检索结果-内蒙古大学图书馆

26th IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Zhang, Zhong Wang, Chunheng Xiao, Baihua Zhou, Wen Liu, Shuang Shi, Cunzhao CASIA State Key Lab Management & Control Complex Syst Beijing Peoples R China

ISBN: (纸本)9780769549897

In this paper, we propose a novel method for cross-view action recognition via a continuous virtual path which connects the source view and the target view. Each point on this virtual path is a virtual view which is obtained by a linear transformation of the action descriptor. All the virtual views are concatenated into an infinite-dimensional feature to characterize continuous changes from the source to the target view. However, these infinite-dimensional features cannot be used directly. Thus, we propose a virtual view kernel to compute the value of similarity between two infinite-dimensional features, which can be readily used to construct any kernelized classifiers. In addition, there are a lot of unlabeled samples from the target view, which can be utilized to improve the performance of classifiers. Thus, we present a constraint strategy to explore the information contained in the unlabeled samples. The rationality behind the constraint is that any action video belongs to only one class. Our method is verified on the IXMAS dataset, and the experimental results demonstrate that our method achieves better performance than the state-of-the-art methods.

关键词： feature extraction image classification image motion analysis video signal processing

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Boundary control Design for a Class of Nonlinear Parabolic Distributed Parameter systems

引用

IEEE TRANSACTIONS ON FUZZY systems 2014年第3期22卷 642-652页

作者： Wu, Huai-Ning Wang, Jun-Wei Li, Han-Xiong Beijing Univ Aeronaut & Astronaut Beihang Univ Sch Automat Sci & Elect Engn Sci & Technol Aircraft Control Lab Beijing 100191 Peoples R China Univ Sci & Technol Beijing Sch Automat & Elect Engn Beijing Peoples R China Beijing Univ Aeronaut & Astronaut Beihang Univ Sch Automat Sci & Elect Engn Beijing 100191 Peoples R China City Univ Hong Kong Dept Syst Engn & Engn Management Hong Kong Hong Kong Peoples R China Cent South Univ State Key Lab High Performance Complex Mfg Changsha Hunan Peoples R China

This paper deals with the problem of fuzzy boundary control design for a class of nonlinear distributed parameter systems which are described by semilinear parabolic partial differential equations (PDEs). Both distributed measurement form and collocated boundary measurement form are considered. A Takagi-Sugeno (T-S) fuzzy PDE model is first applied to accurately represent the semilinear parabolic PDE system. Based on the T-S fuzzy PDE model, two types of fuzzy boundary controllers, which are easily implemented since only boundary actuators are used, are proposed to ensure the exponential stability of the resulting closed-loop system. Sufficient conditions of exponential stabilization are established by employing the Lyapunov direct method and the vector-valued Wirtinger's inequality and presented in terms of standard linear matrix inequalities. Finally, the advantages and effectiveness of the proposed control methodology are demonstrated by the simulation results of two examples.

关键词： Boundary control collocated boundary measurement distributed measurement distributed parameter systems Takagi-Sugeno (T-S) fuzzy model

来源：评论

学校读者我要写书评

暂无评论

Scene Text Recognition using Part-based Tree-structured Character Detection

Scene Text Recognition using Part-based Tree-structured Char...

引用

26th IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Shi, Cunzhao Wang, Chunheng Xiao, Baihua Zhang, Yang Gao, Song Zhang, Zhong CASIA State Key Lab Management & Control Complex Syst Beijing Peoples R China

ISBN: (纸本)9780769549897

Scene text recognition has inspired great interests from the computer vision community in recent years. In this paper, we propose a novel scene text recognition method using part-based tree-structured character detection. Different from conventional multi-scale sliding window character detection strategy, which does not make use of the character-specific structure information, we use part-based tree-structure to model each type of character so as to detect and recognize the characters at the same time. While for word recognition, we build a Conditional Random Field model on the potential character locations to incorporate the detection scores, spatial constraints and linguistic knowledge into one framework. The final word recognition result is obtained by minimizing the cost function defined on the random field. Experimental results on a range of challenging public datasets (ICDAR 2003, ICDAR 2011, SVT) demonstrate that the proposed method outperforms state-of-the-art methods significantly both for character detection and word recognition.

关键词： character recognition computer vision random processes trees (mathematics)

来源：评论

学校读者我要写书评

暂无评论

Unmanned Aerial Vehicles (UAV) Heading Optimal Tracking control Using Online Kernel-based HDP Algorithm

Unmanned Aerial Vehicles (UAV) Heading Optimal Tracking Cont...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Tan, Fuxiao Liu, Derong Guan, Xinping Luo, Bin Fuyang Teachers Coll Sch Comp & Informat Fuyang Anhui Peoples R China Anhui Univ Minist Educ Key Lab Intelligent Comp & Signal Proc Hefei 230039 Anhui Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing Peoples R China Shanghai Jiao Tong Univ Sch Elect Informat & Elect Engn Shanghai 200030 Peoples R China Anhui Univ Sch Comp Sci & Technol Hefei 230039 Anhui Peoples R China

ISBN: (纸本)9781479914845

UAV can work in places that are dangerous, or not easy to reach for humans. However, due to active control and operating difficulties, it is still a challenge to develop fully autonomous flight in complex environments. This paper applies a novel heuristic dynamic programming for the UAV heading optimal tracking controller design, using kernel-based heuristic dynamic programming (KHDP). Kernel-based HDP is developed by integrating kernel methods and approximately linear dependence (ALD) analysis with the critic learning of HDP algorithm. Compared with conventional HDP where neural networks are widely used and their features were manually designed, the proposed algorithm can obtain better generalization capability and learning efficiency through applying the sparse kernel machine into the critic learning process of HDP algorithm. Simulation and experimental results of UAV heading optimal tracking control problems demonstrate the effectiveness of the proposed kernel-based HDP algorithm.

关键词： Dynamic programming

来源：评论

学校读者我要写书评

暂无评论

Social manufacture cloud mode in high-end apparel, footwear and hats

Social manufacture cloud mode in high-end apparel, footwear ...

引用

World Congress on Intelligent control and Automation (WCICA)

作者： Xiuqing Shang Baoli Su Xiwei Liu Gang Xiong Zengbo You The State Key Laboratory of Management and Control for Complex Systems Chinese Academy of Sciences Beijing China Dongguan Research Institute of CASIA Chinese Academy of Sciences Cloud Computing Center Dongguan Guangdong Province China Beijing Engineering Research Center of Intelligent Systems and Technology

This paper expounds the high-end apparel footwear and hats manufacture industry society mode of cloud services, achieve consumers actively participate in the high-end apparel, footwear and hats industry of mass customization services. Through social production theory and the combination of cloud computing services, use many kinds of 3D technology, new process technology of cooperative management, e-commerce, logistics and wisdom dynamic value chain analysis and so on the many kinds of technologies, constructed with size and cost of mass production, customization of new clothing, footwear and hats business model, and implements all participate in the design, all involved in manufacture, and everyone involved for “a new type of manufacture and service mode, will effectively drive the transformation and upgrading of industries, and bring new economic growth.

关键词： Business Collaboration Clothing Crowdsourcing Three-dimensional displays Computational modeling

来源：评论

学校读者我要写书评

暂无评论

Optimal Tracking control for a Class of Continuous Time complex-valued systems Based on Adaptive Dynamic Programming Algorithm

Optimal Tracking Control for a Class of Continuous Time Comp...

引用

第三十三届中国控制会议

作者： Ruizhuo Song Frank L.Lewis Qinglai Wei Wendong Xiao School of Automation and Electrical Engineering University of Science and Technology Beijing University of Texas at Arlington Research Institute University of Texas at Arlington State Key Laboratory of Synthetical Process Automation Northeastern University The State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of Sciences

ISBN: (纸本)9781479947249

Based on the adaptive dynamic programming(ADP) algorithm,a new optimal tracking control method is proposed for a class of complex-valued nonlinear systems in this *** tracking error is rst de ned,and then the performance index function which is about the tracking error is *** transformation,the complex-valued tracking error system is mapped into *** optimal control method for the tracking error system is *** two neural networks are used to be as the critic network and action network,*** is proven that the closed-loop system is uniformly ultimately bounded based on Lyapunov ***,the simulation study is given to show the effectiveness of the proposed optimal tracking control method for complex-valued nonlinear system.

关键词： Adaptive dynamic programming,optimal control,neural network,complex-valued

来源：评论

学校读者我要写书评

暂无评论

Tracking control of discrete-time affine nonlinear systems based on kernel-HDP algorithm

Tracking control of discrete-time affine nonlinear systems b...

引用

World Congress on Intelligent control and Automation (WCICA)

作者： Fuxiao Tan Derong Liu Xinping Guan Fuyang Teachers College Anhui University Hefei Anhui China State Key Laboratory of Management and Control for Complex Systems Chinese Academy of Sciences School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai China

In the past decade, adaptive dynamic programming (ADP) has been widely used to realize online learning tracking control of dynamical systems, where neural networks with manually designed features are commonly used. In order to improve the generalization capability and learning efficiency of ADP, this paper presents a novel framework of ADP with sparse kernel machines by integrating kernel methods and approximately linear dependence (ALD) analysis into the critic module of ADP for the optimal tracking controller design. An ADP algorithm based on sparse kernel learning and heuristic dynamic programming (HDP) is proposed, that is, kernel HDP (KHDP). Based on KHDP, an experiment is established. By simulation, the effectiveness of proposed algorithm is demonstrated.

关键词： Kernel Vectors Dictionaries Equations Approximation algorithms Mathematical model Heuristic algorithms

来源：评论

学校读者我要写书评

暂无评论

Event-Triggered Reinforcement Learning Approach for Unknown Nonlinear Continuous-Time System

Event-Triggered Reinforcement Learning Approach for Unknown ...

引用

International Joint Conference on Neural Networks

作者： Xiangnan Zhong Zhen Ni Haibo He Xin Xu Dongbin Zhao Department of Electrical Computer and Biomedical Engineering University of Rhode Island Kingston USA College of Mechatronics and Automation National University of Defense Technology Changsha China State Key Lab of Management and Control for Complex Systems Chinese Academy of Sciences Beijing P. R. China

This paper provides an adaptive event-triggered method using adaptive dynamic programming (ADP) for the nonlinear continuous-time system. Comparing to the traditional method with fixed sampling period, the event-triggered method samples the state only when an event is triggered and therefore the computational cost is reduced. We demonstrate the theoretical analysis on the stability of the event-triggered method, and integrate it with the ADP approach. The system dynamics are assumed unknown. The corresponding ADP algorithm is given and the neural network techniques are applied to implement this method. The simulation results verify the theoretical analysis and justify the efficiency of the proposed event-triggered technique using the ADP approach.

关键词： Equations Neural networks Stability analysis Performance analysis Approximation algorithms Approximation methods Heuristic algorithms

来源：评论

学校读者我要写书评

暂无评论

A Robust Road Segmentation Method Based on Graph Cut with Learnable Neighboring Link Weights 17

A Robust Road Segmentation Method Based on Graph Cut with Le...

引用

IEEE 17th International Conference on Intelligent Transportation systems (ITSC)

作者： Yuan, Jun Tang, Shuming Wang, Fei Zhang, Hong Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Chinese Acad Sci High Tech Innovat Engn Ctr Inst Automat Beijing 100190 Peoples R China Xi An Jiao Tong Univ Inst Artificial Intelligence & Robot Xian 710049 Peoples R China Minzu Univ China Sch Informat Engn Beijing 100081 Peoples R China

ISBN: (纸本)9781479960781

Road region detection is a crucial functionality for road following in advanced driver assistance systems (ADAS). To address the problem of environment interference in road segmentation through a monocular vision approach, a novel graph-cut based method is proposed in this paper. The novelty of this proposal is that weights of neighboring links (n-links) in a s-t graph are estimated by Multilayer Perceptrons (MLPs) rather than calculating by the neighboring contrast simply in previous graph-cut based methods. Estimating n-link weights by MLPs reinforces the ability of graph-cut based road segmentation algorithms to tolerate the complex and changeable appearance of road surfaces. Additionally, the Gentle AdaBoost algorithm is integrated into the graph-cut framework to estimate the terminal link (t-link) weights in the s-t graph. Experiments are conducted to show the robustness and efficiency of the proposed method.

关键词： Advanced driver assistance systems

来源：评论

学校读者我要写书评

暂无评论

Workflow performance analysis and simulation based on multidimensional workflow net

引用

COMPUTERS IN INDUSTRY 2014年第2期65卷 333-344页

作者： Liu Sheng Fan Yushun Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Tsinghua Univ Dept Automat Beijing 100084 Peoples R China Chinese Acad Sci Cloud Comp Ctr Dongguan 523808 Peoples R China

Workflow model performance analysis plays an important role in the research of workflow techniques and efficient implementation of workflow management. Instances dwelling times (IDT) which consist of waiting times and handle times in a workflow model is a key performance analysis goal. In a workflow model the instances which act as customers and the resources which act as servers form a queuing network. Multidimensional workflow net (MWF-net) includes multiple timing workflow nets (TWF-nets) and the organization and resource information. This paper uses queuing theory and MWF-net to discuss mean value and probability distribution density function (PDDF) of IDT. It is assumed that the instances arrive with exponentially distributed inter-arrival times and the resources handle instances within exponentially distributed times or within constant times. First of all, the mean value and PDDF of IDT in each activity is calculated. Then the mean value and PDDF of IDT in each control structure of a workflow model is computed. According to the above results a method is proposed for computing the mean value and PDDF of IDT in a workflow model. Finally an example is used to show that the proposed method can be effectively utilized in practice. (C) 2013 Elsevier B.V. All rights reserved.

关键词： MWF-net Performance analysis Dwelling time Probability density

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：