in 3D Car Racing Simulator

Autonomous Drifting Control in 3D Car Racing Simulator

引用

International IEEE Conference on Intelligent Systems, IS

作者： Igor Zubov Ilya Afanasyev Aidar Gabdullin Ruslan Mustafin Ilya Shimchik Center for Technologies in Robotics and Mechatronics Components Innopolis University Innopolis Russia Institute of Robotics Innopolis University Innopolis Russia Innopolis University Innopolis Russia

ISBN: (纸本)9781538670989;9781538670972

It is known that drifting is a driving technique, when a car is moving along some direction different from its steering trajectory, having a slip angle at the rear axle greater then at the forward axle. Even though it is often used in auto sport, it is still not applied to everyday life due to safety concerns. On the other hand, using all car control possibilities can provide safe driving even in extreme conditions without a crash. This article is devoted to the investigation and development of a drift controller and its application in electric car simulation with studying the problems of autonomous drifting and stabilization around an equilibrium state. To implement the drift controller, we used all-wheel drive Roborace Robocar in Speed Dreams car racing simulator, applying the mechanical bicycle and simplified nonlinear tire models to define tire parameters, and two state equilibrium model to compute the equilibrium points. Although the steering drift controller is rather simple and based on errors from equilibrium values, to find controller's gains the model was linearized, and controller was represented as full-state feedback that guaranteed its stability.

关键词： Automobiles Tires Computational modeling Wheels Mathematical model Friction Robots

来源：评论

学校读者我要写书评

暂无评论

Stiffness analysis of parallel manipulator navaro with dual actuation modes

Stiffness analysis of parallel manipulator navaro with dual ...

引用

2018 International Russian Automation Conference, RusAutoCon 2018

作者： Klimchik, Alexandr Pashkevich, Anatol Chablat, Damien Innopolis University Center for Technologies in Robotics and Mechatronics Components Innopolis Russia IMT Atlantique Automation Production and Computer Sciences Nantes France LS2N Centre National de la Recherche Scientifique Nantes France

ISBN: (纸本)9781538649381

The paper deals with enhanced stiffness analysis of the NaVaRo robot, a three-degree-of-freedom planar parallel manipulator with variable actuation schemes that are switched from one to another in order to avoid kinematic singularities. The main scientific contribution is in the area of extension of classical MSA technique for the case of complex open-loop and closed-loop manipulators. The proposed approach produces the Cartesian stiffness matrices and presents the manipulator stiffness model as a set of conventional equations describing the link elasticities that are supplemented by a set of constraints describing connections between links. The main advantage is computational simplicity that straightforwardly aggregates the stiffness model equations avoiding traditional column/row merging procedures of the conventional MSA. The efficiency of this approach is illustrated by comparison analysis of NaVaRo manipulator for different actuation modes. © 2018 IEEE.

关键词： Stiffness

来源：评论

学校读者我要写书评

暂无评论

On the movement of the rope robot on a vertical surface

引用

IOP Conference Series: Materials Science and Engineering 2020年第1期747卷

作者： M I Efimov E S Briskin N G Sharonov Department of Theoretical Mechanics Volgograd State Technical University 28 Lenin Avenue Volgograd 400005 Russia Center for Technology Components of Robotics and Mechatronics Innopolis University Innopolis Russia

A method of moving a cable robot on a vertical surface with support on it is considered. The motion of the robot with adjustable, with the help of the load, the position of the center of mass is investigated. The stages of overcoming obstacles by such a robot and the equations of motion at individual stages of movement are described.

关键词：

来源：评论

学校读者我要写书评

暂无评论

About features of management of mobile robots with stepping movers of a rope type in a water environment

引用

IOP Conference Series: Materials Science and Engineering 2020年第1期747卷

作者： E S Briskin V V Gulevsky I S Penshin N G Sharonov Department of Theoretical Mechanics Volgograd State Technical University 28 Lenin Avenue Volgograd 400005 Russia Center for Technology Components of Robotics and Mechatronics Innopolis University Innopolis Russia

The methods of moving robotic platforms having in their arsenal either an anchor-rope or an anchor-rope-tracked mover are analyzed. The algorithms of operation of caterpillar-anchor-cable movers of various designs and...

关键词：

来源：评论

学校读者我要写书评

暂无评论

Assymetry of coupling between the P3 and P4 electroencephalographic leads during the motions 3

Assymetry of coupling between the P3 and P4 electroencephalo...

引用

3rd School on Dynamics of Complex Networks and their Application in Intellectual robotics, DCNAIR 2019

作者： Khorev, Vladimir Zhuravlev, Maksim Borovkova, Ekaterina Ishbulatov, Yuri Gridnev, Vladimir Karavaev, Anatoly Center for Technologies in Robotics and Mechatronics Components Innopolis University Russia Department of Open Systems Physics Saratov State University Russia Department of Dynamic Modeling and Biomedical Engineering Saratov State University Saratov Russia Saratov State University Saratov Branch Institute of RadioEngineering and Electronics Russian Academy of Sciences Saratov State Medical University Named after V. I. Razumovsky Saratov Russia Department of Innovative Cardiological Information Technology Institute of Cardiological Research Saratov State Medical University Saratov Russia Saratov Branch Institute of RadioEngineering and Elecrronics Russian Academy of Sciences Russia

Based on the coupling analysis we analyze electroencephalograms (EEGs) acquired in untrained humans (operators) during real and imaginary movements, and show a difference between the related EEG signals and the record... 详细信息

ISBN: (纸本)9781728124704

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Target localization intervention and prognosis evaluation for an individual with mild cognitive impairment

Brain‐X

引用

Brain‐X 2023年第3期1卷

作者： Weiping Wang Haiyan Zhao Chang He Yuanbo Cui Zhen Wang Alexander Hramov Ping Luan Xiong Luo Jipeng Ouyang Kurths Jürgen School of Computer and Communication Engineering University of Science and Technology Beijing Beijing China Shunde Graduate School University of Science and Technology Beijing Foshan Guangdong China Beijing Key Laboratory of Knowledge Engineering for Materials Science Beijing China Contribution: Writing - review & editing Department of Neurology Peking University Third Hospital Beijing China Contribution: Resources Zhen Wang The Center for Optical Imagery Analysis and Learning and School of Mechanical Engineering Northwestern Polytechnical University Xi'an Shaanxi 710072 China. Contribution: Writing - original draft The 6th Research Institute of China Electronics Corporation Beijing China The Center for Optical Imagery Analysis and Learning and School of Mechanical Engineering Northwestern Polytechnical University Xi'an Shaanxi China Chang He School of Computer and Communication Engineering University of Science and Technology Beijing Beijing 100083 China. Contribution: Investigation Center for Technologies in Robotics and Mechatronics Components Innopolis University Innopolis Russia Saratov State Medical University Saratov Russia Contribution: Data curation Guangdong Second Provincial General Hospital & Health Science Center Shenzhen Guangdong China Department of Neurology Shunde Hospital Southern Medical University Foshan Guangdong China Institute of Physics Humboldt-University Berlin Germany Potsdam Institute for Climate Impact Research Potsdam Germany

Currently, no specific treatments are available for Alzheimer's disease (AD). Mild cognitive impairment (MCI), the preclinical stage of AD, has a high possibility of reversing symptoms through neural regulation. A state dynamics model for single brain regions was developed to simulate blood oxygen level-dependent signals in a patient with early mild cognitive impairment. Subsequently, the analysis of functional connections was used to comprehensively consider multiple complex network centralities to locate the intervention targets, and a multiple brain region collaborative control scheme was designed. Finally, the reliability and effectiveness of the intervention were verified at the brain region and subnetwork levels. This technique provides a basis for future clinical diagnosis and treatment of AD and MCI.

关键词： adaptive pinning control Alzheimer's disease BOLD signals computational modeling Sub_network

来源：评论

学校读者我要写书评

暂无评论

Motion control of self-driving vehicles on rough roads

引用

IOP Conference Series: Materials Science and Engineering 2019年第1期707卷

作者： I Shapovalov S Gafurov A Klimchik Center for technologies in Robotics and Mechatronics components Innopolis University 1 Universitetskaya Str. Innopolis Russia Author to whom any correspondence should be addressed

Control of self-driving vehicles is one of the-up-to-date tasks. Vehicles are non-linear dynamic systems with a large number of parameters. When it is supposed to move on a rough road with a lot of abrupt turns, significant unpredictable and unmeasurable disturbances emerge and the control quality degrades significantly. We implemented model predictive path integral (MPPI) control to deal with significant unmeasured disturbances. To approve efficiency of the proposed controller, we conducted simulation of complex car motion on a plane under the control of PID, and MPPI controllers. Performance of controllers is comparatively equal in stable modes, when reference position and velocity do not change. MPPI controllers outperform PID ones in unstable modes due to their ability to predict a vehicle behavior. Also, MPPI is the best choice for the rejection of significant external disturbances.

关键词：

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：