检索结果-内蒙古大学图书馆

2019 IEEE International Conference on Service Operations and Logistics, and Informatics, SOLI 2019

作者： Das, Polash Kumar Hu, Bin Liu, Chang Cui, Kaixin Ranjan, Prabhat Xiong, Gang School of Electronic and Information Engineering South China University of Technology Guangzhou China 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 Cloud Computing Center Chinese Academy of Science Dongguan China

ISBN: (纸本)9781728128535

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. © 2019 IEEE.

关键词： Local binary pattern

来源：评论

学校读者我要写书评

暂无评论

Robust Trajectory Tracking of Delta Parallel Robot Using Sliding Mode control

Robust Trajectory Tracking of Delta Parallel Robot Using Sli...

引用

IEEE Symposium Series on Computational Intelligence (SSCI)

作者： Tingting Su Xu Liang Guangping He Quanliang Zhao Lei Zhao North China University of Technology Beijing China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China

ISBN: (数字)9781728124858

ISBN: (纸本)9781728124865

For purpose of realizing robust trajectory tracking of parallel Delta robot with uncertain model parameters, a sliding mode control approach based on Delta robot dynamics is proposed. Once the reference trajectory is given, we can obtain the sliding mode controller, so that Delta parallel robot can move along the reference trajectory. Meanwhile, the disturbance and uncertainty of robot system are considered in the proposed method, which is beneficial to improve the reliability of controller and practicability of robot. The system stability is proved by Lyapunov method. Simulation experiment results demonstrate that the robust trajectory tracking of parallel Delta robot can be realized by the proposed method, and the designed controller is simple, robust and reliable.

关键词： Parallel robots Trajectory Trajectory tracking Robot kinematics Mathematical model

来源：评论

学校读者我要写书评

暂无评论

Lane change decision-making through deep reinforcement learning with rule-based constraints

arXiv

引用

arXiv 2019年

作者： Wang, Junjie Zhang, Qichao Zhao, Dongbin Chen, Yaran State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China

Autonomous driving decision-making is a great challenge due to the complexity and uncertainty of the traffic environment. Combined with the rule-based constraints, a Deep Q-Network (DQN) based method is applied for autonomous driving lane change decision-making task in this study. Through the combination of high-level lateral decision-making and lowlevel rule-based trajectory modification, a safe and efficient lane change behavior can be achieved. With the setting of our state representation and reward function, the trained agent is able to take appropriate actions in a real-world-like simulator. The generated policy is evaluated on the simulator for 10 times, and the results demonstrate that the proposed rule-based DQN method outperforms the rule-based approach and the DQN method. Copyright © 2019, The Authors. All rights reserved.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Object Reconstruction with Deep Learning: A Survey

Object Reconstruction with Deep Learning: A Survey

引用

IEEE International Conference on Cyber Technology in automation, control, and Intelligent systems

作者： Zishu Gao En Li Guodong Yang Zhe Wang Yunong Tian Zize Liang Rui Guo Shengchuan Li The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences and The University of Chinese Academy of Sciences Beijing China The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China State Grid Shandong Electric Power Company Jinan China State Grid Liaoning Electric Power Company Limited Shenyang China

ISBN: (数字)9781728107707

ISBN: (纸本)9781728107714

Object reconstruction is one of the most crucial branches of computer vision. With the development of deep learning, many tasks have achieved remarkable improvements in computer vision. 3D reconstruction with deep learning also has attracted much attention in recent years. Deep learning methods based on CNN-based and GAN-based architectures have been adopted for 3D object prediction. In addition, researchers utilize different inputs such as RGB and depth images to achieve prediction based on different problem. In this paper, we provide a detailed overview of recent advances in 3D object reconstruction. The reviewed approaches are categorized into three groups depending on the input modality: RGB-based, depth-based and other-input-based. Particularly, we introduce the various methods and indirectly classify the shape representation. As a survey, we discuss the strong and weak points of exciting approaches.

关键词： Three-dimensional displays Image reconstruction Shape Machine learning Generators Two dimensional displays automation

来源：评论

学校读者我要写书评

暂无评论

Research on fingerprint triangle region recognition Based on Convolutional Neural Networks

Research on fingerprint triangle region recognition Based on...

引用

作者： Ai Le Zhizhong Zhang Institute of Criminal Science and Technology People's Public Security University of China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences

In today's society, the growing instability has made identification technology a hot issue. Most traditional methods are based on a series of hand-defined preprocesses such as binarization. However, these preprocesses require strong prior knowledge. And that will lead to dropped or false extractions of minutiae. In this paper, a fingerprint triangle region recognition approach based on deep convolutional neural networks is proposed, which directly extract minutiae on raw fingerprint images without any preprocess since we tactfully take the advantage of the strong representative capacity of deep convolutional neural networks(including JudgeNet and LocateNet). Results show that our approach performs better in accuracy and robustness.

关键词： Neural network minutiae fingerprint image convolutional layer

来源：评论

学校读者我要写书评

暂无评论

Faster R-CNN Based Indoor Flame Detection for Firefighting Robot

Faster R-CNN Based Indoor Flame Detection for Firefighting R...

引用

IEEE Symposium Series on Computational Intelligence (SSCI)

作者： Jia Guo Zengguang Hou Xiaoliang Xie Shuncai Yao Qiaoli Wang Xuechen Jin School of Electrical and Control Engineering North University of China Taiyuan China The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China

ISBN: (数字)9781728124858

ISBN: (纸本)9781728124865

Firefighters are primarily tasked to handle fire incidents, but they are often exposed to high risks when extinguishing fire. Firefighting robots are actively being researched to reduce fire fighters injuries and deaths as well as increase their effectiveness on performing tasks. However, the major concern is how to make the flame detection methods to satisfy the high precision requirement of firefighting robot. Therefore, the flame detection of firefighting robot has become a hot topic in this area. In this paper, a Faster R-CNN model is proposed to detect flame in noisy images of fire ground. Firstly, the region generation network is used to extract the candidate flame regions. Secondly, the candidate flame regions are convoluted and pooled to extract the flame characteristics. Thirdly, the output features of Region Proposal Network (RPN) are fed into two fully connected layers: a box-regression layer which recognizes the locations of objects and a box-classification layer which classifies the objects. The dataset used in the experiment was obtained by video capture. The network is pre-trained based on Google platform Tensorflow, and the obtained precision and frame rate of the proposed method are up to 99.8% and 1.4 FPS, respectively. The experimental results demonstrate that the method equipped merits such as automatically extract the flame characteristics, effectively improve the precision of flame detection, and has excellent generalization ability and robustness.

关键词： Service robots Feature extraction Convolutional neural networks Image classification Regression analysis Object detection Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Multi-Objective Neural Architecture Search for Light-Weight Model

Multi-Objective Neural Architecture Search for Light-Weight ...

引用

Chinese automation Congress (CAC)

作者： Nannan Li Yaran Chen Zixiang Ding Dongbin Zhao Zhonghua Pang Ruisheng Qin State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Key Laboratory of Fieldbus Technology and Automation of Beijing North China University of Technology Beijing China

Neural architecture search (NAS) has achieved superior performance in visual tasks by automatically designing an effective neural network architecture. In recent years, deep neural networks are increasingly applied to resource-constrained devices. As a result, in addition to the model performance, model size is another very important factor that requires to consider when designing powerful neural network architectures. Therefore, we propose the multi-objective neural architecture search for light-weight model and name it Light-weight NAS. On one hand, the Light-weight NAS introduces Multiply-ACcumulate (MAC) into the optimize objective to get the architecture with fewer parameters. On the other hand, we simplify the search space and adopt weight sharing to make the search process more efficient. Experimental results indicate that the searched architecture can perform competitive classification accuracy with few parameters on the image classification task, while using less computation cost than the most existing multi-objective NAS approaches.

关键词： Computer architecture Convolution Computational modeling Task analysis Training Performance evaluation Neural networks

来源：评论

学校读者我要写书评

暂无评论

Comparative Study of Four Speed controllers of Brushless DC Motors for Industrial Applications

引用

IFAC-PapersOnLine 2020年第5期53卷 59-64页

作者： Tariku Sinshaw Tamir Gang Xiong Zhen Shen Xiaoyan Gong Sheng Liu Ehtisham Lodhi Li Wan Xisong Dong State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing 100190 China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing 100049 China Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing Cloud Computing Center Chinese Academy of Sciences Donggguan 523808 China Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation Chinese Academy of Sciences Beijing 100190 China Ten Dimensions (Guangdong) Technology Co. Ltd. Foshan 528225 China

Direct current (DC) motors are one of the most important kind of motors and are widely used in robotic and industrial applications. Recently, there have been significant efforts to develop direct current (DC) motors in an attempt to control speed of motors. However, conventional controlling approaches perform undesirably in terms of stability and quick response. Therefore, this paper presents a hybrid intelligent controller configuration for optimized speed control of brushless direct current (BLDC) motors in a factory supervisory control data acquisition (SCADA) system. We compare this hybrid intelligent controller with a conventional PID controller, fuzzy logic controller (FLC), and artificial neural network model reference controller (ANNMRC) in MATlab , and the results show that the hybrid (neuro-fuzzy) controller performs superior in terms of stability, speed trajectory tracking capability, fast response, and simplicity for implementation.

关键词： BLDC motor fuzzy logic controller (FLC) artificial neural network model reference controller (ANNMRC) hybrid (neuro-fuzzy) control

来源：评论

学校读者我要写书评

暂无评论

3-D Motion Analysis and Implementation of a Developed Gliding Robotic Dolphin

3-D Motion Analysis and Implementation of a Developed Glidin...

引用

IEEE International Conference on Robotics and Biomimetics

作者： Jian Wang Zhengxing Wu Jincun Liu Min Tan Junzhi Yu State Key Lab Management and Control for Complex Systems Institute of Automation CAS Beijing China Dept. Mech. Eng. Sci. Peking University Beijing China

This paper investigates the three-dimensional (3-D) maneuverability of a gliding robotic dolphin through analyzing the horizontal and vertical motions. Concretely, in order to improve the performance in the horizontal plane, the gliding robotic dolphin is developed with a rudder installed on its belly, and the 3-D full-state dynamic model is derived briefly. By setting two typical body and/or caudal fin (BCF)-based and three typical median and/or paired fin (MPF)-based turning patterns, the turning performances are revealed and analyzed. With regard to the vertical plane, a novel finite state machine framework is proposed to realize the vertical downward action. Finally, extensive experiments involving the turning and vertical motions are conducted to illustrate and analyze the 3-D maneuverability, which provides valuable guidance for the real-world applications of the gliding robotic dolphin.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A fusion measurement method based on kalman filter with improved state block and neural network for nanometer displacement 15

A fusion measurement method based on kalman filter with impr...

引用

15th IEEE International Conference on Mechatronics and automation, ICMA 2018

作者： Zhang, Zhuoliang Du, Zhangming Deng, Lu Zhou, Chao Cao, Zhiqiang Wang, Shuo Cheng, Long State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences University of Chinese Academy of Sciences Beijing China School of Statistics and Mathematics Central University of Finance and Economics Beijing China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781538660720

In the field of nanomanipulation, measurement method for the nano-scale displacement is one of the key technologies, and there are many restrictions on the sensors mounted in microscopic device. In order to reduce the influence of sensors on workspace, we fused the measurements of self-sensing and time-digit-conversion (TDC) method to estimate the measured nanometer displacement. Both of the two methods have a simple measurement circuit and are easy to be integrated. They can reduce the effect of thermal radiation on workspace and work in a vacuum environment (such as SEM chamber). We proposed a method based on Kalman filter with improved state block and neural network to obtain the fusion estimation. Our method achieved a sampling rate equal to that of self-sensing, as well as a precision higher than those of the two source methods. The linearity (R2) of our method is 0.9999915 throughout 8 µm range. Finally, we compared our method with the traditional fusion method based on statistics. © 2018 IEEE.

关键词： Kalman filters

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：