检索结果-内蒙古大学图书馆

International Conference on Automation and Computing (ICAC)

作者： Zhenwei Gao Yongqiang Bai Key Laboratory of Complex System Intelligent Control and Decision Beijing Institute of Technology Beijing China

Fast single image dehazing has been a challenging problem in many fields, such as computer vision and real-time applications. The existing image dehazing algorithms cannot achieve a trade-off between the dehazing performance and the computational complexity. The proposed approach first applies the mean filter twice to estimate airlight, which include pixel-based dark channel and bright channel constraints. And then the relationship between channel values of the restored image and atmospheric light is qualitatively analyzed to give the optimum estimate of atmospheric light. Using the airlight and atmospheric light, we can easily restore the scene radiance via the atmospheric scattering model. Compared with others, the main advantage of the proposed approach is its high speed and significant visibility improvement even in the sky and white areas. This speed allows the enhanced haze image to be applied in real-time processing applications. A comparative study and quantitative evaluation are proposed with a few other state of the art algorithms which demonstrates that similar or better quality results are obtained.

关键词： Atmospheric modeling Image restoration Real-time systems Channel estimation Scattering Filtering Computational modeling

来源：评论

学校读者我要写书评

暂无评论

Decentralized control for Arbitrarily Interconnected systems over Lossy Network

引用

自动化学报 2010年第9期36卷 1321-1327页

作者： LI Hui School of Automation Beijing Institute of TechnologyBeijing 100081P.R.China Key Laboratory of Complex System Intelligent Control and Decision Ministry of EducationBeijing 100081P.R.China

This paper deals with the control of arbitrarily topological interconnected systems where information communicated between subsystems may be lost due to unreliable links. First, the stochastic variable that is responsible for the communication status of lossy network is regarded as a source of model uncertainty. The system is modeled in the framework of linear fractional transformation with a deterministic nominal system and a stochastic model uncertainty. Then, the robust control theory is employed for system analysis. The largest probability of communication failure, tolerated by the interconnected systems keeping mean square stable, can be obtained by solving a μ synthesis optimization problem. Decentralized state feedback controllers are designed to ensure that the whole system is mean square stable for a given communication failure rate, based on the technique of linear matrix inequalities. An illustrative example is presented finally to verify the effectiveness of the proposed model and method

关键词：拓扑子系统通信故障率随机变量

来源：评论

学校读者我要写书评

暂无评论

Large Receptive Field Boundary Matching Networks for Generating Better Proposals

Large Receptive Field Boundary Matching Networks for Generat...

引用

第40届中国控制会议

作者： Lei Xu Jiexi Liu Bo Chen Beijing Institute of Technology School of Automation Key Laboratory of Complex System Intelligent Control and Decision

Temporal Action Detection is a research hotspot in Video *** is necessary not only to give the specific moments of the beginning and end of each action instance in the video,but also to give the category of the action *** present,most of the methods in temporal action detection are divided into two steps:The video is divided into a series of video clips to determine whether each clip is an action instance,and the fragments that are not an action instance are deleted;Segments that may be action instances are then classified to get the final *** present,the difficulties in action detection research mainly include the following two points:1) The boundary is not *** from action recognition,action detection requires precise positioning,but an action in life is often not very *** is also the reason why the mean average precision(mAP) of action detection is low at present.2) The time span is *** life,an action often spans a very long *** movements such as waving can last for a few seconds,while long movements such as rock climbing or cycling can last for tens of minutes,which makes it extremely difficult for us to extract *** view of the above difficulties,this paper proposes a large receptive field boundary matching network(LRFBMN) model which takes advantage of the relationship between proposals to improve the accuracy of proposal *** model is mainly divided into two parts:1) Clipping feature map is processed by large kernel convolution,and then proposal feature is generated by ROI-pooling;2) The proposals are arranged in a certain order to form a fixed graph,and the information exchange between graph nodes is realized by using convolution with *** experiments,this model is 2.35% higher than baseline and 1.06% higher than state-of-the-art in THUMOS14 data set.

关键词： Temporal Action Detection Video Understanding Proposal Large Receptive Field

来源：评论

学校读者我要写书评

暂无评论

PI Tuning and Optimization for Speed control of PMSM Based on Multivariable Sliding-Mode Extremum Seeking

PI Tuning and Optimization for Speed Control of PMSM Based o...

引用

第34届中国控制与决策会议

作者： Fan Li Wei Shen Chuanyu Ge Key Laboratory of Complex System Intelligent Control and Decision School of AutomationBeijing Institute of Technology

ISBN: (纸本)9781665478977

The PI controller is the most basic and widely used for the permanent magnet synchronous motor speed *** cumbersome parameter adjustment process makes it difficult for the PI controller to balance convenience and *** this end,this paper presents a new PI tuning and optimization scheme based on multivariable sliding-mode extremum ***,by analyzing the frequency domain model of permanent magnet synchronous motor,the analytical calculation formulas of controller parameters and motor parameters are derived as the initial value of PI parameter ***,a multivariable sliding-mode extremum seeking optimizer is designed to optimize the control parameters by minimizing the cost function based on the feedback error *** feasibility of the above scheme is proved by theoretical derivation,and the simulation and experimental results also verify the feasibility and effectiveness of the proposed method.

关键词： permanent-magnet synchronous motor(PMSM) multivariable sliding mode extremum seeking(MSME) self-tuning parameter optimization

来源：评论

学校读者我要写书评

暂无评论

Object Tracking Algorithm of Adaptive Kernel-Bandwidth for Mean-Shift Based on Optical-flows

Object Tracking Algorithm of Adaptive Kernel-Bandwidth for M...

引用

第三十二届中国控制会议

作者： Qinlong He Junzheng Wang Jing Li Key Laboratory of Complex System Intelligent Control and Decision School of Automation Beijing Institute of Technology

ISBN: (纸本)9781479900305

To obtain and update the kernel-bandwidth,we present an adaptive bandwidth obtainment algorithm based on object contour extraction from optical-flow *** combination of modified mountain cluster approach and fast scanning window contour extractor guarantees the speed of this algorithm.A novel ellipse detection method based on a modified RANSAC is adopted to reduce the *** results demonstrate that the algorithm select the proper size of tracking kernel-bandwidth with minor extra computational overhead and keep up with the object robustly when the scale changed rapidly.

关键词： object tracking mean shift kernel bandwidth mountain cluster RANSAC

来源：评论

学校读者我要写书评

暂无评论

Data yard based system effectiveness evaluation and decision support method

引用

Guofang Keji Daxue Xuebao/Journal of National University of Defense Technology 2014年第1期36卷 124-130页

作者： Chen, Chen Wang, Yun School of Automation Beijing Institute of Technology Beijing 100081 China Key Laboratory of Complex System Intelligent Control and Decision Ministry of Education Beijing 100081 China

With the development of information technology, the increase of system information brings new problems to the military system effectiveness evaluation. Aiming at nonlinear, high dimension and strong coupling data of system effectiveness analysis, a data yard based system effectiveness evaluation and decision support method was proposed. Data recovery, subtraction, refinement and reconstruction operations were applied to the simulation data processing, then a data yard cube was built up to meet the multiple demands for system analysis of different levels and data dependency were reduced. Taking task-oriented networked fire control system for example, its system effectiveness evaluation, timeliness evaluation and indices analysis were carried out, and practicability and validity of the method were verified in three levels. Applying data mining technology to the simulation system effectiveness evaluation decision-making, makes it get more extensive application.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

A Map Matching Algorithm for Inertial Navigation systems Based on the Adaptive Projection Method

A Map Matching Algorithm for Inertial Navigation Systems Bas...

引用

International Symposium on Computational Intelligence and Design, ISCID

作者： Hao Luo Zhihong Deng Mengyin Fu Bo Wang National Key Laboratory of Intelligent Control and Decision of Complex System School of Automation Beijing China

ISBN: (纸本)9781479970063

In this paper, it studies the various elements of map-matching algorithm, in order to achieve better real-time and accuracy for vehicle navigation systems. This paper uses two-stage staggered mesh, combined with the second round screening domain. Using of vehicle location, direction, road geometric and topological relations with the angular rate of change, this paper proposes a new map matching algorithm, angle and distance segment dominated approach. The results show that the map-matching algorithm in this paper can achieve vehicle navigation and positioning functions accurately and quickly.

关键词： Roads Vehicles Navigation Accuracy Real-time systems Network topology Adaptive algorithms

来源：评论

学校读者我要写书评

暂无评论

An electro-hydraulic control system with energy recycling

An electro-hydraulic control system with energy recycling

引用

Chinese Automation Congress (CAC)

作者： Taoxinjun Tao Junzheng Wang Jiangbo Zhao Xiaojie Hu Key laboratory of Intelligent Control and Decision of Complex System Beijing Institute of Technology Beijing China

ISBN: (纸本)9781467371902

When traditional electro-hydraulic proportional valve or servo valve controlled systems are used to drive unbalanced external load, the hydraulic valve itself exists throttling losses. At the same time, the excess kinetic or potential energy of external load is consumed in the form of heat. In order to reduce energy loss and recycle external load energy, this paper puts forward a kind of electro-hydraulic control equipment which can recycle energy. It consists of directional valve, hydraulic motor, generator, power transformation device. In details, the directional valve is used to control the fluid direction of hydraulic actuator, hydraulic motor is connected to the fluid return channel of the directional valve. A generator is connected to hydraulic motor so that the back pressure of the actuator can be controlled by adjusting the torque applied on the hydraulic motor. In this way, the trajectory of the actuator is controlled. The mechanical energy applied on the hydraulic motor can be converted to electricity via the power conversion device, and then transmitted back to the grid. The simulation and experiment results prove that the proposed scheme is feasible.

关键词： Valves Torque Generators Actuators Recycling

来源：评论

学校读者我要写书评

暂无评论

ADFNet: A two-branch robotic grasping network based on attention mechanism

ADFNet: A two-branch robotic grasping network based on atten...

引用

第40届中国控制会议

作者： Pengwei Xie Nan Hao Bo Chen Beijing Institute of Technology School of Automation Key Laboratory of Complex System Intelligent Control and Decision

One of the challenges of RGB-D-based robotic grasping technology is how to make full use of these two complementary heterogeneous data sources while ensuring real-time performance. The existing robotic grasping methods mainly extract information from single-mode images or use a one-branch network to process RGB and depth images. These methods are insufficient in fully fusing the effective information of the two modes, which limits the anti-jamming performance. In this work,we propose Attention Dense Fusion Network（ADFNet）, a novel RGB-D based robotic grasping system that directly predicts the optimal grasping pose from RGB-D images. Our system uses a two-branch network with a heterogeneous framework that processes RGB and depth image information separately and retain the original structure of each data source. After applying dense fusion networks at different scales, the high-dimensional features in the RGB and depth branches are embedded and fused at the pixel level. Besides, we incorporate attention mechanisms to effectively suppress the independent background regions of the feature map and enhance the significant features, which improves the prediction accuracy. We conduct qualitative and quantitative experiments on the standard Cornell Grasp Dataset. The experimental results show that ADFNet can effectively improve the prediction accuracy to 98.9 %, which is better than existing methods while ensuing real-time performance.

关键词： robotic grasping RGB-D attention mechanism

来源：评论

学校读者我要写书评

暂无评论

A multi-objective decomposition-based stochastic particle swarm optimization algorithm and its application to optimal design for linear motor

引用

Kongzhi Lilun Yu Yingyong/control Theory and Applications 2013年第6期30卷 693-701页

作者： Wang, Guang-Hui Chen, Jie Cai, Tao Li, Peng School of Automation Beijing Institute of Technology Beijing 100081 China Key Laboratory of Complex System Intelligent Control and Decision Ministry of Education Beijing 100081 China

This article proposes a multi-objective decomposition stochastic particle swarm optimization (MDSPSO) algorithm. In MDSPSO, every particle has a weighted vector constantly. Then, an improved Tchebycheff decomposition method is applied to decompose the multi-objective problem into some single-objective problems. The reference position of every particle is uniformly generated in the zone with the center which is the geometrical center of its current position, the best previous reference position as well as the swarm best reference position. The radius of this zone is the distance from the center to its current position. Then the particle is updated to the new position according to the reference position and its current velocity. The comparisons with the decomposition-based multi-objective particle swarm optimizer (dMOPSO), a multiobjective evolutionary algorithm based on decomposition (MOEA/D), and nondominated sorting genetic algorithm II (NSGA-II) show that the solutions of MDSPSO can be dominated at least with the best diversity. To reduce the computational time by finite element analysis for optimizing the structure parameters of linear motor, artificial neural network is used as the model to evaluate the performance. Finally, MDSPSO is applied to optimize four objectives simultaneously. The practical result is shown that the optimized linear motor has an increased thrust, improved efficiency, reduced fluctuation and manufacturing cost.

关键词： Multiobjective optimization

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：