检索结果-内蒙古大学图书馆

SPIE 12th International Symposium on Multispectral Image Processing and Pattern Recognition, MIPPR 2023

作者： Huang, Shixiang Chi, Longyun Fu, Wenxing Tian, Jinwen National Key Laboratory of Multispectral Information Intelligent Processing Technology Huazhong University of Science and Technology Wuhan China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing China

ISBN: (数字)9781510674943

ISBN: (纸本)9781510674936

As a crucial auxiliary technique in inertial navigation, scene matching has been widely applied in aircraft navigation and guidance. To enhance the adaptability and efficiency of scene matching algorithms in complex environments, existing approaches have gradually shifted towards heterogeneous scene matching, such as optical/ infrared scene matching based on deep learning features, with a focus on point features. However, due to the complex and diverse nonlinear distortions between optical and infrared images, the matching accuracy often fails to meet the practical requirements of navigation and positioning. In view of this problem, an EPM-Net algorithm based on edge features is proposed to improve matching performance by extracting more stable and discriminative edge point descriptors. Experimental results on infrared datasets demonstrate that this method achieves an average matching accuracy improvement of more than four times compared to traditional and existing deep learning methods. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Polyphonic sound event localization and detection based on Multiple Attention Fusion ResNet

引用

Mathematical Biosciences and Engineering 2024年第2期21卷 2004-2023页

作者： Zhang, Shouming Zhang, Yaling Liao, Yixiao Pang, Kunkun Wan, Zhiyong Zhou, Songbin Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming650500 China Institute of Intelligent Manufacturing Guangdong Academy of Science Guangdong Key Laboratory of Modern Control Technology Guangzhou510030 China

Sound event localization and detection have been applied in various fields. Due to the polyphony and noise interference, it becomes challenging to accurately predict the sound event and their occurrence locations. Aiming at this problem, we propose a Multiple Attention Fusion ResNet, which uses ResNet34 as the base network. Given the situation that the sound duration is not fixed, and there are multiple polyphonic and noise, we introduce the Gated Channel Transform to enhance the residual basic block. This enables the model to capture contextual information, evaluate channel weights, and reduce the interference caused by polyphony and noise. Furthermore, Split Attention is introduced to the model for capturing cross-channel information, which enhances the ability to distinguish the polyphony. Finally, Coordinate Attention is introduced to the model so that the model can focus on both the channel information and spatial location information of sound events. Experiments were conducted on two different datasets, TAU-NIGENS Spatial Sound Events 2020, and TAU-NIGENS Spatial Sound Events 2021. The results demonstrate that the proposed model significantly outperforms state-of-the-art methods under multiple polyphonic and noise-directional interference environments and it achieves competitive performance under a single polyphonic environment. ©2024 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

A 2-18 GHz 8-W Distributed GaN Power Amplifier Based on Input and Output Matching Network 15

A 2-18 GHz 8-W Distributed GaN Power Amplifier Based on Inpu...

引用

15th International Conference on Microwave and Millimeter Wave technology, ICMMT 2023

作者： Pu, Ziqi Zhu, Xu Qi, Liang Wang, Yong Chi, Pei-Ling Yang, Tao University of Electronic Science and Technology of China Chengdu China Laboratory of Electromagnetic Space Cognition and Intelligent Control Technology Beijing100191 China

ISBN: (纸本)9798350338874

A high efficiency non-uniform distributed power amplifier (NDPA) based on a 0.15 μm Gallium Nitride (GaN) HEMT process is proposed. The amplifier contains eight amplification cells and uses artificial transmission line theory to design the drain transmission line with decreasing characteristic impedance. To improve the efficiency of the amplifier, the amplifier is class AB biased and designed for optimum impedance matching using the matching networks. The electromagnetic simulation results of the designed amplifier show that the small signal gain of the amplifier is more than 12.6 dB and the saturated output power (Psat) is more than 39.1 dBm with power-added efficiency (PAE) of larger than 28.5% in the frequency range of 2-18 GHz. The core area of the chip is 3.0×1.8 mm2 © 2023 IEEE.

关键词： Power amplifiers

来源：评论

学校读者我要写书评

暂无评论

Low-Light Image Enhancement Method for Consistency Judgment of Multi-view Multi-target for UAV Swarm 7th

Low-Light Image Enhancement Method for Consistency Judgment ...

引用

7th Chinese Conference on Swarm Intelligence and Cooperative control, CCSICC 2023

作者： Li, WeiXue Song, Chuang Hao, MingRui Zhang, Hang Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing100074 China

ISBN: (纸本)9789819733392

To address the challenges posed by low-light images in multi-drone detection tasks, which lead to significant differences in target image features across different perspectives and poor accuracy in target association under multiple viewpoints, this paper proposes an enhanced network architecture based on MIRNet for low-light image enhancement. The goal is to improve the stability of target features in multi-view scenarios. By incorporating Sobel convolution to capture target edges and texture features, and by designing a residual contextual block combined with an attention mechanism and a pixel loss function that emphasizes the central region, the model not only acquires richer features but also focuses more on the central region's target characteristics. Experimental results demonstrate that the proposed approach effectively enhances image brightness, contrast, and target texture, exhibiting substantial advantages in both objective and subjective evaluation metrics. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Combat Intention Recognition of Aerial Battlefield Targets Based on LSTM 3rd

Combat Intention Recognition of Aerial Battlefield Targets B...

引用

3rd International Conference on Autonomous Unmanned Systems, ICAUS 2023

作者： Xu, Hongfeng Zhao, Jiajia Zhang, Hang Jiang, Jixiang Chen, Linxiu Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing100074 China

ISBN: (纸本)9789819710867

In the course of military operations, the battlefield situation changes rapidly, and the combat time is fleeting. How to quickly and accurately identify the enemy’s combat intention is one of the important preconditions to ensure the commander’s correct command decision and obtain the initiative in the battlefield. In this paper, aiming at the problems of low accuracy and insufficient algorithm robustness of traditional target combat intention recognition methods in air battlefield, a combat intention recognition method based on LSTM is proposed according to the characteristics of sequence and multi-dimension of target characteristic data. Based on the historical and current state characteristics, electromagnetic characteristics and action characteristics of the target obtained by the sensor, the method uses the LSTM network to build the target combat intention recognition model, and learns the changes of the target characteristics through the network model to realize the target combat intention recognition. Simulation results show that the proposed method can effectively improve the accuracy of target combat intention recognition. © Beijing HIWING Scientific and Technological Information Institute 2024.

关键词： Military operations

来源：评论

学校读者我要写书评

暂无评论

A Combat Intention Reasoning Method for Warship Formation Targets Based on Deep Learning 1

引用

7th Chinese Conference on Swarm Intelligence and Cooperative control, CCSICC 2023

作者： Xu, Hongfeng Zhao, Jiajia Zhang, Hang Jiang, Jixiang Chen, Linxiu Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing100074 China

ISBN: (数字)9789819733361

ISBN: (纸本)9789819733354

With the rapid development of science and technology, modern war presents the characteristics of mathematics and information. Grasping the operational intention of battlefield targets plays a crucial role in the trend of war. The target of warship formation is an important fighting force in modern war. How to analyze and reason the target’s fighting intention accurately and timely is one of the most important parts of modern battlefield situation cognition system. Aiming at the problems of too strong subjectivity, lack of objectivity and poor model robustness existing in traditional intention reasoning methods, this paper introduces the idea of deep learning data-driven, and takes the electromagnetic, state and formation characteristic information of ship formation targets as input, designs a deep learning-based ship formation target intention reasoning model. The effectiveness of the algorithm is verified by mathematical simulation. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Review of Maneuvering Strategies in the Level Flight Section of UAV 1

引用

7th Chinese Conference on Swarm Intelligence and Cooperative control, CCSICC 2023

作者： Sun, Wendi Hao, Mingrui Science and Technology on Complex System Control and Intelligent Agent Cooperative Laboratory Beijing100074 China

ISBN: (数字)9789819733408

ISBN: (纸本)9789819733392

In view of the threat of the anti-missile defense system, this paper summarized the maneuver penetration strategies of the UAV in the level flight phase, in consideration of the flight ability and technological development of the aircraft. The basic ideas, advantages and disadvantages of each penetration strategy, the future development trend of mobile penetration technology and new research ideas are discussed in this paper. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Knowledge mapping analysis of the track and hotspot of water lubrication:A scientometrics review

引用

Friction 2023年第9期11卷 1557-1591页

作者： Runzhou XU Defa WU Zhenyao WANG Yipan DENG Qian CHENG Hao PANG Wenshu WEI Yinshui LIU State Key Laboratory of Digital Manufacturing Equipment and Technology School of Mechanical Science and EngineeringHuazhong University of Science and TechnologyWuhan 430074China Beijing Tianma Intelligent Control Technology Co. Ltd.Beijing 101300China

With the enhancement of environmental protection awareness of the international community and the continuous promotion of green and sustainable development of manufacturing industry,water lubrication instead of mineral oil has become the future development trend due to its green,pollution-free,clean,safe,and sustainable advantages especially in ships,marine,coal mining,and other *** recent years,with the rapid development of water lubrication research,significant progress has been made in related research knowledge domain and discipline.A systematic and extensive assessment of water lubrication research has become increasingly *** objective of this research is to reveal the research status,research hotspots,and development trends in the field of water ***,Citespace was used to conduct a systematic bibliometric and scientometrical analysis of 1,792 publications from Web of science core collection database(1997–2021).The results show that China and USA are the most productive countries in the field of water lubrication and have made outstanding *** the analysis of hot key words and co-citation references,this paper reviews the research status of water lubrication in three aspects:(1)lubricating medium modification;(2)material preparation;(3)surface *** has become a research hotspot to promote the superlubricity contact interface and the application of *** results of this study can make a significant contribution to the development of water lubrication by providing a comprehensive understanding of the research status and research hotspots in this *** understanding and discussion of research hotspots and research status are expected to provide insights into future research *** addition,this study will provide valuable references and guidelines for researchers who are interested in this field.

关键词： water lubrication friction scientometrics Citespace

来源：评论

学校读者我要写书评

暂无评论

Relative Navigation of Unmanned Aerial Vehicles Based on Data Link Ranging and Partial Guidance Information 1

引用

7th Chinese Conference on Swarm Intelligence and Cooperative control, CCSICC 2023

作者： Wang, Ziwen Song, Chuang Hao, Mingrui Liang, Xinkai Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing100074 China

ISBN: (数字)9789819733323

ISBN: (纸本)9789819733316

In GNSS-denied environments, precise relative navigation between unmanned aerial vehicles (UAVs) is a key technology for achieving cooperative tasks. The relative navigation method based on data link ranging information combines altitude, airspeed measurements, and attitude information to ensure the observability of UAVs’ relative states. However, due to the significant constraints imposed by observability conditions, a novel approach is proposed that utilizes partial guidance information from the UAV swarm towards the target as additional measurements. This approach enhances the observability capability of relative navigation and alleviates the constraints imposed by the observability conditions. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Observability

来源：评论

学校读者我要写书评

暂无评论

Common Aircraft Formation control Methods and Application Prospects of High Order Fully Actuated System Theory in Aircraft Formation control 7th

Common Aircraft Formation Control Methods and Application Pr...

引用

7th Chinese Conference on Swarm Intelligence and Cooperative control, CCSICC 2023

作者： Liu, Xinyu Hao, Mingrui Fan, Yu Zhen, Yan Yue, Keyuan Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing100074 China

ISBN: (纸本)9789819733279

This article provides a review of formation control for multiple aircrafts. Firstly, several commonly used aircraft formation control methods were introduced, including leader-follower approach, behavior based formation control, virtual structure method, and artificial potential field method. Considering that the controller design of these methods is mostly based on first-order differential equations and state space methods or uses fuzzy theory or neural networks, further solutions are needed in issues such as model accuracy, controller anti-interference, and controller stability analysis. Therefore, this article proposes the possibility of applying high-order fully actuated (HOFA) system theory in aircraft formation control. In response to the nonlinear, coupled, and real-time aircraft formation control problems, the development of HOFA system theory is introduced, and it is pointed out that fully actuated system (FAS) method has outstanding advantages in dealing with nonlinear, time-varying, hysteresis problems. The article summarizes the current research and practice of FAS theory in the field of single aircraft control and multi-spacecraft formation control, and then propose a new idea of designing FAS formation control method for multiple aircrafts. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Aircraft

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：