检索结果-内蒙古大学图书馆

IEEE intelligent Vehicles Symposium

作者： Yang Yi Li Hao Zhu Hao Shang Songtian Lyu Ningyi Song Wenjie School of Automation and State Key Laboratory of Complex System Intelligent Control and Decision Beijing Institute of Technology

ISBN: (纸本)9781509048052

Large-scale intersections stamped on maps have diverse visual features for detection, while small-scale urban intersections are hard to be identified especially when GPS signals are missing. In this paper, we propose a Hidden Markov Model (HMM) based small-scale intersection detection method utilizing monocular vision. We extract visual cues of road transformations and dynamic vehicles' tracks, and then design an Intersection Scan Model to obtain the potential traversable direction of the current road, which is the primary criterion of the intersection estimation. For better performances, we take the detections of consecutive frames into consideration and finally integrate them into HMM to estimate the probabilities of intersections. Results from KITTI datasets and real-world experiments have shown the functionality of the presented approach.

关键词： Hidden Markov models Roads Global Positioning System Vehicle dynamics Semantics Image segmentation Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Multi Constellation Fast Selection Method Based on Equivalent Distance Error

Multi Constellation Fast Selection Method Based on Equivalen...

引用

第37届中国控制会议

作者： Guangjun Wang Yutao Cheng Shaohui Yang School of Automatic China University of Geosciences Hubei Key Laboratory of Advance Control and Intelligent Automation for Complex Systems STATE GRID PUYANG ELECTRIC POWER SUPPLY COMPANY

A single satellite navigation system can get high accuracy in general environment, but when the ground satellite navigation receiver is in complex environment, single system navigation often results in poor location results due to the visible satellite less than four. If multiple constellation fusion navigation is used, the number of visible satellites can be increased, thus improving the positioning results. However, the use of all visible satellites in location calculation will bring a huge amount of calculation, which seriously affects the real-time performance of navigation and positioning. Therefore, a reasonable selection of star selection method is urgently needed in the integrated navigation system. Based on the two performance indexes of balanced geometric accuracy factor（GDOP） and star selection efficiency, fast star selection algorithm based on equivalent distance error is proposed in this paper. The experimental results show that the method can effectively improve the efficiency of multi constellation star selection of the premise of high precision.

关键词： Satellite navigation Multi-constellation fusion Satellite selection Geometric Dilution of Precision

来源：评论

学校读者我要写书评

暂无评论

Hexagon-Shaped Screw Recognition and Positioning System Based on Binocular Vision

Hexagon-Shaped Screw Recognition and Positioning System Base...

引用

第37届中国控制会议

作者： Fang Wang Xin Chen Chang Tan Jinbin Li Yaodong Zhang School of Automation China University of Geoscience Hubei key Laboratory of Advanced Control and Intelligent Automation for Complex Systems State Grid Hubei Electric Power Research Institute

Traditional artificial live work asks for a high standard with operator’s mental state and technical level in high-voltage and strong-magnetic environment,which not only reduces the efficiency of modern production and living but also causes potential threats to the safety of ***,developing robot live work has great significance for both academic research and industrial applications.A key problem of the live work for an industrial robot is recognition and positioning of the hexagonshaped screw in substation with high *** solve this problem,this article designs a hexagon-shaped screw recognition and positioning system based on binocular vision in transformer substation.A method for stereo matching including 3 steps is proposed:edge noise of the target is reduced by median filter at the beginning;then the target can be obtained through the image segmentation method of adjusting threshold;further moments are used to express the centers of hexagons in 2 images which work as stereo matching *** depth information can be obtained due to visual geometric relationships based on stereo model and camera calibration parameters based on camera *** experiment results show that the binocular system designed in this article can accurately identify the target with good stability,and the measurement error is controlled in 4%.

关键词： Binocular stereo vision Image segmentation Stereo matching Depth information

来源：评论

学校读者我要写书评

暂无评论

Privacy Preservation for Distributed Nonsmooth Constrained Optimization Based on Pseudo-Subgradient

Privacy Preservation for Distributed Nonsmooth Constrained O...

引用

第37届中国控制会议

作者： Xianlin Zeng Shu Liang Jie Chen Key Laboratory of Intelligent Control and Decision of Complex Systems School of Automation Beijing Institute of Technology Key Laboratory of Knowledge Automation for Industrial Processes of Ministry of Education School of Automation and Electrical Engineering University of Science and Technology Beijing Beijing Advanced Innovation Center for Intelligent Robots and Systems (Beijing Institute of Technology) Key Laboratory of Biomimetic Robots and Systems (Beijing Institute of Technology) Ministry of Education

In this paper, we investigate a privacy preservation design in the distributed nonsmooth convex optimization with set constraints. To solve the distributed optimization problem while preserving the privacy, we use pseudo-subgradients involved with（non-integrable） set-valued functions. Based on pseudo-subgradients, we propose distributed nonsmooth optimization algorithms with keeping subgradient information confidential. Then we prove the correctness and convergence of the distributed privacy preservation optimization algorithms to achieve the exact solution of the original optimization problem.

关键词： Distributed nonsmooth convex optimization privacy preservation set constraints pseudo-subgradients

来源：评论

学校读者我要写书评

暂无评论

A New Approach for Face Anti-Spoofing Using Handcrafted and Deep Network Features

A New Approach for Face Anti-Spoofing Using Handcrafted and ...

引用

IEEE International Conference on Service Operations and Logistics, and Informatics, SOLI

作者： Polash Kumar Das Bin Hu Chang Liu Kaixin Cui Prabhat Ranjan Gang Xiong School of Electronic and Information Engineering South China University of Technology Guangzhou China The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Science Beijing China College of Computer Science Sichuan University Chengdu China Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation Chinese Academy of Sciences Beijing China The Cloud Computing Center Chinese Academy of Science Dongguan China

In biometrics, face recognition methods are achieving momentum with recent progress in the computer vision(CV). Face recognition is widely used in the identification of an individual's identity. Unfortunately, in recent research work has revealed this face biometrics system is unprotected to spoofing attacks using by very low price instrument such as printed 2D photos attack, 3D masking attack and taking videos using smart devices (reply attack). Therefore, a Liveness Attack Detection (LAD) approach is needed to improve the high-quality security of face recognition system. Most of the earlier worked LAD methods for face anti-spoofing methods have highlight on using the handcrafted features, which are developed by expert knowledge of researcher. As example Gabor filter, Histogram of Oriented Gradients, local ternary pattern, and the Local Binary Pattern. Because of that, the extracted features consider limited factors of the problem, yielding a capture accuracy that is very low and changes with the point of presentation in attack face images. The deep learning method has developed in the computer vision research community, which is proven to be suitable for automatically training. In this article, we approach to mix or combine the handcrafted features and deep neural network features to design the discriminant face spoofing detection. The handcrafted features were based on LBP analysis. We examine the features information from the brightness and the chrominance channels using LBP descriptor. In deep features, we present an approach based on pre-trained convolutional neural network VGG-16 model using static features to recognize video and printed(2D) photo attacks. By attaching this two types of image features on our dataset and public databases, we get good results to identify real and attack images feature, called hybrid features, which has better discrimination ability to understand spoofing image feature.

关键词： Face Videos Feature extraction Databases Face recognition Password

来源：评论

学校读者我要写书评

暂无评论

An Analysis of Blockchain-based Bitcoin Mining Difficulty: Techniques and Principles

An Analysis of Blockchain-based Bitcoin Mining Difficulty: T...

引用

Chinese Automation Congress

作者： Xiaojing Zhang Rui Qin Yong Yuan Fei-Yue Wang The State Key Laboratory for Management and Control of Complex Systems Chinese Academy of Sciences Beijing China Beijing Engineering Research Center of Intelligent Systems and Technology Chinese Academy of Sciences Beijing China

Bitcoin is a decentralized peer-to-peer electronic cash system, and it realizes the circulation and distribution of cryptocurrency via miners contributing their computational power to solve a cryptographic puzzle. With more and more people participating in Bitcoin mining, the continuous growing of the computational power might greatly reduce the time for finding a new valid block. To keep the stability of the Bitcoin system, the difficulty of the Bitcoin network will be adjusted every 2016 blocks. This paper aims to study the principles of the difficulty adjustment of the whole Bitcoin blockchain network in Bitcoin mining. We first describe the computing process of the target and thus the difficulty of a block, and then study its influence factors and their effect on the difficulty. After that, we study the adjustment of the difficulty, and propose a framework for the adjustment of the difficulty that can be easily used in practice. Our work can help researchers better understand the principles of Bitcoin mining.

关键词： Bitcoin mining Blockchain Network difficulty Target Adjustment of difficulty

来源：评论

学校读者我要写书评

暂无评论

Multi Constellation Fast Selection Method Based on Equivalent Distance Error

Multi Constellation Fast Selection Method Based on Equivalen...

引用

Chinese control Conference

作者： Guangjun Wang Yutao Cheng Shaohui Yang School of Automatic China University of Geosciences Wuhan Hubei Key Laboratory of Advance Control and Intelligent Automation for Complex Systems State Grid Puyang Electric Power Supply Company

A single satellite navigation system can get high accuracy in general environment, but when the ground satellite navigation receiver is in complex environment, single system navigation often results in poor location results due to the visible satellite less than four. If multiple constellation fusion navigation is used, the number of visible satellites can be increased, thus improving the positioning results. However, the use of all visible satellites in location calculation will bring a huge amount of calculation, which seriously affects the real-time performance of navigation and positioning. Therefore, a reasonable selection of star selection method is urgently needed in the integrated navigation system. Based on the two performance indexes of balanced geometric accuracy factor (GDOP) and star selection efficiency, fast star selection algorithm based on equivalent distance error is proposed in this paper. The experimental results show that the method can effectively improve the efficiency of multi constellation star selection of the premise of high precision.

关键词： Satellites Satellite navigation systems Receivers Extraterrestrial measurements Measurement uncertainty Clocks Space vehicles

来源：评论

学校读者我要写书评

暂无评论

Hexagon-Shaped Screw Recognition and Positioning System Based on Binocular Vision

Hexagon-Shaped Screw Recognition and Positioning System Base...

引用

Chinese control Conference (CCC)

作者： Fang Wang Xin Chen Chang Tan Jinbin Li Yaodong Zhang Hubei key Laboratory of Advanced Control and Intelligent Automation for Complex Systems State Grid Hubei Electric Power Research Institute Wuhan P. R. China

Traditional artificial live work asks for a high standard with operator's mental state and technical level in high-voltage and strong-magnetic environment, which not only reduces the efficiency of modern production and living but also causes potential threats to the safety of operators. Therefore, developing robot live work has great significance for both academic research and industrial applications. A key problem of the live work for an industrial robot is recognition and positioning of the hexagon-shaped screw in substation with high accuracy. To solve this problem, this article designs a hexagon-shaped screw recognition and positioning system based on binocular vision in transformer substation. A method for stereo matching including 3 steps is proposed: edge noise of the target is reduced by median filter at the beginning; then the target can be obtained through the image segmentation method of adjusting threshold; further moments are used to express the centers of hexagons in 2 images which work as stereo matching points. Finally depth information can be obtained due to visual geometric relationships based on stereo model and camera calibration parameters based on camera model. The experiment results show that the binocular system designed in this article can accurately identify the target with good stability, and the measurement error is controlled in 4%.

关键词： Cameras Fasteners Calibration Image segmentation Mathematical model

来源：评论

学校读者我要写书评

暂无评论

Crowdsensing game with demand uncertainties: A deep reinforcement learning approach

arXiv

引用

arXiv 2018年

作者： Zhan, Yufeng Xia, Yuanqing Zhang, Jiang Li, Ting Wang, Yu School of Automation Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing Institute of Technology Beijing100081 China Lab Department of Computer Science University of North Carolina at Charlotte CharlotteNC28223 United States

Currently, explosive increase of smartphones with powerful built-in sensors such as GPS, accelerometers, gyroscopes and cameras has made the design of crowdsensing applications possible, which create a new interface between human beings and life environment. Until now, various mobile crowdsensing applications have been designed, where the crowdsourcers can employ mobile users (MUs) to complete the required sensing tasks. In this paper, emerging learning-based techniques are leveraged to address crowdsensing game with demand uncertainties and private information protection of MUs. Firstly, a novel economic model for mobile crowdsensing is designed, which takes MUs' resources constraints and demand uncertainties into consideration. Secondly, an incentive mechanism based on Stackelberg game is provided, where the sensing-platform (SP) is the leader and the MUs are the followers. Then, the existence and uniqueness of the Stackelberg Equilibrium (SE) is proven and the procedure for computing the SE is given. Furthermore, a dynamic incentive mechanism (DIM) based on deep reinforcement learning (DRL) approach is investigated without knowing the private information of the MUs. It enables the SP to learn the optimal pricing strategy directly from game experience without any prior knowledge about MUs' information. Finally, numerical simulations are implemented to evaluate the performance and theoretical properties of the proposed mechanism and approach. Copyright © 2018, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Efficient Deployment of Patrols to Catch Arsonists

Efficient Deployment of Patrols to Catch Arsonists

引用

Chinese Automation Congress (CAC)

作者： Jinpeng Han Fei-Yue Wang Yisheng Lv Fenghua Zhu Yilun Lin Xingyuan Dai Li Li School of Software Engineering Xian Jiaotong University Xian China The State Key Laboratory for Management and Control of Complex Systems Chinese Academy of Sciences Beijing Qingdao Academy of Intelligent Industries Qingdao Shandong The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Science Beijing China Department of Automation Tsinghua University Beijing China

Forest fires are serious disasters that endanger the safety and property of residents. To deal with the arson-caused forest fires, we use security game theory to generate optimal patrol strategy under limited patrolling resources. The existing security game algorithms focus on a single behavior model to prevent attacks, while our work is to incorporate the secondary damage caused by the attack behavior into the optimization object. For forest fires, the security game algorithm only expects to catch arsonists in the forest, which is unreasonable in our opinion. Our algorithm incorporates the spread of fires into patrolling path planning so that defenders avoid being swallowed by fire via capturing the spread of it.

关键词： Games Forestry Security Game theory Mathematical model Automation control systems

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：