检索结果-内蒙古大学图书馆

Person Re-Identification Based on Spatial Feature Learning and Multi-Granularity Feature Fusion

上海交通大学学报（英文版） 2025年第2期30卷 363-374页

作者：刁子健曹帅李文威梁佳楠文桂林黄伟溪张寿明 Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming China Robotic Laboratory South China Robotics Innovation Research Institute Foshan China Robotic Laboratory Institute of Intelligent Manufacturing Guangdong Academy of Sciences Guangzhou China Foshan Zhiyouren Technology Co. Ltd. Foshan China

In view of the weak ability of the convolutional neural networks to explicitly learn spatial invariance and the probabilistic loss of discriminative features caused by occlusion and background interference in pedestrian re-identification tasks,a person re-identification method combining spatial feature learning and multi-granularity feature fusion was ***,an attention spatial transformation network(A-STN)is proposed to learn spatial features and solve the problem of misalignment of pedestrian spatial *** the network was divided into a global branch,a local coarse-grained fusion branch,and a local fine-grained fusion branch to extract pedestrian global features,coarse-grained fusion features,and fine-grained fusion features,*** them,the global branch enriches the global features by fusing different pooling *** local coarse-grained fusion branch uses an overlay pooling to enhance each local feature while learning the correlation relationship between multi-granularity *** local fine-grained fusion branch uses a differential pooling to obtain the differential features that were fused with global features to learn the relationship between pedestrian local features and pedestrian global ***,the proposed method was compared on three public datasets:Market1501,DukeMTMC-RelD and *** experimental results were better than those of the comparative methods,which verifies the effectiveness of the proposed method.

关键词： pedestrian re-identification spatial features attention spatial transformation network multi-branch network relation features

来源：评论

学校读者我要写书评

暂无评论

Design of TeleHaptic Simulators for Various Control Architectures 4

Design of TeleHaptic Simulators for Various Control Architec...

引用

4th International Conference on Computing, Mathematics and Engineering Technologies, iCoMET 2023

作者： Qureshi, Falaq Uddin, Riaz Ned University of Engineering and Technology Haptics Human-Robotics and Condition Monitoring Lab National Center of Robotics and Automation - Ncra HEC/PC Pakistan Department of Electrical Engineering Karachi75270 Pakistan

ISBN: (纸本)9798350335316

In this paper, we discuss the design of different models for teleoperation control by presenting the significant benchmark results for various important force reflecting control architectures used in 1-DOF bilateral teleoperation. They are used to analyze the results of force and distance tracking graphs in free motion and contact mode obtained from various control models by varying dynamics of master, slave, environment, and communication channel. In this regard, different force reflecting teleoperation control architectures are simulated via proposed model design, such as two-channel (2C) architectures, three-channel (3C) and finally four-channel (4C) architecture. These benchmark results are presented for each architecture via MATLAB/Simulink-based simulator. © 2023 IEEE.

关键词： Remote control

来源：评论

学校读者我要写书评

暂无评论

Uncertain Pushing Adaptive Coordinated Control for the Human-Exoskeleton-Walker System

引用

IEEE robotics and automation Letters 2025年第7期10卷 7086-7093页

作者： Zhang, Xinhao Yang, Chen Zhang, Jingting Zou, Chaobin Song, Guangkui Huang, Rui Farooq, Muhammad Umar Cheng, Hong University of Electronic Science and Technology of China Center for Robotics School of Automation Engineering Chengdu 611731 China

Lower Limb Exoskeletons are potential in the gait training for patients with gait disorders. For patients in the early rehabilitation stages with weak upper limb strength, it is challenge to keep balance by themselves only. A mobile robotic walker is helpful to maintain the walking balance, with the help of a physician pushing behind to keep a forward walking associated with the exoskeleton. However, since the gait patterns are varying with different training tasks, how to ensure a coordinated movement between the exoskeleton and the mobile robotic walker is challenge, especially with the uncertain pushing applied by the physician. In this letter, the Uncertain Pushing Adaptive Coordinated Control (UP-ACC) approach is proposed to solve the problem, which consists of two contributions. Based on the decoupled simplified dynamics, the center of mass trajectories and footstep placements are generated through linear model predictive control. In addition, the optimal footstep placement is used for the human-like gait planning by introducing the phases of heel-strike and toe-off. The proposed method has been verified in the robot simulation platform CoppeliaSim, and the experimental results indicate its effectiveness in generating coordinated motion and human-like gait patterns for the human-exoskeleton-walker system with the external pushing from 0 to 150 N and walking speed from 0.2 m/s to 0.6 m/s. © 2016 IEEE.

关键词： coordinated motion Exoskeleton human-like gait model predictive control robotic walker

来源：评论

学校读者我要写书评

暂无评论

Monitoring Street light using Power Line Carrier Communication (PLCC) & SCADA

Monitoring Street light using Power Line Carrier Communicati...

引用

2023 International Conference on System, Computation, automation and Networking, ICSCAN 2023

作者： Baskaran, A. Arunmozhi, S. Vishnu, S. Manakula Vinayagar Institute of Technology Dept of Robotics and Automation Engineering Puducherry India Manakula Vinayagar Institute of Technology Dept of Electronics and Communication Engineering Puducherry India

ISBN: (纸本)9798350315127

Streetlights provide illumination at night and provides safety on roads. Conventional monitoring of streetlights involves periodic human inspection which is time consuming, costly and sometimes unsafe. We proposed a remote monitoring and control of streetlights mounted on power transmission line posts using Power Line Carrie r Communication (PLCC) technology. PLC C allows transmission of data over existing power cables and does not require additional infrastructure. A PLCC modem is installed at each streetlight fixture which transmits status updates like lamp ON/OFF, voltage, current drawn etc. to a data concentrator unit via the low frequency power line network. The concentrator unit sends this information to a control center via a wireless or wired backhaul network. Such a solution ensures 24x7 monitoring of streetlights with minimum additional hardware investment. Mathematical models of different PLCC modulation schemes are developed and their performance is analyzed and compared through simulations. These Data were synchronized with SCADA to monitor the Streetlight. Practical implementation issues are also discussed. © 2023 IEEE.

关键词： Electric power transmission

来源：评论

学校读者我要写书评

暂无评论

Simulation of magnetization process and Faraday effect of magnetic bilayer films

引用

Chinese Physics B 2024年第9期33卷 590-597页

作者： Sheng Gao An Du Lei Zhang Tian-Guang Li Da-Cheng Ma Department of Basic and General Studies Shenyang Institute of Science and TechnologyShenyang 110167China College of Science Northeastern UniversityShenyang 110819China National Frontiers Science Center for Industrial Intelligence and Systems Optimization Northeastern UniversityShenyang 110819China Office of Academic Research Shenyang Institute of Science and TechnologyShenyang 110167China State Key Laboratory of Robotics Shenyang Institute of AutomationChinese Academy ofSciencesShenyang 110016China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of SciencesShenyang110016China

We described ferromagnetic film and bilayer films composed of two ferromagnetic layers coupled through antiferromagnetic interfacial interaction by classical Heisenberg model and simulated their magnetization state,magnetic permeability,and Faraday effect at zero and finite temperature by using the Landau–Lifshitz–Gilbert(LLG)*** results indicate that in a microwave field with positive circular polarization,the ferromagnetic film has one resonance peak while the bilayer film has two resonance ***,the resonance peak disappears in ferromagnetic film,and only one resonance peak emerges in bilayer film in the negative circularly polarized microwave *** the microwave field’s frequency exceeds the film’s resonance frequency,the Faraday rotation angle of the ferromagnetic film is the greatest,and it decreases when the thickness of the two halves of the bilayer is *** the microwave field’s frequency remains constant,the Faraday rotation angle fluctuates with temperature in the same manner as spontaneous magnetization *** a DC magnetic field is applied in the direction of the anisotropic axis of the film,the Faraday rotation angle varies with the DC magnetic field and shows a similar shape of the hysteresis loop.

关键词： magnetic bilayer films magnetic permeability hysteresis loop Faraday effect Landau-Lifshitz-Gilbert(LLG)equation

来源：评论

学校读者我要写书评

暂无评论

Exploring Eye-Tracking Based Biomarkers to Assess Cognitive Abilities in Autistic Children: A Feasibility Study

引用

IEEE Journal of Biomedical and Health Informatics 2025年第6期29卷 4401-4414页

作者： Zhang, Hanlin Hu, Chunchun Wang, Zhiyong Zhou, Bingrui Wang, Xinming Nie, Wei Ye, Qinyi Lin, Ruihan Xu, Xiu Liu, Honghai Harbin Institute of Technology State Key Laboratory of Robotics and System School of Mechanical Engineering and Automation Shenzhen518055 China Children's Hospital of Fudan University Department of Child Health Care Shanghai201102 China Peng Cheng Laboratory Shenzhen518000 China

Cognitive assessment can reveal a person's cognitive processing and behavioral patterns, making it an indispensable component of autism intervention and prognosis. Existing machine-assisted cognitive assessment methods primarily focus on children's performance outcomes, overlooking distinctive behavioral models, particularly characteristics of eye movement behavior, which have been demonstrated as the most direct indicators of cognitive abilities. In this study, we explore eye-tracking biomarkers for assisting cognitive assessment through a series of meticulously designed multi-level human-computer interaction protocols, encompassing three cognitive abilities: pairing and categorization, emotion recognition, and social interaction. A platform embedded with an eye-tracking module has been developed to reliably collect and analyze eye movement data, even in the presence of unrestricted large head movements in children. Experimental results indicate that there are significant group differences between autism and typically developing children in the eye-tracking features of total fixation duration, response latency, time to first fixation, mean fixation duration, and visit count in the absence of significant intergroup differences in the Wechsler Preschool and Primary Scale of Intelligence (WPPSI) and Wechsler Intelligence Scale for Children (WISC) assessment results. In addition, certain eye-tracking features in each group are correlated with WPPSI/WISC scale scores, enabling clinical cognitive assessments within each group based on these eye movement features. This study suggests that using eye-tracking features as biomarkers to assist detailed cognitive assessments holds significant potential for the intervention and prognosis of autism. © 2013 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Planning of Time-Efficient Trajectories for Mobile Robots with Differential-Drives 29

Planning of Time-Efficient Trajectories for Mobile Robots wi...

引用

29th IEEE International Conference on Emerging Technologies and Factory automation, ETFA 2024

作者： Lelidis, Philipp Vick, Axel Production Machinery and Equipment Management Fraunhofer Institute for Production Systems and Design Technology Ipk Berlin Germany Process Automation and Robotics Fraunhofer Institute for Production Systems and Design Technology Ipk Berlin Germany

ISBN: (纸本)9798350361230

To effectively utilize the capacities of the production facilities, flexible and fast transport, and manipulation technology is essential. Current path planning methods use simple paths without exploiting the physical limitations of mobile robots. This paper deals with the time-efficient kinematic planning of path and velocity trajectories for autonomous mobile robots equipped with a differential-drive, used to load and unload machine tools. For a close parking position next to the machine tools, the mobile robot must approach practically straight without the necessity of turning at the end. After a brief definition of the kinematics of a mobile robot with nonholonomic constraints, a Bezier-curve is combined with multiple jerk-limited velocity trajectories considering the initial and final state as well as the physical limitations. For a time-efficient acceleration and deceleration the maximum acceleration of the mobile robot is used and differentiated into the radial and tangential acceleration. This allows a quickly reached close parking pose next to a machine tool. The algorithm is tested with simulations in RVIZ in combination with Gazebo and ROS2 as well as with the real mobile robot Tend-o-Bot. © 2024 IEEE.

关键词： Mobile robots

来源：评论

学校读者我要写书评

暂无评论

Multi-modality hierarchical fusion network for lumbar spine segmentation with magnetic resonance images

引用

Control Theory and technology 2024年第4期22卷 612-622页

作者： Han Yan Guangtao Zhang Wei Cui Zhuliang Yu School of Automation Science and Engineering South China University of TechnologyGuangzhou510641GuangdongChina Guangzhou First People’s Hospital Guangzhou510180GuangdongChina Shien-Ming Wu School of Intelligent Engineering South China University of TechnologyGuangzhou511442GuangdongChina Institute for Super Robotics(Huangpu) Guangzhou510000GuangdongChina

For the analysis of spinal and disc diseases,automated tissue segmentation of the lumbar spine is *** to the continuous and concentrated location of the target,the abundance of edge features,and individual differences,conventional automatic segmentation methods perform *** the success of deep learning in the segmentation of medical images has been shown in the past few years,it has been applied to this task in a number of *** multi-scale and multi-modal features of lumbar tissues,however,are rarely explored by methodologies of deep *** of the inadequacies in medical images availability,it is crucial to effectively fuse various modes of data collection for model training to alleviate the problem of insufficient *** this paper,we propose a novel multi-modality hierarchical fusion network(MHFN)for improving lumbar spine segmentation by learning robust feature representations from multi-modality magnetic resonance *** adaptive group fusion module(AGFM)is introduced in this paper to fuse features from various modes to extract cross-modality features that could be ***,to combine features from low to high levels of cross-modality,we design a hierarchical fusion structure based on *** to the other feature fusion methods,AGFM is more effective based on experimental results on multi-modality MR images of the lumbar *** further enhance segmentation accuracy,we compare our network with baseline fusion *** to the baseline fusion structures(input-level:76.27%,layer-level:78.10%,decision-level:79.14%),our network was able to segment fractured vertebrae more accurately(85.05%).

关键词： Lumbar spine segmentation Deep learning Multi-modality fusion Feature fusion

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Muscle Activation Reaction on Vertical Climbing 9

Evaluation of Muscle Activation Reaction on Vertical Climbin...

引用

9th International Conference on Electrical Engineering, Control and robotics, EECR 2023

作者： Wang, Li Pang, Muye Xiang, Kui Luo, Jing Tang, Biwei Lu, Baizhong Wuhan University of Technology School of Automation Wuhan China Wuhan Guozhi Robotics System Engineering Co. Ltd. China

ISBN: (纸本)9781665491204

Vertical climbing is a common movement in industrial field, which requires coordination of entire body joints and is a high-risk task for workers. Exoskeletons have the ability to assist wear to perform vertical climbing and reduce the risk of failed motion. However, raw studies have paid attention on exoskeleton-assisted vertical climbing. In order to develop vertical climbing assistance strategy for exoskeleton system, it is essential to obtain the inherent control strategy of human subject for this movement. Muscle activations, which can be observed by surface Electromyography (sEMG) signals, are able to present muscle activity or human potential control intent. Therefore, we adopt muscle synergy technology to analyze human vertical climbing movement. Firstly, the whole process is divided into four phases according to the movement data and sEMG data collected in experiment. Then, the preprocessed signals were decomposed using a non-negative matrix factorization (NNMF) algorithm. Finally, four muscle synergistic responses are extracted by variance accounted for (VAF) approach. The results of the experiments showed that the subjects' muscle synergy between the different phases was not highly correlated. The final finding may indicate that during vertical climbing, human beings change muscle activation patterns to adapt to the impacts from body stability and to realize vertical climbing. © 2023 IEEE.

关键词： Non-negative matrix factorization

来源：评论

学校读者我要写书评

暂无评论

Spatio-Temporal Communication Compression in Distributed Prime-Dual Flows 63

Spatio-Temporal Communication Compression in Distributed Pri...

引用

63rd IEEE Conference on Decision and Control, CDC 2024

作者： Ren, Zihao Wang, Lei Yuan, Deming Su, Hongye Shi, Guodong Zhejiang University College of Control Science and Engineering China Nanjing University of Science and Technology School of Automation China University of Sydney Australia Centre for Field Robotics Australia

ISBN: (纸本)9798350316339

In this paper, we study distributed prime-dual flows for multi-agent optimization with spatio-temporal compressions. The central aim of multi-agent optimization is for a network of agents to collaboratively solve a system-level optimization problem with local objective functions and node-to-node communication by distributed algorithms. The scalability of such algorithms crucially depends on the complexity of the communication messages, and a number of communication compressors for distributed optimization have recently been proposed in the literature. First of all, we introduce a general spatio-temporal compressor characterized by the stability of the resulting dynamical system along the vector field of the compressor. We show that several important distributed optimization compressors such as the greedy sparsifier, the uniform quantizer, and the scalarizer all fall into the category of this spatio-temporal compressor. Next, we propose two distributed prime-dual flows with the spatio-temporal compressors being applied to local node states and local error states, respectively, and prove (exponential) convergence of the node trajectories to the global optimizer for (strongly) convex cost functions. Finally, a few numerical examples are present to illustrate our theoretical results. © 2024 IEEE.

关键词： Cost functions

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：