检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Gao, Jiaqi Huang, Zhizhong Lei, Yiming Shan, Hongming Wang, James Z. Wang, Fei-Yue Zhang, Junping The Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University Shanghai200433 China The Institute of Science and Technology for Brain-inspired Intelligence MOE Frontiers Center for Brain Science Fudan University Shanghai200433 China The Shanghai Center for Brain Science and Brain-Inspired Technology Shanghai201210 China The College of Information Sciences and Technology The Pennsylvania State University University ParkPA16802 United States The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China The Institute of Systems Engineering Macau University of Science and Technology China Qingdao Academy of Intelligent Industries Qingdao266109 China

Most conventional crowd counting methods utilize a fully-supervised learning framework to establish a mapping between scene images and crowd density maps. They usually rely on a large quantity of costly and time-intensive pixel-level annotations for training supervision. One way to mitigate the intensive labeling effort and improve counting accuracy is to leverage large amounts of unlabeled images. This is attributed to the inherent self-structural information and rank consistency within a single image, offering additional qualitative relation supervision during training. Contrary to earlier methods that utilized the rank relations at the original image level, we explore such rank-consistency relation within the latent feature spaces. This approach enables the incorporation of numerous pyramid partial orders, strengthening the model representation capability. A notable advantage is that it can also increase the utilization ratio of unlabeled samples. Specifically, we propose a Deep Rank-consistEnt pyrAmid Model (DREAM), which makes full use of rank consistency across coarse-to-fine pyramid features in latent spaces for enhanced crowd counting with massive unlabeled images. In addition, we have collected a new unlabeled crowd counting dataset, FUDAN-UCC, comprising 4,000 images for training purposes. Extensive experiments on four benchmark datasets, namely UCF-QNRF, ShanghaiTech PartA and PartB, and UCF-CC-50, show the effectiveness of our method compared with previous semi-supervised methods. The codes are available at https://***/bridgeqiqi/DREAM. Copyright © 2022, The Authors. All rights reserved.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

An Interpretability Analysis of Travel Decision Learning in Cyber-Physical-Social-systems

An Interpretability Analysis of Travel Decision Learning in ...

引用

Digital Twins and Parallel Intelligence (DTPI), IEEE International Conference on

作者： Miao Guo Peijun Ye Xudong Liu Sheng Liu Gang Xiong Liguo Zhang The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Faculty of Information and Technology Beijing University of Technology Beijing China The Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation Chinese Academy of Sciences Beijing China The Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing The Cloud Computing Center Chinese Academy of Sciences Beijing China

In the few decades, the rise of Internet and social media has fundamentally changed the management, control, and operation modes of modern engineering and social systems like defense, energy, critical health care and ... 详细信息

关键词： Deep learning Social networking (online) Scalability Perturbation methods Neurons Transportation Transforms

来源：评论

学校读者我要写书评

暂无评论

Joint Face Alignment and 3D Face Reconstruction with Efficient Convolution Neural Networks

Joint Face Alignment and 3D Face Reconstruction with Efficie...

引用

International Conference on Pattern Recognition

作者： Keqiang Li Huaiyu Wu Xiuqin Shang Zhen Shen Gang Xiong Xisong Dong Bin Hu Fei-Yue Wang School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China The Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation Chinese Academy of Sciences Beijing China The Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing Cloud Computing Center Chinese Academy of Sciences Dongguan China

3D face reconstruction from a single 2D facial image is a challenging and concerned problem. Recent methods based on CNN typically aim to learn parameters of 3D Morphable Model (3DMM) from 2D images to render face alignment and 3D face reconstruction. Most algorithms are designed for faces with small, medium yaw angles, which is extremely challenging to align faces in large poses. At the same time, they are not efficient usually. The main challenge is that it takes time to determine the parameters accurately. In order to address this challenge with the goal of improving performance, this paper proposes a novel and efficient end-to-end framework. We design an efficient and lightweight network model combined with Depthwise Separable Convolution and Muti-scale Representation, Lightweight Attention Mechanism, named Mobile-FRNet. Simultaneously, different loss functions are used to constrain and optimize 3DMM parameters and 3D vertices during training to improve the performance of the network. Meanwhile, extensive experiments on the challenging datasets show that our method significantly improves the accuracy of face alignment and 3D face reconstruction. Model parameters and complexity of our method are also improved greatly.

关键词： Training Solid modeling Three-dimensional displays Convolution Face recognition Neural networks complexity theory

来源：评论

学校读者我要写书评

暂无评论

Fast Calibration of Agent-Based Model using Mean-Field Approach

Fast Calibration of Agent-Based Model using Mean-Field Appro...

引用

Digital Twins and Parallel Intelligence (DTPI), IEEE International Conference on

作者： Wanze Lu Gang Xiong Xudong Liu Sheng Liu Peijun Ye Liguo Zhang Faculty of Information and Technology Beijing University of Technology Beijing China The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China The Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation Chinese Academy of Sciences Beijing China The Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing The Cloud Computing Center Chinese Academy of Sciences Beijing China

Calibration of simulation system is an important step to establish a reliable simulation system. In this paper, based on the existing mean field calibration theory, a new fast calibration method for complex urban traffic system based on mean field method is discussed by establishing the relationship between the macroscopic observation quantity and the proxy microscopic parameters. This method makes use of the machine learning method, and reduces the dimension of the state vector in the discrete time period, so that the dimension of the macroscopic state transition matrix is lower, and then reduces the computational complexity of the system calibration. Finally, the calibration results of the simulation system were verified by SUMO traffic simulation software.

关键词： Visualization Computational modeling Microscopy Digital twin Machine learning Traffic control Reliability theory

来源：评论

学校读者我要写书评

暂无评论

Design of Smart Home Monitoring and control System Based on Zigbee and WIFI

Design of Smart Home Monitoring and Control System Based on ...

引用

第三十八届中国控制会议

作者： Chentao Li Kaifeng Dong Fang Jin Junlei Song Wenqin Mo School of Automation China University of Geosciences Hubei key Laboratory of Advanced Control and Intelligent Automation for Complex Systems

Smart Home system is the use of home life associated with hardware and related application technology, the introduction of home appliance automation, remote control, intelligent processing technology in a traditional home environment, to design a provide users with comprehensive information exchange capabilities, in order to enhanced home life safety, comfort and convenience of home systems. At present, there are problems such as complicated wiring, single service, and high price in this field. In response to these problems, this paper designs a smart home system based on Zigbee and WIFI. The system consists of a terminal node, a gateway node and a remote control terminal. The terminal node and the gateway node form a home internal network through Zigbee technology, and the remote control terminal accesses and controls the home internal network through WIFI.

关键词： Smart home Zigbee WIFI Wireless transmission Remote control

来源：评论

学校读者我要写书评

暂无评论

control System Design for Weight on Bit in complex Geological Drilling Process

Control System Design for Weight on Bit in Complex Geologica...

引用

第三十八届中国控制会议

作者： Sike Ma Min Wu Jun Cheng Luefeng Chen School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems

With the increase in drilling depth, the encountered formations become more complicated, and industrial controller for weight on bit has limited precision due to the uncertain and varying formations. In this paper, we design a scheme of control system for weight on bit to achieve higher control precision in complex geological drilling process. A double-loop control structure is introduced, which involves with two system models: a multi-degree-of-freedom lumped parameter drill string model and a finite element bit-rock interaction model. The effect of varying formations on weight on bit is analyzed, and a control strategy for control system is presented in this paper.

关键词： Drilling process weight on bit control system drill string model bit-rock interaction model uncertain formations

来源：评论

学校读者我要写书评

暂无评论

Position Solution and Motion Simulation for Rock Drilling Arm

Position Solution and Motion Simulation for Rock Drilling Ar...

引用

第三十八届中国控制会议

作者： Zhilin Tang Jianqi An School of Automation China University of Geosciences Hubei key Laboratory of Advanced Control and Intelligent Automation for Complex Systems

Drilling rigs are key devices in tunnel projects, which dig holes on a rock face by drilling arms. The quality and efficiency of tunnel constructions are directly determined by the positioning accuracy of the holes and time for traversing all the holes. This paper provides a complete solution for trajectory planning with accuracy and efficiency. First, this paper analyzes the structure of a drilling arm, establishes a forward kinematic model of the drilling arm by Denavit-Hartenberg convention. Next,to solve the inverse kinematics problem of drilling arm, a particle swarm optimization with adaptive inertia weight is ***, an optimal drilling sequence is found based on Hopfield network. Thereafter, a quintic polynomial method has been adopted to calculate the trajectory of the drilling arm. Finally, results of simulations show that the solution satisfies the accuracy of positioning and calculates the optimal trajectory.

关键词： inverse kinematic robot manipulator trajectory planning particle swarm optimization

来源：评论

学校读者我要写书评

暂无评论

Stability Analysis of Nonlinear Teleoperation systems With Time-Varying Delays Via A Delay-Product-Type Functional

Stability Analysis of Nonlinear Teleoperation Systems With T...

引用

第三十八届中国控制会议

作者： Xiao-Hui Guo Chuan-Ke Zhang Yong He School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems

This paper is concerned with the stability analysis of a class of nonlinear teleoperation systems with time-varying delays. The proportional derivative position position control scheme with asymmetrical time-varying delays in control loops is considered for the master and the slave robots. Firstly, a new Lyapunov-Krasovskii functional（LKF） with several delayproduct-type terms is constructed by using the information of asymmetrical time-varying delays;and the Wirtinger-based integral inequality and the reciprocally convex matrix inequality are used to estimate the derivative of the LKF. As a result, a delaydependent stability criterion with less conservatism is established. Finally, an example is given to show the effectiveness and merits of the proposed criterion.

关键词： Nonlinear teleoperation system time-varying delay stability analysis linear matrix inequality

来源：评论

学校读者我要写书评

暂无评论

Extraction of Color Characteristics of Pesticide Detection Card Based on Machine Vision

Extraction of Color Characteristics of Pesticide Detection C...

引用

第三十八届中国控制会议

作者： fang Jin xin Tu kaifeng Dong junlei Song wenqin Mo School of Automation China University of Geosciences Hubei key Laboratory of Advanced Control and Intelligent Automation for Complex Systems

In this paper, aiming at the pesticide residue in water resources, considering the necessity of rapid detection on site,a method based on machine vision for pesticide residue detection is proposed. The method combines machine vision and image processing technology to quickly extract the RGB three-component eigenvalues of the pesticide residue detection card. Each RGB channel has 256 brightness levels, which can overcome the shortcomings of low brightness level and indistinct image,and improve the accuracy of detection. The results show that the method is simple,fast and efficient, it is suitable for quickly extracting the characteristic values of pesticide residue detection cards.

关键词： Machine vision pesticide residue detection RGB color space

来源：评论

学校读者我要写书评

暂无评论

Parallel Architecture Based Iterative Segmentation Optimal Cyclic Block Kernel Learning Algorithm

Parallel Architecture Based Iterative Segmentation Optimal C...

引用

第三十八届中国控制会议

作者： Lu Li Xin Chen School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems

The kernel learning algorithm has been widely used to solve the generalization problem existing in reinforcement learning. However, when the state-action space of the sample is large, the computation and storage burden in the kernel learning algorithm will increase. In such case, there will be long running time and the real-time performance of the control system cannot be guaranteed. Therefore, in order to enhance the computational speed, this paper proposes a parallel architecture based iterative segmentation optimal cyclic block kernel learning algorithm. The experimental results show that the proposed method can significantly improve the computational efficiency of the kernel learning algorithm, which has important engineering practice significance.

关键词： Kernel Learning Algorithm Iterative Segmentation Cyclic Block Parallel Architecture

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：