检索结果-内蒙古大学图书馆

Chinese control and Decision Conference, CCDC

作者： Qiaobing Yao Hualong Yu Wankou Yang Changyin Sun Key Lab of Measurement and Control of Complex Systems of Engineering Southeast University Nanjing China School of Autmation Southeast University Nanjing Jiangsu CN Key Laboratory of Child Development and Learning Science of Ministry of Education Southeast University Nanjing China

This paper presents an imaging method for 360-degree panoramic view based on four wide angle cameras. In order to complete the image mosaic, all the parameters such as focal length, principal point and distortion coefficients, etc are calibrated by our proposed calibration toolbox. Then, our approach does not adopt the scheme which stitching all the images to the surrounding view after distortion correction. The proposed method directly calculates the mapping relationship between the wide-angle lens images and cylindrical projection images to generate lookup tables which can greatly simplifies the computation and reduces the loss of information in each image. Finally, panoramic image is composed by image registration and image fusion. Experimental results show that this method is valid.

关键词： Machine vision Mobile robots

来源：评论

学校读者我要写书评

暂无评论

Road detection via unsupervised feature learning

Road detection via unsupervised feature learning

引用

International Conference on Image and Vision Computing New Zealand, IVCNZ

作者： Siyu Xia Junkang Zhang Kaiyue Lu A. K. Qin Key Laboratory of Measurement and Control of Complex Systems of Engineering Southeast University Nanjing China College of Engineering and Computer Science Australian National University Canberra ACT Australia School of Computer Science and Information Technology RMIT University Melbourne Victoria Australia

ISBN: (纸本)9781509003587

Computer vision based road detection is an indispensable and challenging task in many real-world applications such as obstacle detection in autonomous driving. Low-level image features (e.g., color and texture) and pre-trained models are commonly used for this task. In this paper, we propose a simple yet effective approach to detect roads from a single image, which avoids the supervised model training that typically relies on a considerable number of labeled images. The key idea is to leverage unsupervised feature learning to obtain good road representations. Specifically, we first represent an input road image as a set of image patches. The K-means clustering algorithm is then applied to these image patches (after pre-processing) to generate K cluster centroids. Thus obtained centroids will be used together with a nonlinear mapping function and a bag-of-words projection to derive the image's feature representation in pixel and region levels respectively. All pixels (of the input image) using the former mapping will be clustered by Density Peaks algorithm into several regions, and the regions represented by the latter feature will be grouped by a graph cut method into two classes: road and non-road. Experimental results on several complicated road images demonstrate the effectiveness of our proposed method.

关键词： Roads Feature extraction Training Image color analysis Clustering algorithms Testing Image segmentation

来源：评论

学校读者我要写书评

暂无评论

A Multi-dimensional Taylor Network (MTN)-Based Approach for Nonlinear Stochastic systems Tracking control

A Multi-dimensional Taylor Network (MTN)-Based Approach for ...

引用

International Conference on control, Automation and systems

作者： Yu-Qun Han Hong-Sen Yan School of Automation Southeast University Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education

ISBN: (纸本)9781479999767

The problem of tracking control for stochastic nonlinear systems is investigated in this paper. Because of the randomness and nonlinearity of stochastic nonlinear systems, the existing methods are sometimes difficult to achieve the desired tracking performance. In this paper, a new network controller (multi-dimensional Taylor network) is proposed, which only relies on the output of system. Firstly we give the structure of multi-dimensional Taylor network (MTN), and then prove the MTN has a good approximation performance. Secondly, Design a MTN control strategy relying on the system output, which will guarantee the tracking of system output to desired output. An example is given to illustrate the effectiveness of the proposed design approach.

关键词： Multi-dimensional Taylor network Stochastic nonlinear systems Stochastic stability Tracking control

来源：评论

学校读者我要写书评

暂无评论

Optimal Tracking control of MISO Nonlinear systems Based on Multi-dimensional Taylor Network Only by Output Feedback

Optimal Tracking Control of MISO Nonlinear Systems Based on ...

引用

International Conference on control, Automation and systems

作者： Qi-Ming Sun Hong-Sen Yan School of Automation Southeast University Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education

ISBN: (纸本)9781479999767

The control input item is added to constitute the nonlinear dynamic model, on the basis of the original multi-dimensional Taylor network in this paper. And this nonlinear dynamic model is used to optimally control MISO nonlinear system only by output feedback without the disturbance estimation of the system or needing the state observer. The back-propagation algorithm is used to train the parameters of the multi-dimensional network with the control input item. Through the simulation, it is demonstrated the multi-dimensional Taylor network used as the optimal MISO nonlinear system tracking controller is effective.

关键词： Nonlinear systems Multi-dimensional Taylor Network Optimal Track control Parameter Learning

来源：评论

学校读者我要写书评

暂无评论

The Design of Robust MIMO Neural Network Disturbance Observer for Multi-variable System 33

The Design of Robust MIMO Neural Network Disturbance Observe...

引用

第三十三届中国控制会议

作者： LI Juan LI Shihua LI Shengquan School of Automation Southeast UniversityKey Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education School of Hydraulic Energy and Power Engineering Yangzhou University

ISBN: (纸本)9781479947249

Multi-variable systems widely exist in the practical engineering control systems whose performances are always severely interrupted by strong disturbances including unmodeled dynamics, parameter variations, couplings and external disturbances. Disturbance observer(DOB) is known as an effective technique to estimate disturbances and has been extensively applied for feed-forward compensation design in the presence of disturbances. Yet many disturbance observer techniques in previous literature are just used for single-input-single-output(SISO) systems or the DOBs can be applied in the multi-variable systems, but the DOBs are still SISO DOBs. A decoupled robust multi-input-multi-output neural network disturbance observer(MNNDOB) is designed for the multi-input-multi-output(MIMO) systems. Simulation results on the mixing tank show that the proposed method has better disturbance estimation performance when there are severe model mismatches compared with the MIMO linear disturbance observer.

关键词： Multi-variable system,Model mismatches,MIMO neural network disturbance observer,Disturbance estimation

来源：评论

学校读者我要写书评

暂无评论

Decentralized control for power systems components based-on nonlinear differential-algebraic equations subsystem model

Communications in Computer and Information Science

引用

Communications in Computer and Information Science 2014年 462卷 397-406页

作者： Zang, Qiang Zhou, Ying Mei, Ping Zheng, Baichao Zhang, Kaifeng School of Information and Control Engineering Nanjing University of Information Science & Technology Nanjing210044 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing210096 China College of Automation Nanjing University of Posts and Telecommunications Nanjing210003 China

ISBN: (纸本)9783662452608

Components of power systems essentially belong to a special class of nonlinear differential-algebraic equations subsystem, whose index is one and interconnection is locally measurable. In this paper, the decentralized control problem is discussed using inverse systems method for such class of power systems components. Firstly, the definition of α -order integral right inverse system is presented. Secondly, a recursive algorithm is proposed to judge whether the controlled component is invertible. Then a physically feasible α -order integral right inverse system is constructed with which the controlled component is made linearization and decoupled, so that linear control theory and methods can be applied. Finally, a decentralized excitation controller is designed for one synchronous generator within multi-machine power systems based on the proposed method in this *** simulation results demonstrate the effectiveness of the proposed control scheme. © Springer-Verlag Berlin Heidelberg 2014.

关键词： Decentralized control

来源：评论

学校读者我要写书评

暂无评论

Global decentralized stabilization for a class of large-scale feedforward nonlinear systems

Global decentralized stabilization for a class of large-scal...

引用

American control Conference

作者： Qixun Lan Chuanlin Zhang Shihua Li Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing 210096 P. R. China College of Automation Engineering Shanghai University of Electric Power Shanghai 200090 P.R. China School of Automation Southeast University Nanjing 210096 P. R. China

ISBN: (纸本)9781479917730

This paper considers the problem of global decentralized stabilization for a class of large-scale feedforward nonlinear systems. First, by using generalized homogeneous systems theory, a local linear decentralized control law is recursively constructed. Second, a series of nested saturation functions are integrated with the proposed local linear control law to render the whole closed-loop large-scale system global asymptotical stability. Due to the flexibility of the generalized homogeneous systems theory, the proposed approach not only weakens the existing restrictions imposed on the interconnected nonlinearities, but also can be applied to more general classes of large-scale feedforward nonlinear systems. Numerical example shows that the effectiveness of the proposed control scheme.

关键词： Decentralized control Feedforward neural networks Nonlinear systems Closed loop systems Lyapunov methods Asymptotic stability Feedforward systems

来源：评论

学校读者我要写书评

暂无评论

Mars Entry Trajectory Tracking Via Constrained Multi-Model Predictive control 33

Mars Entry Trajectory Tracking Via Constrained Multi-Model P...

引用

第三十三届中国控制会议

作者： WU Chao LI Shihua YANG Jun GUO Lei School of Automation Southeast University & Key Laboratory of Measurement and Control of Complex Systems of EngineeringMinistry of Education School of Automation Science and Electrical Engineering Beihang University & Institute of Instrument Science and Opto-Electronics Engineering

ISBN: (纸本)9781479947249

Tracking law designed for future Mars entry missions is investigated in this article. For precision landing, the nonlinear entry dynamics, complex uncertainties and input saturation constraints are unavoidable problems. Facing these challenges, the Mars entry trajectory tracking scheme via constrained multi-model predictive control(CMPC) is employed. The CMPC is made up of some constrained predictive control(CPC) in different time domain during the Mars entry mission. Each constrained predictive controller consists of a linearized prediction model(obtained by linearizing at different operating point), feedback correction for active model mismatch rejection caused by the complex uncertainties, and constrained rolling optimization for a smooth control input under a saturation constraint. Monte Carlo simulations demonstrate the effectiveness and excellence of the proposed method under the saturation constraint of input and uncertainties of initial state and aerodynamic parameters such as atmospheric density, ballistic coefficient and lift-to-drag ratio.

关键词： Mars Entry,Trajectory Tracking,Constrained Multi-Model Predictive control,Monte Carlo Simulation

来源：评论

学校读者我要写书评

暂无评论

Adaptive fuzzy control of output-constrained switched nonlinear systems

引用

ICIC Express Letters 2015年第12期9卷 3355-3362页

作者： Niu, Ben Liu, Yanli Shen, Mouquan School of Control Science and Engineering Dalian University of Technology No. 2 Linggong Road Ganjingzi District Dalian China College of Mathematics and Physics Bohai University No. 19 Keji Road New Songshan District Jinzhou China Automation Research Institute Bohai University No. 19 Keji Road New Songshan District Jinzhou China College of Electrical Engineering and Control Science Nanjing Technology University Nanjing China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing China

In this paper, the problem of adaptive fuzzy tracking control is considered of uncertain switched nonlinear systems with an output constraint. First, a barrier Lyapunov function (BLF) is employed to deal with the output constraint. Then fuzzy logic systems are used to approximate the unknown nonlinearities and backstepping technique is employed to construct an adaptive fuzzy controller. The designed controller guarantees all the closed-loop signals remain bounded while the system output converges to a small neighborhood of the desired reference signal without violating the constraint. An example is given to demonstrate the validity of the developed result. © 2015 ICIC International.

关键词： Lyapunov functions

来源：评论

学校读者我要写书评

暂无评论

High-level spatial modeling in convolutional neural network with application to pedestrian detection

High-level spatial modeling in convolutional neural network ...

引用

Canadian Conference on Electrical and Computer engineering (CCECE)

作者： Feng Liu Yongzhen Huang Wankou Yang Changyin Sun School of Automation. Southeast University Nanjing China Key Lab of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing China National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing China Key Lab of Child Development and Learning Science of Ministry of Education. Southeast University Nanjing China

ISBN: (纸本)9781479958306

Convolutional neural network (CNN) has achieved great success in many vision tasks. A key to this success is its ability to powerful automatically learns both high-level and low-level features. In general, low-level features have a small size of receptive fields and appear multiple times in different locations of objects, while high-level semantic features have a relatively large size of receptive fields and only appear once in a specific location of objects. However, traditional CNN treats these two kinds of features in the same manner, i.e., learning them by the convolution operation, which can be approximately considered as cumulating the probabilities that a feature appears in different locations. This strategy is reasonable for low-level features but not for high-level semantic ones, especially in the case of pedestrian detection, where a local feature can be shared by different locations but a semantic part, e.g., a head, only appears once for a human. To jointly model the spatial structure and appearance of high-level semantic features, we propose a new module to learn spatially weighted max pooling in CNN. The proposed method is evaluated on several pedestrian detection databases and the experimental results show that it achieves much better performance than traditional CNN.

关键词： Convolution Semantics Kernel Deformable models Computational modeling Feature extraction Training

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：