检索结果-内蒙古大学图书馆

2021 CIE International Conference on Radar, Radar 2021

作者： Lu, Dongdong Tie, Wenjie Lei, Songlin Qiu, Xiaolan Suzhou Aerospace Information Research Institute Laboratory of Spatial Information Intelligent Processing System Suzhou China Chinese Academy of Sciences Key Laboratory of Technology in Geo-spatial Information Processing and Application Systems Beijing China

ISBN: (纸本)9781665498142

Deep learning has achieved remarkable results in the field of target detection and recognition. For small targets in images, image pyramid can be used to fuse multi-scale features to improve detection performance. However, when test on remote sensing images, it is found that some important small goals will still be missed. Aiming at the problems of small target detection in remote sensing images, this paper proposes two S2ANet improved network variants based on the attention mechanism for synthetic aperture radar(SAR) payload and optical payload: for SAR images, CBAM(Convolutional Block Attention Module) attention is added to the backbone network to increase the attention of the feature extraction network for small targets in the channel and space dimensions;For optical images, firstly increase the CBAM channel attention and spatial attention in the backbone, secondly, the SE(Squeeze And Excitation) channel attention is added to the input features before the channel dimension fusion of the pyramid structure, then the attention-enhanced targets are fully integrated through up-sampling and horizontal splicing operations to improve the missed alarm rate and recall rate of small remote sensing targets. Finally, a comparative verification was carried out on the constructed airborne KU-band SAR data set and the optical remote sensing aircraft data set composed of some DOTA1.5 and FAIR1M data sets. The experimental results proved that the designed two variant networks can be used for small remote sensing. There have been certain improvements in the missed alarm rate, accuracy rate, and recall rate of the target. © 2021 IEEE.

关键词： Radar remote sensing Radar detection Object detection Radar imaging Optical imaging Feature extraction Adaptive optics

来源：评论

学校读者我要写书评

暂无评论

Image-based Freeform Handwriting Authentication with Energy-oriented Self-Supervised Learning

arXiv

引用

arXiv 2024年

作者： Wang, Jingyao Mou, Luntian Zheng, Changwen Gao, Wen The University of Chinese Academy of Sciences Beijing100049 China The National Key Laboratory of Space Integrated Information System Institute of Software Chinese Academy of Sciences Beijing100086 China Beijing Institute of Artiicial Intelligence Faculty of Information Beijing University of Technology Beijing100124 China Beijing Key Laboratory of Multimedia and Intelligent Software Technology Beijing100124 China The School of Electronics Engineering and Computer Science Peking University Beijing100871 China

Freeform handwriting authentication verifies a person’s identity from their writing style and habits in messy handwriting data. This technique has gained widespread attention in recent years as a valuable tool for various fields, e.g., fraud prevention and cultural heritage protection. However, it still remains a challenging task in reality due to three reasons: (i) severe damage, (ii) complex high-dimensional features, and (iii) lack of supervision. To address these issues, we propose SherlockNet, an energy-oriented two-branch contrastive self-supervised learning framework for robust and fast freeform handwriting authentication. It consists of four stages: (i) pre-processing: converting manuscripts into energy distributions using a novel plug-and-play energy-oriented operator to eliminate the influence of noise;(ii) generalized pre-training: learning general representation through two-branch momentum-based adaptive contrastive learning with the energy distributions, which handles the high-dimensional features and spatial dependencies of handwriting;(iii) personalized fine-tuning: calibrating the learned knowledge using a small amount of labeled data from downstream tasks;and (iv) practical application: identifying individual handwriting from scrambled, missing, or forged data efficiently and conveniently. Considering the practicality, we construct EN-HA, a novel dataset that simulates data forgery and severe damage in real applications. Finally, we conduct extensive experiments on six benchmark datasets including our EN-HA, and the results prove the robustness and efficiency of SherlockNet. We will release our code and dataset at https://***/WangJingyao07/SherlockNet. Copyright © 2024, The Authors. All rights reserved.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Discrete Element Simulation of Durability for Bionic Wheels of Mars Rover 2

Discrete Element Simulation of Durability for Bionic Wheels ...

引用

2nd Spring International Conference on Defence technology, ICDT 2020

作者： Lin, Y.C. Yan, Y.P. Yuan, B.F. Liu, Y.F. Zou, M. Beijing Key Laboratory of Intelligent Space Robotic System Technology and Application Institute of Spacecraft System Engineering CAST Beijing100094 China Key Laboratory for Bionics Engineering of Education Ministry Jilin University Changchun130022 China

Four kinds of bionic surfaces (convex, scale-like, ribbed and concave shape) for Mars rover wheels were designed to improve wheel durability. A discrete element wheel-soil simulation system was developed, and three-dimensional discrete element analysis and soil bin tests were conducted. The results show that the masses of the convex and scale-like forms increased by 5.4% and 17%, respectively, and that the tangential cumulative forces decreased by about 40% and 70%, respectively. The wear mass decreased by 53% and 47%, respectively, compared with a prototypical wheel. The simulation shows that the durability increased significantly. The average tangential cumulative forces of the concave and ribbed shapes increased by more than 50%, and the wear mass decreased by 35% and 32%, respectively, compared with a prototypical wheel. The simulation shows that the results were not definitive. The analysis shows that the durability of the wheels can be improved via bionic optimization method. These results therefore provide a basis and reference for the design and optimization of the Mars rover's wheel surface. © Published under licence by IOP Publishing Ltd.

关键词： Wheels

来源：评论

学校读者我要写书评

暂无评论

Design of a Capsule robot system for Gastric Hemorrhage Detection using Luminol

Design of a Capsule Robot System for Gastric Hemorrhage Dete...

引用

IEEE International Conference on Mechatronics and Automation

作者： Yuchen Mao Jian Guo Shuxiang Guo Qiang Fu Tianjin Key Laboratory for Control Theory & Application Complicated Systems and Intelligent Robot Laboratory School of Electrical Engineering and Automation Tianjin University of Technology Binshui Xidao Extension 391 Tianjin China Shenzhen Institute of Advanced Biomedical Robot Co. Ltd No.12 Ganli Sixth Road Jihua Street Longgang District Shenzhen China Key Laboratory of Convergence Medical Engineering System and Healthcare Technology The Ministry of Industry and Information Technology School of Life Science Beijing Institute of Technology No.5 Zhongguancun South Street Beijing China

Gastric hemorrhage in upper gastrointestinal bleeding is an obvious indicator of deteriorating gastric disease. This paper proposes a capsule robot system for detecting bleeding in the stomach. The patient ingests a capsule robot containing luminol reagent, which detects bleeding in the stomach via chemiluminescence. The MCU receives the optical sensor signal, and the data is transmitted via radio frequency. The external lower computer receives and forwards the data to the upper computer for processing and display. The data is used to determine the presence and amount of stomach bleeding. Chemiluminescence is an excellent sensor, requiring no external energy supply, and demonstrating excellent sensitivity and selectivity. Combining chemical and electronic sensors presents opportunities for further development. Capsule robot detection reduces the discomfort and risk of secondary injury associated with traditional endoscopy. This paper establishes an experimental platform using porcine blood to simulate human blood, demonstrating the feasibility of the system.

关键词：

来源：评论

学校读者我要写书评

暂无评论

key Techniques on Unified Identity Authentication in OpenMBEE Integration 4

Key Techniques on Unified Identity Authentication in OpenMBE...

引用

4th IEEE International Conference on Electronics and Communication Engineering, ICECE 2021

作者： Xue, Junjie Zhou, Junhua Shi, Guoqiang Feng, Chaoqun Liu, Penghua Quan, Hongyan Beijing Complex Product Advanced Manufacturing Engineering Research Center Beijing Simulation Center Beijing China State Key Laboratory of Intelligent Manufacturing System Technology Beijing China Institute of Electronic System Engineering Beijing China Beijing Complex Product Advanced Manufacturing Engineering Research Center Beijing Simulation Center Beijing China Science and Technology on Space System Simulation Laboratory Beijing Simulation Center Beijing China School of Computer Science and Technology East China Normal University Shanghai China

ISBN: (纸本)9781728194226

In order to make full use of the concept of model-based systems engineering (MBSE) and the collaborative design capability of the open model-based engineering environment (OpenMBEE) in establishing complex product development platform, we propose an effective method to solve the problem of unified identity authentication in OpenMBEE integration. The proposed method is based on the Model View Controller(MVC) architecture in OpenMBEE, which has the characteristics strong plasticity and can be benefit for expanding the function in the controller layer. In our research, we make full use of the Software Development Kit (SDK) of OpenMBEE to expand the existing functions in the controller layer, and increase the function of communicating with the application development platform, then realize the function of sharing user authentication information between the development platform and OpenMBEE. After expansion, the system includes three modules, including the Front-end Service Module(FSM), MQ based Information Receiving Service Module(IFRSM), and the OpenMBEE Back-end Server Module(BSM). The effectiveness of the proposed strategies is verified by some practical instances, which verifies that our study can provide an effective design idea for the identity authentication in OpenMBEE integration. ©2021 IEEE

关键词： Integration

来源：评论

学校读者我要写书评

暂无评论

How many trees are there in China?

引用

Science Bulletin 2025年第7期70卷 1076-1079页

作者： Kai Cheng Haitao Yang Yuling Chen Zekun Yang Yu Ren Yixuan Zhang Danyang Lin Weiyan Liu Guoran Huang Jiachen Xu Mengxi Chen Zhiyong Qi Guangcai Xu Shengli Tao Hongcan Guan Qin Ma Huawei Wan Tianyu Hu Yanjun Su Zhiheng Wang Keping Ma Qinghua Guo Institute of Remote Sensing and Geographic Information System School of Earth and Space SciencesPeking UniversityBeijing 100871China State Forestry and Grassland Administration Key Laboratory of Forest Resources&Environmental Management Beijing Forestry UniversityBeijing 100083China College of Forestry Southwest Forestry UniversityKunming 650224China Beijing Green Valley Technology Co. Ltd.Haidian DistrictBeijing 100091China Institute of Ecology College of Urban and Environmental SciencesPeking UniversityBeijing 100871China School of Tropical Agriculture and Forestry Hainan UniversityHaikou 570228China School of Geography Nanjing Normal UniversityNanjing 210023China Satellite Environmental Application Center of Ministry of Ecology and Environment Beijing 100094China State Key Laboratory of Vegetation and Environmental Change Institute of BotanyChinese Academy of SciencesBeijing 100093China University of Chinese Academy of Sciences Beijing 100049China

Accurate quantification of tree populations within regions is critical for evaluating forest ecosystem conditions and developing effective forest management strategies[1].High-quality tree census data,collected through field surveys and remote sensing technologies,is fundamental to China's sustainable development and environmental conservation *** data facilitates the monitoring of forest structural changes,carbon sequestration dynamics,and ecosystem health ***,China maintains the world's largest managed forest area,achieved through comprehensive national afforestation and reforestation programs[2,3].Consequently,precise tree enumeration is crucial for formulating effective forest management policies,monitoring and protecting wildlife habitats,and preventing natural disasters in China.

关键词： remote sensing technologiesis quantification tree populations forest management developing effective forest management strategies high quality field surveys monitoring forest structural changescarbon sequestration dynamicsand evaluating forest ecosystem conditions tree population

来源：评论

学校读者我要写书评

暂无评论

DNN Task Assignment in UAV Networks: A Generative AI Enhanced Multi-Agent Reinforcement Learning Approach

arXiv

引用

arXiv 2024年

作者： Tang, Xin Chen, Qian Weng, Wenjie Liao, Binhan Wang, Jiacheng Cao, Xianbin Li, Xiaohuan Guangxi University Key Laboratory of Intelligent Networking and Scenario System School of Information and Communication Guilin University of Electronic Technology Guilin541004 China The College of Computing and Data Science Nanyang Technological University 639798 Singapore School of Architecture and Transportation Engineering Guilin University of Electronic Technology Guilin541004 China National Engineering Laboratory for Comprehensive Transportation Big Data Application Technology Guangxi Nanning530001 China College of Computing and Data Science Nanyang Technological University 639798 Singapore School of Electronic and Information Engineering The Key Laboratory of Advanced Technology of Near Space Information System Ministry of Industry and Information Technology of China Beihang University Beijing100191 China

Unmanned Aerial Vehicles (UAVs) possess high mobility and flexible deployment capabilities, prompting the development of UAVs for various application scenarios within the Internet of Things (IoT). The unique capabilities of UAVs give rise to increasingly critical and complex tasks in uncertain and potentially harsh environments. The substantial amount of data generated from these applications necessitates processing and analysis through deep neural networks (DNNs). However, UAVs encounter challenges due to their limited computing resources when managing DNN models. This paper presents a joint approach that combines multiple-agent reinforcement learning (MARL) and generative diffusion models (GDM) for assigning DNN tasks to a UAV swarm, aimed at reducing latency from task capture to result output. To address these challenges, we first consider the task size of the target area to be inspected and the shortest flying path as optimization constraints, employing a greedy algorithm to resolve the subproblem with a focus on minimizing the UAV’s flying path and the overall system cost. In the second stage, we introduce a novel DNN task assignment algorithm, termed GDM-MADDPG, which utilizes the reverse denoising process of GDM to replace the actor network in multi-agent deep deterministic policy gradient (MADDPG). This approach generates specific DNN task assignment actions based on agents’ observations in a dynamic environment. Simulation results indicate that our algorithm performs favorably compared to benchmarks in terms of path planning, Age of Information (AoI), energy consumption, and task load balancing. Copyright © 2024, The Authors. All rights reserved.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Distributed Force Synchronization for Networked robotic Manipulators with Transmission Delays

Distributed Force Synchronization for Networked Robotic Mani...

引用

IEEE International Conference on robotics and Biomimetics

作者： Xiaodong Zhang Chao Ma Tao Xiao Liziyi Hao Beijing Key Laboratory of Intelligent Space Robotic Systems Technology and Application Beijing Institute of Spacecraft System Engineering CAST China School of Mechanical Engineering University of Science and Technology Beijing Beijing China

ISBN: (纸本)9781665405362

This paper investigates the force synchronization problem for multiple robotic manipulators with network-induced transmission delays. More specifically, the synchronization control strategy is proposed under distributed framework to deal with interaction forces. Based on the developed control and information exchange strategy, sufficient synchronization criterion under directed topology is established by means of Lyapunov-Krasovskii method. Finally, an illustrate example is provided with simulation results to validate the effectiveness of the theoretical results.

关键词： Network topology Control design Simulation Force Decentralized control Manipulators Delays

来源：评论

学校读者我要写书评

暂无评论

Single-Dimensional Intuitive teaching Control for Constrained space robotic Manipulation

Single-Dimensional Intuitive teaching Control for Constraine...

引用

IEEE International Conference on robotics and Biomimetics

作者： Hang Gao Xiaodong Zhang Huanbin Xu Tao Xiao Chao Ma School of Mechanical Engineering University of Science and Technology Beijing Beijing China Beijing Key Laboratory of Intelligent Space Robotic Systems Technology and Application Beijing Institute of Spacecraft System Engineering Cast China

ISBN: (纸本)9781665405362

In this paper, a single-dimensional intuitive teaching algorithm for space robots is proposed to solve the motion control problem when the operating space is limited or the moving direction is relatively special under complex space environments. More precisely, the developed method can specify the direction and reaches the specified position under the drag motion of the hand. The realization algorithm of single-dimension intuitive teaching is derived according to the structure of the robot. In the end, an experiment example is given, which proves the feasibility of the proposed algorithm.

关键词： robot kinematics Education Aerospace electronics robot sensing systems Sensor systems Sensors Reliability

来源：评论

学校读者我要写书评

暂无评论

A Soft robotic system Imitating the Multimodal Sensory Mechanism of Human Fingers for intelligent Grasping and Recognition

SSRN

引用

SSRN 2024年

作者： Xu, Jinsui Xu, Boyi Zhan, Hao Xie, Zhijie Tian, Zhen Lu, Yifan Wang, Zheping Yue, Honghao Yang, Fei South China University of Technology China State Key Laboratory of Robotics and System School of Mechatronics Engineering Harbin Institute of Technology Harbin150001 China Wu Xianming School of Intelligent Engineering South China University of Technology Guangzhou510641 China College of Mechanical and Electrical Engineering Northeast Forestry University Harbin150042 China Science and Technology on Space Physics Laboratory China Academy of Launch Vehicle Technology Beijing100000 China

The sensory function is crucial for achieving precise feedback control and environmental interaction in soft robots. Therefore, the multimodal sensory capabilities that mimic human fingers have always been a research hotspot. This study proposes a design method for a soft robotic gripper that can emulate the multimodal perception mechanism of human fingers and achieve high-precision recognition of grasped objects using machine learning algorithms. In addition, a finger texture structure inspired by human fingerprints is designed using a negative pressure-induced buckling method to enhance the soft gripper's ability to perceive minute surface textures. Inspired by slow adapting (SA) receptors and fast adapting (FA) receptors of human fingers, this study designs a capacitive curvature sensor (CS) and a triboelectric texture sensor (TS) to detect the size, material, and texture of objects. Furthermore, a non-contact medium identification sensor (MIS), having a sensitivity of more than 1300 times higher compared to the traditional MISs, is fabricated using the principle of electromagnetic resonance. It is shown that by employing a deep learning-based multi-channel feature fusion network, the soft grasping system with multimodal sensing can achieve an object recognition accuracy of 98.43%. This work provides an innovative approach for the application of soft robots in various fields, such as logistics sorting and food safety. © 2024, The Authors. All rights reserved.

关键词： Textures

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：