检索结果-内蒙古大学图书馆

2024 International Conference on Image, Signal Processing, and Pattern Recognition, ISPP 2024

作者： Jia, Yunhua Zhou, Chengjiang Yunnan Normal University School of Information Kunming650500 China Pattern Recognition and Artificial Intelligence Laboratory Kunming650500 China

ISBN: (纸本)9781510680425

As the field of artificial intelligence progresses, multi-target tracking, one of the advanced visual tasks of computer vision, has developed *** present, as multi-target tracking technology gradually matures, related scientific research results are slowly appearing in our daily lives, bringing more powerful help to our ***, the precision of multi-target tracking faces significant constraints, mainly attributed to factors like occlusion and interference from the *** to reduce the constraints of occlusion and other factors on the accuracy of multi-target *** this paper, we propose a staged multi-target tracking and matching algorithm that combines depth estimation *** using the depth estimation information of targets in the scene, combined with the proposed staged matching algorithm improves the precision of the algorithm for multi-target tracking. © 2024 SPIE.

关键词： Detection and tracking algorithms Ablation algorithm development Data modeling Computer vision technology Sensors Video

来源：评论

学校读者我要写书评

暂无评论

Uniqueness condition for 1D signal reconstruction from power spectrum with related interference signal information

Uniqueness condition for 1D signal reconstruction from power...

引用

2024 International Conference on Optics, Electronics, and Communication Engineering, OECE 2024

作者： Tian, Yuan Pang, Yongda Li, Yuling Software School Dalian University of Technology Liaoning Dalian116620 China

ISBN: (纸本)9781510685437

Signal reconstruction from its power spectrum is an important technique widely useful in different application fields. However, uniqueness is generally hard to be guaranteed by usual approaches due to nonlinearity of the power spectrum measurement models. In this paper a very general structure of the 1-dimensonal signal with given power spectrum is established and on basis of this formulism some conditions are introduced to guarantee the uniqueness of solution in signal reconstruction. Such conditions are about the information of the interference signals and according to which an algorithm is established for signal construction. The algorithm is simple, efficient and its solution is unique in case of linear-phase signals. Some generalized and more practical conditions are also discussed. © 2024 SPIE.

关键词： Reconstruction algorithms Autocorrelation Fourier transforms Instrument modeling algorithm development Nonlinear optics Permeability Polymers Signal attenuation Materials properties

来源：评论

学校读者我要写书评

暂无评论

The BP neural network microgrid fault diagnosis method based on optimisation of pelican algorithm

The BP neural network microgrid fault diagnosis method based...

引用

2024 International Conference on Automation Control, algorithm, and Intelligent Bionics, ACAIB 2024

作者： Sun, Mingze Guo, Yanbing Hou, Yongkang Shanghai Dianji University School of Mechanical Shanghai201306 China College of Ocean Science and Engineering Institute of Marine Materials Science and Engineering Shanghai Maritime University Shanghai201306 China Shanghai Dianji University School of Business Shanghai201306 China

ISBN: (纸本)9781510682597

In this study, a fault diagnosis method combining the Pelican algorithm and BP neural network is proposed for improving the fault diagnosis accuracy and efficiency of microgrid systems. Pelican algorithm is a new optimisation algorithm developed in recent years, which can effectively optimise the weights and deviations of BP neural networks. Based on this characteristic, the Pelican algorithm is used to process the data of the actual microgrid system, and compared and analysed with the traditional BP neural network and RNF neural network. The experimental results show that the BP neural network optimised by the Pelican algorithm exhibits higher accuracy and robustness in microgrid fault diagnosis, which provides an important support for the reliability of microgrid systems. © 2024 SPIE.

关键词： Neural networks Evolutionary algorithms Mathematical optimization Data modeling Education and training algorithm development Computer simulations Detection and tracking algorithms Diagnostics

来源：评论

学校读者我要写书评

暂无评论

Research on orderly charging scheduling of new energy vehicles in airfield 9

Research on orderly charging scheduling of new energy vehicl...

引用

9th International Symposium on Sensors, Mechatronics, and Automation System, ISSMAS 2023

作者： Zhuge, Jingchang Zhang, Yiming Kang, Chunhua Shan, Xubao Wang, Shizheng Li, Xiaoxiang College of Electronic Information and Automation Civil Aviation University of China Tianjin300300 China Capital Airports Holdings Co. Ltd. Beijing Daxing International Airport Beijing102600 China

ISBN: (纸本)9781510672802

In view of the charging scheduling problem of new energy vehicles in the airfield area, the traditional disordered charging phenomenon causes the unbalanced utilization of charging piles, which makes some charging piles overloaded and cannot be applied to the safe operation of the distribution network in the airfield area. By analyzing the vehicle charging law of a domestic hub airport, with the goal of minimizing the deviation of the comprehensive utilization rate of charging piles and the minimum vehicle queuing time, a new energy vehicle charging scheduling model was established, and the particle swarm optimization algorithm was used to solve the model, and the actual charging data of the airport was compared and verified. The results showed that the algorithm could reduce the variance of the comprehensive utilization rate of charging piles by 70.4%, reduce the queuing time of vehicle charging by 59.6%, and effectively improved the safety of the airport distribution network and the operating efficiency of new energy vehicles. © 2024 SPIE.

关键词： Particle swarm optimization Particles Mathematical optimization Data modeling Computer simulations algorithm development Computer programming Efficient operations Nonlinear optimization Stochastic processes

来源：评论

学校读者我要写书评

暂无评论

Automated Global-Scale Detection and Characterization of Anthropogenic Activity using Multi-Source Satellite-Based Remote Sensing Imagery 13

Automated Global-Scale Detection and Characterization of Ant...

引用

Conference on Geospatial Informatics XIII

作者： Goldberg, Hirsh R. Ratto, Christopher R. Banerjee, Amit Kelbaugh, Michael T. Giglio, Mark Vermote, Eric F. Johns Hopkins Univ Appl Phys Lab Baltimore MD 21218 USA MITRE Corp Mclean VA USA NASA Goddard Space Flight Ctr Greenbelt MD USA

ISBN: (数字)9781510661653

ISBN: (纸本)9781510661646;9781510661653

Satellite-based remote sensing imagery is an effective means for detecting objects and structures in support of many applications. However, detecting the spatial and temporal bounds of a specific activity in satellite imagery is inherently more complex and research in this area is nascent. One reason for this is that describing an activity implies defining both spatial and temporal bounds and while activity is inherently continuous in nature, the geospatial (imagery) time series for any particular swath of ground provided by satellite imagery is relatively sparse and discrete in comparison. The IARPA Space-Based Machine Automated Recognition Technique (SMART)(1) program is the first large-scale research program to target advancing the state of the art for automatically detecting, characterizing, and monitoring large-scale anthropogenic activity in global, multi-spectral satellite imagery. The program has two primary research objectives: 1) the "harmonization" of multiple imagery sources and 2) automated reasoning at scale to detect, characterize, and monitor activities of interest. This paper provides details on the goals, dataset, metrics, and lessons learned of the IARPA SMART program. By releasing the annotated dataset, the program aims to foster additional research in this area by the community at large.

关键词： Satellites algorithm development Satellite imaging Earth observing sensors Object detection Evolutionary algorithms Machine learning

来源：评论

学校读者我要写书评

暂无评论

Uniqueness conditions for 1d signal reconstruction from power spectrum with additional data term information

Uniqueness conditions for 1d signal reconstruction from powe...

引用

2024 International Conference on Optics, Electronics, and Communication Engineering, OECE 2024

作者： Tian, Yuan Pang, Yongda Li, Yuling Software School Dalian University of Technology Liaoning Dalian116620 China

ISBN: (纸本)9781510685437

Signal reconstruction from its power spectrum is an important technique widely useful in different application fields. However, uniqueness is generally hard to be guaranteed by usual approaches due to nonlinearity of the power spectrum measurement models. In this paper a very general structure of the 1-dimensonal signal with given power spectrum is established and some conditions are introduced to guarantee the uniqueness of solution in signal reconstruction on basis of this formulism. Such conditions are about one or more additional information of the signal component and two algorithms are established for signal construction. One of the algorithms is exact and another one is iterative and approximate, both can reach the real signal under the introduced conditions. © 2024 SPIE.

关键词： Reconstruction algorithms Autocorrelation Data modeling algorithm development Fourier transforms Instrument modeling Interpolation Nonlinear optics Permeability Signal attenuation

来源：评论

学校读者我要写书评

暂无评论

A method to calculate the power-carbon emissions flow with the consideration of the full life-cycle carbon cost 9

A method to calculate the power-carbon emissions flow with t...

引用

9th International Conference on Energy Materials and Electrical Engineering, ICEMEE 2023

作者： Ye, Jichao Zhang, Hanbing Huang, Hui Hu, Xinwei Wu, Xinhua Qiu, Yi State Grid Zhejiang Electric Power Co. Ltd. Lishui Power Supply Company Lishui Zhejiang323000 China

ISBN: (纸本)9781510672765

The proposed "double carbon"target by the Chinese government underscores the importance of reducing carbon emissions in the power industry. The power industry, whose carbon emission accounts for about 43.1% of the overall energy-related carbon emissions, is one of the Chinese largest carbon-emitting industries. Calculating the carbon emissions flow in power systems helps to better reduce the use of conventional fossil fuel and complete the "double carbon"target. This paper first analyzes the full life-cycle carbon cost from the device perspective, thus setting a boundary for carbon accounting. Then the calculation method of power-carbon emissions flow is developed. Finally, the performance of the proposed method is evaluated based on the Lishui City power system. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Carbon Matrices Power consumption Systems modeling Data modeling Industry Power grids algorithm development Manufacturing Manufacturing equipment

来源：评论

学校读者我要写书评

暂无评论

Research on multi dimensional power consumption information decoupling and separation optimization algorithm based on power supply big data and time-varying characteristics of user profiles 9

Research on multi dimensional power consumption information ...

引用

9th International Conference on Energy Materials and Electrical Engineering, ICEMEE 2023

作者： Zhao, Yun Chen, Junyi Fan, Jiahao State Grid Shanghai Shibei Electric Power Supply Company Shanghai200072 China

ISBN: (纸本)9781510672765

The multi-dimensional power consumption information decoupling and separation optimization algorithm based on power supply big data and user profile is a new algorithm applied in the power field. Through the analysis of big data in the power supply system, combined with user portraits, the power consumption habits and demand characteristics of users at different times and in different scenarios are obtained. Through the analysis and extraction of time-varying characteristics, the decoupling and separation of multi-dimensional power consumption information is realized, so as to better understand the impact of different factors on power consumption behavior. The advantage of this algorithm is that it can provide refined electricity consumption data and analysis results, thereby providing more intelligent and personalized services for power operators and users. By decoupling and separating multidimensional electricity consumption information, it is possible to gain a deeper understanding of users' electricity consumption behavior and needs, providing effective reference and support for the planning, operation, and management of power supply systems. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Power consumption Power supplies Mathematical optimization Feature extraction algorithm development Covariance matrices Data processing Industry Information security Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Cell-based hybrid adaptive mesh refinement algorithm for immersed boundary method

引用

INTERNATIONAL JOURNAL FOR NUMERICAL METHODS IN FLUIDS 2022年第3期94卷 272-294页

作者： Saravanan, Vignesh Choung, Hanahchim Lee, Soogab Seoul Natl Univ Dept Aerosp Engn Gwanak Ro 1 Seoul South Korea Seoul Natl Univ Inst Engn Res Seoul South Korea

This article proposes a hybrid adaptive mesh refinement (AMR) algorithm for the immersed boundary method (IBM) combination, and the AMR code is split into mesh and physics codes to optimize each part individually. The uniform parent grid solver is used for AMR grids by constructing hanging cells for the high-order extension. The restrictive spatial refinement in a fully threaded tree (FTT) data structure is explored, and a simplified stencil search algorithm for hanging cells construction is introduced, including current and following child AMR level cells, if any. The proposed AMR method was applied to IBM, which offers flexibility in treating complex geometries in the Cartesian grid, leading to algorithmic simplicity and computational efficiency. Local near immersed boundary refinement is proposed to avoid complex and computationally expensive IBM and AMR algorithms near the solid bodies. Finally, a high-order flux scheme extension at AMR level transition cells and the proposed method's applicability for steady and transient flows are demonstrated. Besides state and flux variables storage, the proposed hybrid AMR method's additional cost is 4.5 words/cell instead of 3.5 words/cell for 2D and 3.75 words/cell instead of 2.75 words/cell for 3D compared to the conventional FTT-based AMR method. By comparing the uniform grid, the AMR final grid distribution shows that the optimal cell distribution based on flow physics reduces the cells required by more than 40% to resolve the complex flow features in less computational time. The enhanced performance and accuracy of the proposed AMR method in resolving different scale flow features are validated through benchmark problems.

关键词： algorithm development cell-based data structure high-order extension hybrid adaptive mesh refinement immersed boundary method steady transient flow

来源：评论

学校读者我要写书评

暂无评论

Research on 3D point cloud registration algorithm based on FPFH and ColorICP

Research on 3D point cloud registration algorithm based on F...

引用

2024 International Conference on Optical and Photonic Engineering, icOPEN 2024

作者： Pan, Junjie Zhang, Xu School of Mechatronic Engineering and Automation Shanghai University Shanghai China

ISBN: (数字)9781510688117

ISBN: (纸本)9781510688100

With the rapid development of 3D reconstruction, point cloud registration technology, a key step in 3D data processing, has garnered significant attention. Existing 3D point cloud registration technologies face issues such as low matching rates in coarse registration, misidentification of feature points, lengthy registration times, and low registration accuracy. Consequently, an improved registration algorithm that combines Fast Point Feature Histogram (FPFH) for coarse registration and Colored Iterative Closest Point (ColorICP) for fine registration has been proposed. The process begins with pre-processing the point cloud through downsampling filtration;next, point cloud features are extracted using FPFH to achieve feature matching and obtain the initial transformation matrix;finally, ColorICP is used for fine point cloud registration. Experiments on the Stanford bunny dataset from the standard point cloud library and real-world point cloud data demonstrate that the proposed registration algorithm effectively utilizes both color and geometric features of the point cloud, achieving significant improvements in registration accuracy and duration compared to traditional registration algorithms. © 2025 SPIE.

关键词： Point clouds Image registration Histograms Detection and tracking algorithms Reconstruction algorithms Nondestructive evaluation Picosecond phenomena Cameras RGB color model algorithm development

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：