检索结果-内蒙古大学图书馆

Deep Learning-based Moving Object Segmentation:Recent Progress and Research Prospects

Machine Intelligence Research 2023年第3期20卷 335-369页

作者： Rui Jiang Ruixiang Zhu Hu Su Yinlin Li Yuan Xie Wei Zou College of Information Engineering Shanghai Maritime UniversityShanghai201306China School of Computer Science and Technology East China Normal UniversityShanghai200062China Research Center of Precision Sensing and Control Institute of AutomationChinese Academy of SciencesBeijing100190China State Key Laboratory for Management and Control of Complex Systems Institute of AutomationChinese Academy of SciencesBeijing100190China

Moving object segmentation(MOS),aiming at segmenting moving objects from video frames,is an important and challenging task in computer vision and with various *** the development of deep learning(DL),MOS has also entered the era of deep models toward spatiotemporal feature *** paper aims to provide the latest review of recent DL-based MOS methods proposed during the past three ***,we present a more up-to-date categorization based on model characteristics,then compare and discuss each category from feature learning(FL),and model training and evaluation *** FL,the methods reviewed are divided into three types:spatial FL,temporal FL,and spatiotemporal FL,then analyzed from input and model architectures aspects,three input types,and four typical preprocessing subnetworks are *** terms of training,we discuss ideas for enhancing model *** terms of evaluation,based on a previous categorization of scene dependent evaluation and scene independent evaluation,and combined with whether used videos are recorded with static or moving cameras,we further provide four subdivided evaluation setups and analyze that of reviewed *** also show performance comparisons of some reviewed MOS methods and analyze the advantages and disadvantages of reviewed MOS methods in terms of ***,based on the above comparisons and discussions,we present research prospects and future directions.

关键词： Moving object segmentation(MOS) change detection background subtraction deep learning(DL) video understanding

来源：评论

学校读者我要写书评

暂无评论

Efficient Autonomous Exploration of Unknown Environment Using Regions Segmentation and VRP 1

引用

16th International Conference on Intelligent Robotics and Applications, ICIRA 2023

作者： Xue, Chaoyu Zhao, Tianhao Xie, Anhuan Zhu, Qiuguo Wu, Jun Xiong, Rong College of Control Science and Engineering Zhejiang University Hangzhou China Polytechnic Institute Zhejiang University Hangzhou China Zhejiang Lab Hangzhou China State Key Laboratory of Industrial Control and Technology Zhejiang University Hangzhou China

ISBN: (数字)9789819964987

ISBN: (纸本)9789819964970

Autonomous exploration of unknown environments is a critical application scenario in robotics. However, existing studies have strived to generate an efficient tour plan that enables the robots to fully explore the environment. This is due to the greedy strategies and the lack of utilizing the information of the unexplored area. To address the above issues, we propose a new exploration strategy. Our approach involves partitioning the unexplored area into distinct regions and utilizing their estimated workload and spatial structure to construct a region graph. Subsequently, a VRP (Vehicle Routing Problem) planner allocates regions to robots and generates a global tour for each robot in a coordinated manner, which is then refined and provided to the robot’s navigation module. Experimental results demonstrate that that our method outperforms existing approaches in terms of exploration speed, total distance, and overlap ratio. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2023.

关键词： Robots

来源：评论

学校读者我要写书评

暂无评论

Novel vision-LiDAR fusion framework for human action recognition based on dynamic lateral connection

引用

IET cyber-systems and Robotics 2024年第4期6卷 21-31页

作者： Fei Yan Guangyao Jin Zheng Mu Shouxing Zhang Yinghao Cai Tao Lu Yan Zhuang The School of Control Science and Engineering Dalian University of TechnologyDalianChina Technology Centre of Dalian Customs Dalian CustomsDalianChina ZX‐YZ School of Network Science Haikou University of EconomicsHainanChina The State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of AutomationChinese Academy of SciencesBeijingChina

In the past decades,substantial progress has been made in human action ***,most existing studies and datasets for human action recognition utilise still images or videos as the primary ***-based approaches can be easily impacted by adverse environmental *** this paper,the authors propose combining RGB images and point clouds from LiDAR sensors for human action recognition.A dynamic lateral convolutional network(DLCN)is proposed to fuse features from *** RGB features and the geometric information from the point clouds closely interact with each other in the DLCN,which is complementary in action *** experimental results on the JRDB-Act dataset demonstrate that the proposed DLCN outperforms the state-of-the-art approaches of human action *** authors show the potential of the proposed DLCN in various complex scenarios,which is highly valuable in real-world applications.

关键词： neural network-based pedestrian identification sensor fusion

来源：评论

学校读者我要写书评

暂无评论

On extended state Kalman filter-based identification algorithm for aerodynamic parameters

引用

control Theory and technology 2024年第2期22卷 235-243页

作者： Wenyan Bai Ruizhe Jia Peng Yu Wenchao Xue Beijing Aerospace Automatic Control Institute Beijing100854China School of Automation and Electrical Engineering University of Science and Technology BeijingBeijing100083China Key Laboratory of Knowledge Automation for Industrial Processes Ministry of EducationBeijing100083China Key Laboratory of Systems and Control Institute of Systems ScienceAcademy of Mathematics and Systems ScienceChinese Academy of SciencesBeijing100190China

In this paper, the problem of time-varying aerodynamic parameters identification under measurement noises is studied. By analyzing the key aerodynamic parameters that affect the aircraft control system, a system model with extended states for identifying equivalent aerodynamic parameters is established, and error parameters are extended to the system state, avoiding the difficulty caused by the unknown dynamic in the system. Furthermore, an identification algorithm based on extended state Kalman filter is designed, and it is proved that the algorithm has quasi-consistency, thus, the estimation error can be evaluated in real time. Finally, the simulation results under typical flight scenarios show that the designed algorithm can accurately identify aerodynamic parameters, and has desired convergence speed and convergence precision.

关键词： Aerodynamic parameters Parameter identification Extended state Kalman filter

来源：评论

学校读者我要写书评

暂无评论

TCPP: A Benchmark Platform for Traffic Congestion Prediction with Multi-Source Auxiliary Data

TCPP: A Benchmark Platform for Traffic Congestion Prediction...

引用

Chinese Automation Congress (CAC)

作者： Yusong Zhou Xinmin Zhang Xiaoyu Jiang Zhihuan Song State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Zhejiang University Zhejiang China Huzhou Institute of Industrial Control Technology Huzhou Zhejiang China

ISBN: (数字)9798350368604

ISBN: (纸本)9798350368611

With rapid urbanization, traffic congestion has become a challenge to efficient urban transportation. To address this challenge, we develop a novel traffic congestion prediction platform (TCPP) which is a unified benchmark tool for traffic congestion prediction with multi-source auxiliary data. By combining data integration, model selection and evaluation modules, TCPP provides a standardized framework for researchers to compare and evaluate different models and datasets. Meanwhile, through a comprehensive and detailed configuration syntax, TCPP allows users to flexibly schedule tasks and execute multiple tasks continuously and uninterruptedly. In addition, two datasets collected from California highways are enriched with multi-source weather data and temporal features. We evaluate the performance of TCPP on these two datasets and demonstrate its effectiveness in predicting traffic congestion. The results demonstrate that TCPP can contribute to future research on traffic congestion prediction and the development of intelligent transportation systems and urban traffic management.

关键词： Schedules Diversity reception Data integration Predictive models Benchmark testing Syntactics Data models Forecasting Traffic congestion Meteorology

来源：评论

学校读者我要写书评

暂无评论

Protection of Access Pattern 7

Protection of Access Pattern

引用

7th International Conference on Computer Science and Artificial Intelligence, CSAI 2023

作者： Gao, Biao Jia, Shijie Yin, Peng Zhang, Xueying State Key Laboratory of Information Security Institute of Information Engineering Cas School of Cyber Security University of Chinese Academy of Sciences Beijing China Defence Industry Secrecy Examination and Certification Center School of Cyber Security University of Chinese Academy of Sciences Beijing China China Industrial Control Systems Cyber Emergency Response Team Beijing China

ISBN: (纸本)9798400708688

Encryption is insufficient to ensure the system security because the access patterns of user will still reflect the information about the data and serve as an indicator for adversary to infer the sensitive information. We conclude the related work on the access pattern protection to provide a thorough literature review of history independence and oblivious random access machine, which address the issues of static and dynamic access pattern observations respectively. © 2023 Owner/Author.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Efficient photocatalytic NADH regeneration with Rh-loaded Z-scheme mediator-free system

引用

Chinese Chemical Letters 2024年第2期35卷 496-500页

作者： Yi Zhou Yiling He Ming Gao Ningkai Ding Juying Lei Yanbo Zhou State Environmental Protection Key Laboratory of Environmental Risk Assessment and Control on Chemical Process East China University of Science and TechnologyShanghai 200237China National Engineering Research Center of Industrial Wastewater Detoxication and Resource Recovery East China University of Science and TechnologyShanghai 200237China Shanghai Engineering Research Center for Multi-media Environmental Catalysis and Resource Utilization East China University of Science and TechnologyShanghai 200237China Shanghai Institute of Pollution Control and Ecological Security Shanghai 200092China

Nicotinamide adenine dinucleotide(NADH)regeneration is necessary for the sustainable application of enzymatic *** Rh-based complex[Cp^(*)Rh(bpy)(H)]+has been widely used as an important mediator in NADH regeneration systems,but it is limited by complexity and high ***,a Z-scheme was constructed by loading Rh onto carbon nitride nanosheets/carbon nitride quantum dots(CN-CNQD).The resultant catalyst achieved a high yield of NADH in a mediator-free(M-free)system of 0.283 mmol L^(−1) g^(−1) min^(−1),which is 5.29 times that of pure *** enzyme introduction experiments confirmed that the enzyme active product 1,4-NADH could reach 34.21%selectivity in the M-free *** research revealed that the heterojunction between CNs and CNQDs improved the NADH regeneration activity in the traditional M-involved system,while Rh loading was proved to optimize the yield and selectivity of 1,4-NADH in M-free *** immobilized Rh shows more competitiveness than[Cp^(*)Rh(bpy)(H)]^(+).This study contributes to the construction of an M-free system for further application in greener,lower-cost enzymatic processes.

关键词： Photocatalysis NADH regeneration Mediator-free Carbon nitride Z-scheme

来源：评论

学校读者我要写书评

暂无评论

Real-World Experiments on Acoustic Detection of Small UAVs 3rd

Real-World Experiments on Acoustic Detection of Small UAVs

引用

3rd International Conference on Autonomous Unmanned systems, ICAUS 2023

作者： Xu, Mengdie Wang, Xiaofeng Yao, Chenxi Yang, Chaoqun School of Automation Southeast University Nanjing China State Key Laboratory of Industrial Control Technology Zhejiang University Hangzhou China Nanjing Research Institute of Electronics Technology Nanjing China Houzz Company Palo Alto United States

ISBN: (纸本)9789819710904

This paper presents the real-world experiments on the acoustic detection of small unmanned aerial vehicles (UAVs). To achieve the accurate detection of the small UAVs, a series of data processing steps including harmonics extraction, feature extraction, and support vector machine are carried out. After that, experimental results demonstrate that the small UAVs such as DJI Phantom 4 pro can be detected accurately by using acoustic sensors. © Beijing HIWING Scientific and Technological Information institute 2024.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Semi-asynchronous personalized federated learning for short-term photovoltaic power forecasting

引用

Digital Communications and Networks 2023年第5期9卷 1221-1229页

作者： Weishan Zhang Xiao Chen Ke He Leiming Chen Liang Xu Xiao Wang Su Yang College of Computer Science and Technology China University of Petroleum(East China)China Sichuan Energy Internet Research Institute Tsinghua UniversityChina School of Computer and Communication Engineering Beijing University of Science and TechnologyChina State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of SciencesBeijingChina School of Computer Science Fudan UniversityChina

Accurate forecasting for photovoltaic power generation is one of the key enablers for the integration of solar photovoltaic systems into power *** deep-learning-based methods can perform well if there are sufficient training data and enough computational ***,there are challenges in building models through centralized shared data due to data privacy concerns and industry *** learning is a new distributed machine learning approach which enables training models across edge devices while data reside *** this paper,we propose an efficient semi-asynchronous federated learning framework for short-term solar power forecasting and evaluate the framework performance using a CNN-LSTM *** design a personalization technique and a semi-asynchronous aggregation strategy to improve the efficiency of the proposed federated forecasting *** evaluations using a real-world dataset demonstrate that the federated models can achieve significantly higher forecasting performance than fully local models while protecting data privacy,and the proposed semi-asynchronous aggregation and the personalization technique can make the forecasting framework more robust in real-world scenarios.

关键词： Photovoltaic power forecasting Federated learning Edge computing CNN-LSTM

来源：评论

学校读者我要写书评

暂无评论

Improved material descriptors for bulk modulus in intermetallic compounds via machine learning

引用

Rare Metals 2023年第7期42卷 2396-2405页

作者： De-Xin Zhu Kun-Ming Pan Yuan Wu Xiao-Ye Zhou Xiang-Yue Li Yong-Peng Ren Sai-Ru Shi Hua Yu Shi-Zhong Wei Hong-Hui Wu Xu-Sheng Yang National Joint Engineering Research Center for Abrasion Control and Molding of Metal Materials Henan Key Laboratory of High-Temperature Structural and Functional MaterialsHenan University of Science and TechnologyLuoyang471003China Longmen Laboratory Luoyang471003China State Key Laboratory for Advanced Metals and Materials University of Science and Technology BeijingBeijing100083China Guangdong Province Key Laboratory of Durability for Marine Civil Engineering School of Civil EngineeringShenzhen UniversityShenzhen518060China Department of Industrial and Systems Engineering The Hong Kong Polytechnic UniversityHong Kong999077China

Bulk modulus is an important mechanical property in the optimal design and selection of intermetallic *** this study,bulk modulus datasets of intermetallic compounds were collected,and the features affecting the bulk modulus of intermetallics were screened via feature *** features B_(cal),dB_(avg),and TIE(corresponding to calculated bulk modulus,mean bulk modulus,and third ionization energy,respectively)were found to be the dominant factors influencing bulk modulus and can be extended to other multi-component ***,we predicted the bulk modulus with an accuracy of 95%using surrogate machine learning models with the selected features,and these features were also demonstrated to be effective for high-entropy ***,symbolic regression provided an expression for the relationship between bulk modulus and the screened *** machine learning models provide a new approach for optimizing and predicting the bulk moduli of intermetallic compounds.

关键词： Bulk modulus Intermetallic compounds Machine learning Symbolic regression

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：