检索结果-内蒙古大学图书馆

11th International Conference on Computing and Pattern Recognition, ICCPR 2022

作者： Qu, Zonghua Wei, Chunling Yan, Han Beijing Institute of Control Engineering Science and Technology on Space Intelligent Control Laboratory China

ISBN: (纸本)9781450397056

Facing the increasingly crowded orbital space and the gradually increasing space threats, more attention needs to be paid to spacecraft safety in space. In order to address the problem of non-cooperative spacecraft's approach interference to our spacecraft, the process of non-cooperative spacecraft's approach to our spacecraft by using Hohmann transfer is given by Satellite Tool Kit (STK) software, and the whole process of spacecraft's abnormal orbital maneuvering to approach our spacecraft is identified and judged by the method based on long short-term memory (LSTM) network. The simulation verifies that the LSTM network achieves good results. © 2022 ACM.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Design of Wide Stopband and High Suppression Cavity Filter 24

Design of Wide Stopband and High Suppression Cavity Filter

引用

24th International Vacuum Electronics Conference, IVEC 2023

作者： Zhao, Junyu Ma, Chunguang Zhou, Jinghan Li, Junhui Liu, Jiaming Luo, Yong School of Electronic Science and Engineering University of Electronic Science and Technology of China Chengdu611731 China State Key Laboratory of Electromagnetic Space Cognition and Intelligent Control Technology Beijing100089 China

ISBN: (纸本)9781665473217

Radio frequency filter is the core device to improve the signal to noise ratio of radar. A cavity filter for suppressing high harmonics in Ka band millimeter wave (MMW) radar is presented. The structural parameters of the filter are obtained by theoretical calculation. A cavity filter with the center frequency of 8.1 GHz and the relative bandwidth of 9.80% is designed by using HFSS electromagnetic simulation software. The spurious passband is above twice the frequency of the center frequency. The attenuation of the stopband is greater than 78 dB in 9.2 16 GHz, which can well meet the demand of the need of Ka band MMW radar to suppress high harmonics. © 2023 IEEE.

关键词： Electromagnetic simulation

来源：评论

学校读者我要写书评

暂无评论

A radiation–temperature coupling model of the optical fiber attenuation spectrum in the Ge/P co-doped fiber

引用

Chinese Physics B 2022年第7期31卷 361-365页

作者： Yong Li Haoshi Zhang Xiaowei Wang Jing Jin School of Instrument Science and Optic-electronics Engineering Beihang UniversityBeijing 100191China Beijing Institute of Control Engineering Beijing 100094China Science and Technology on Space Intelligent Control Laboratory Beijing 100094China

A radiation–temperature coupling model of optical fiber attenuation spectrum has been *** spectrum in Ge/P co-doped fiber ranging from 800 nm–1600 nm at different temperatures and doses was measured and decomposed according to the configurational coordinate model based on which the power-law model was employed to predict the intensity of the color center absorption band at different *** the fiber loss in space was predicted by the *** work will benefit the application of fibers in a complicated radiation environment.

关键词： radiation temperature color centers optical fiber

来源：评论

学校读者我要写书评

暂无评论

A lightweight object detection network based on YOLOv5 for SAR image 2

A lightweight object detection network based on YOLOv5 for S...

引用

2nd IEEE International Conference on Signal, Information and Data Processing, ICSIDP 2024

作者： Shen, Aijia Zhao, Liangbo Xu, Fanyun Wang, Guoqing Liu, Wenchao Shen, Zimeng Beijing Institute of Technology National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Beijing China Institute of Remote Sensing Satellite China Academy of Space Technology Beijing China

ISBN: (纸本)9798331515669

Remote sensing image target detection is one of the key technologies in the field of intelligent interpretation of remote sensing images, and it has significant application value in various areas, including military defense. When performing remote sensing image object detection on airborne and spaceborne platforms, the vast amount of remote sensing data processing and limited computational resources impose high real-time requirements on the object detection algorithms. This paper designs a lightweight object detection network model named YOLOv5-tiny, based on the existing deep learning network detection model YOLOv5s, and deploys it on the Jetson TX2 development board for training and testing. Experimental results show that the proposed YOLOv5-tiny model, when tested on the SAR-AIRcraft-1.0 with an input image size of 640x640, is 10 times smaller than YOLOv5s;it has a computational cost of 5.2 GFLOPs, which is 1/5 of YOLOv5s, and the processing time for a single image is reduced to half that of YOLOv5s, with only a 0.1% decrease in accuracy. © 2024 IEEE.

关键词： Object tracking

来源：评论

学校读者我要写书评

暂无评论

Global Information Edge Augmentation Network for Remote Sensing Image Continuous Super-Resolution 2

Global Information Edge Augmentation Network for Remote Sens...

引用

2nd IEEE International Conference on Signal, Information and Data Processing, ICSIDP 2024

作者： Gao, Shize Lei, Yong Zhang, Jingya Wang, Guoqing Liu, Wenchao Beijing Institute of Technology National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Beijing China China Academy of Space Technology Institute of Remote Sensing Satellite Beijing China

ISBN: (纸本)9798331515669

The continuous-scale super-resolution (SR) method for remote sensing (RS) images has the potential to achieve flexible scale SR with a single network, representing a significant research area in the field of RS. However, the majority of prevailing methods learn features from localization, thereby neglecting the global semantic coherence of RS images. This results in unbalanced SR outcomes. Furthermore, the optimization strategy based on the multilayer perceptron (MLP) utilized in the implicit neural representation (INR) method results in blurred reconstructed image edges. To address these issues, a novel continuous-scale SR method for RS images, a global information edge augmentation network (GIEAN), is proposed. Initially, the global state space model (GSSM) aggregates the global information of the image from diverse perspectives and learns the contextual interactions at disparate locations of the image globally. Subsequently, the dual edge enhancement module (DEEM) learns the image body and edges independently through the main branch and edge branch, respectively, with the objective of enhancing the edge component of the SR results. Extensive experimental evaluation on the UCMerced dataset demonstrates the superiority of GIEAN over existing continuous-scale SR techniques. © 2024 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Cross-Domain Detection Transformer with Multi-view Adaptive Feature Alignment in Remote Sensing Imagery 2

Cross-Domain Detection Transformer with Multi-view Adaptive ...

引用

2nd IEEE International Conference on Signal, Information and Data Processing, ICSIDP 2024

作者： Wang, Shu Han, Jianhong Wang, Ying Hao, Xinyuan Luo, Zhaoyi Wang, Yupei Chen, Liang Beijing Institute of Technology National Key Laboratory for Science and Technology on Space-Born Intelligent Information Processing Beijing China Shanghai Academy of Spaceflight Technology Shanghai China

ISBN: (纸本)9798331515669

Unsupervised Domain Adaptation (UDA) techniques are crucial for remote sensing object detection, designed to address performance degradation caused by the domain gap between training and test data. These methods leverage unlabeled target domain data, thus alleviating the high costs associated with data annotation. Recent developments in Detection Transformers (DETR) have simplified the detection pipeline and attracted significant research interest. Building on this architecture, we introduce an unsupervised domain adaptation detector for remote sensing object detection. Specifically, we introduce a multi-view adaptive feature alignment module that initially captures domain-specific features in complex backgrounds by leveraging a cross-attention mechanism. Subsequently, we employ contrastive learning to enforce the aggregation of domain-specific features from various perspectives, thereby improving the accuracy of feature alignment. Moreover, we demonstrate that integrating the self-training framework into DETR-based detectors can significantly mitigate the domain gap by further utilizing unlabeled data in the target domain. We validated the effectiveness and generalizability of our method across two remote sensing cross-domain detection scenarios using four public datasets. © 2024 IEEE.

关键词： object detection remote sensing imagery Unsupervised domain adaptation

来源：评论

学校读者我要写书评

暂无评论

Motion Path Planning of Agent Based on Proximal Policy Optimization Algorithm 5

Motion Path Planning of Agent Based on Proximal Policy Optim...

引用

5th International Conference on Industrial Artificial Intelligence, IAI 2023

作者： Wang, Jiangtao Sun, Zewen Li, Peng Sun, Liang University of Science and Technology Key Laboratory of Intelligent Bionic Unmanned Systems of Ministry of Education School of Intelligent Science and Technology Beijing100083 China University of Science and Technology Beijing Key Laboratory of Urban Underground Space Engineering Beijing100083 China

ISBN: (纸本)9798350325294

Aiming at the problems of insufficient intelligence level, computational complexity, and lack of autonomous learning capability of traditional path planning algorithms, this paper proposes a solution for implementing the motion path planning of agent using proximal policy optimization algorithm based on deep reinforcement learning. The solution can provide a universal method for the path planning of agent moving in a two-dimensional plane, which splits the task into two subtasks: path generation and path tracking, where the agent generates a feasible path based on proximal policy optimization algorithm, and the path tracking task can be implemented by a traditional control algorithm. Finally, the proposed algorithm is simulated and verified in training and testing environments. The results show that the proposed algorithm can effectively complete the path generation task, and the proximal policy optimization algorithm has advantages over the A∗ algorithm in terms of intelligence level and environmental adaptability. Furthermore, the algorithm is generalizable to all movable objects. © 2023 IEEE.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Combine deep learning and Bayesian analysis to separate overlapping gravitational wave signals

引用

science China(Physics,Mechanics & Astronomy) 2025年第5期68卷 205-219页

作者： Cunliang Ma Weiguang Zhou Zhoujian Cao Mingzhen Jia Jiangxi Provincial Key Laboratory of Multidimensional Intelligent Perception and Control Jiangxi University of Science and TechnologyGanzhou 341000China Institute of Applied Mathematics Academy of Mathematics and Systems ScienceChinese Academy of SciencesBeijing 100190China School of Fundamental Physics and Mathematical Sciences Hangzhou Institute for Advanced StudyUCASHangzhou 310024China

Future gravitational wave(GW)observatories,such as the Einstein Telescope,are anticipated to encounter overlapping GW signals,presenting considerable obstacles to GW data processing techniques,including signal identification and parameter *** this letter,we propose a scheme of combining deep learning and Bayesian analysis to disentangle overlapping GW *** deep learning part takes a data-driven approach that employs an encoder-separation-decoder framework which is powerful enough to extract the shape of the signal even when the GW signals completely *** Bayesian analysis part takes the matched filtering technique to extract the amplitude of the GW *** scheme can facilitate the utilization of existing GW detection and parameter estimation methods for future instances of overlapping *** methodology effectively reduces biases in parameter estimation when handling multiple intertwined ***,this marks the first known instance where deep learning has been successfully utilized to disentangle overlapping GW signals.

关键词： gravitational wave separation machine learning Einstein Telescope parameter estimation

来源：评论

学校读者我要写书评

暂无评论

A Fast X-ray Pulsar Time Delay Estimation Method Based on Bispectral Feature Points and Cross-Correlation 42

A Fast X-ray Pulsar Time Delay Estimation Method Based on Bi...

引用

42nd Chinese control Conference, CCC 2023

作者： Huang, Zhiwei Zong, Hua Xu, Qian Li, Xiaomin Beijing Aerospace Automatic Control Institute National Key Laboratory of Science and Technology on Aerospace Intelligent Control Beijing100854 China

ISBN: (纸本)9789887581543

In order to improve the accuracy and real-time performance of X-ray pulsar time delay estimation over short-time observation interval, a method based on bispectral feature points and cross-correlation is proposed in this paper. Firstly, calculate the self-bispectrum of the standard pulsar profile, extract the bispectral feature points by PSO algorithm, and store it in the spacecraft. Secondly, the pulsar photons are received in real-time and get the observation profile by epoch folding. Thirdly, calculate the cross-bispectrum at the bispectral feature points, construct the objective function of time delay estimation, and solve the extremum. Finally, the pulsar time delay estimation is obtained by screening the extreme points using cross-correlation. Simulation experiments based on Insight-HXMT observations of the Crab pulsar show that, the average running time of the proposed algorithm is 41.59ms on Matlab R2017b, and the average estimation error at observation interval below 2.5s is 0.1858ms, which is better than the traditional bispectrum method and the selected bispectrum method. © 2023 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Pulsars

来源：评论

学校读者我要写书评

暂无评论

Prototype-Guided Representation Distribution Optimization for Change Detection in High-Resolution Remote Sensing Imagery 2

Prototype-Guided Representation Distribution Optimization fo...

引用

2nd IEEE International Conference on Signal, Information and Data Processing, ICSIDP 2024

作者： Wang, Guoqing Chen, He Wei, Xin Shi, Junqing Chen, Liang Liu, Wenchao Beijing Institute of Technology National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Beijing China China Academy of Space Technology Institute of Remote Sensing Satellite Beijing China

ISBN: (纸本)9798331515669

Change detection is the process of automatically extracting change areas from bi-temporal remote sensing images. The key of deep learning-based change detection methods is to extract features that represent changes/non-changes. Most of the existing methods only enhance the representation ability of the changed regions through the model architecture design, but lack further constraints in the representation space. This paper introduces a prototype-guided representation distribution optimization method. By comparing pixel features with prototypes, confusing pixels can be determined, and these pixels are adaptively weighted during learning, so that similar representations are closer and different representations are farther apart. In addition, the representation distribution is also applied as transferred knowledge to knowledge distillation for lightweight CD model. Experimental results on two public datasets show the effectiveness of the proposed method. © 2024 IEEE.

关键词： Change detection

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：