检索结果-内蒙古大学图书馆

Multi-Channel Based on Attention Network for Infrared Small Target Detection

Journal of Shanghai Jiaotong university(science) 2024年第3期29卷 414-427页

作者：张彦军王碧云蔡云泽 Department of Automation Shanghai Jiao Tong UniversityShanghai 200240China Shanghai Institute of Aerospace Control Technology Shanghai 201109China Infrared Detection Technology R&D Center of China Aerospace Science and Technology Corporation Shanghai 201109China Key Laboratory of System Control and Information Processing Ministry of Education of ChinaShanghai 200240China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai 200240China Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai Jiao Tong UniversityShanghai 200240China Institute of Marine Equipment Shanghai Jiao Tong UniversityShanghai 200240China

Infrared detection technology has the advantages of all-weather detection and good concealment,which is widely used in long-distance target detection and tracking ***,the complex background,the strong noise,and the characteristics of small scale and weak intensity of targets bring great difficulties to the detection of infrared small targets.A multi-channel based on attention network is proposed in this paper,aimed at the problem of high missed detection rate and false alarm rate of traditional algorithms and the problem of large model,high complexity and poor detection performance of deep learning ***,given the difficulty in extracting the features of infrared multiscale and small dim targets,the multiple channels are designed based on dilated convolution to capture multiscale target ***,the coordinate attention block is incorporated in each channel to suppress background clutters adaptively and enhance target *** addition,the fusion of shallow detail features and deep abstract semantic features is realized by synthesizing the contextual attention fusion ***,it is verified that,compared with other state-of-the-art methods based on the datasets SIRST and MDFA,the proposed algorithm further improves the detection effect,and the model size and computational complexity are smaller.

关键词： infrared image small target detection deep learning attention mechanism feature fusion

来源：评论

学校读者我要写书评

暂无评论

Temporal Dynamic Frequency Autoencoder: Enhancing the Performance of Unsupervised Dimensionality Reduction for Gravitational Wave Glitch Clustering 24

Temporal Dynamic Frequency Autoencoder: Enhancing the Perfor...

引用

4th Asia-Pacific Artificial Intelligence and Big Data Forum, AIBDF 2024

作者： Xiao, Wanhai Ma, Cunliang Cai, Yiting Jiangxi Provincial Key Laboratory of Multidimensional Intelligent Perception and Control Jiangxi University of Science and Technology Jiangxi Ganzhou China

ISBN: (纸本)9798400710865

With the ongoing advancements in gravitational wave detection technology, the results are becoming increasingly precise. However, it is precisely this high precision that has led to the detection of noise signals that should not have been recorded, which are then mixed with real gravitational wave signals. As a result, efficient and accurate algorithms are needed to distinguish between these signals and noise. Past research has mostly relied on fully supervised or semi-supervised learning methods to classify and cluster these glitches, thereby improving the accuracy and reliability of glitch detection. However, neural networks typically require a large amount of training data to perform well, and in future work, it is impractical to manually label a vast number of experimental samples. Additionally, as time progresses, new unlabeled glitches may emerge. To address this issue, we adopted a Temporal Dynamic Frequency Autoencoder (TDFAE) based on a Kolmogorov-Arnold Network (KAN) that integrates Vision Transformers (ViT) and a four-branch encoder. To enhance feature extraction accuracy, we utilized a multi-branch fusion approach with the CLS (Class) token. This innovative unsupervised learning technique focuses on dimensionality reduction and clustering of gravitational wave glitches. Our approach, tested on the GravitySpy O3 dataset, outperforms current semi-supervised learning methods in clustering tasks. Additionally, our work on unsupervised clustering methods for traditional LIGO datasets offers significant potential, representing a key advancement in gravitational wave research. © 2024 Copyright held by the owner/author(s).

关键词： Dimensionality reduction

来源：评论

学校读者我要写书评

暂无评论

Monocular Depth Estimation Algorithm Guided by Global Structure and Local Details 24

Monocular Depth Estimation Algorithm Guided by Global Struct...

引用

4th Asia-Pacific Artificial Intelligence and Big Data Forum, AIBDF 2024

作者： Wang, Wenhao Ma, Cunliang Jiangxi Provincial Key Laboratory of Multidimensional Intelligent Perception and Control Jiangxi University of Science and Technology Jiangxi Ganzhou China

ISBN: (纸本)9798400710865

In the current encoder-decoder architecture for monocular depth estimation, there are issues with unclear structural details of depth scene objects during the decoder’s upsampling process, as well as insufficient capability to extract contextual information from the scene. To address these problems, this paper proposes a monocular depth estimation algorithm guided by global structure and local details. The algorithm utilizes a pre-trained Swin-Transformer as the encoder to downsample the monocular image and extract multi-scale features from different levels of encoder representations. During the decoder phase, high-level features are fused with low-level features to create feature guidance maps enriched with structural semantic and positional information. These maps are then refined layer by layer with local detail feature maps output from a context aggregation module. This process ensures the model retains more global and local information during the multi-scale feature fusion. Finally, global structure guidance maps and local detail guidance maps from all layers are combined to predict the final depth map. Extensive experimental results on both indoor and outdoor datasets demonstrate the superiority of the proposed model. Compared to the AdaBins algorithm, our approach reduces RMSE by 10.46% and 7.41% on the KITTI and NYU Depth v2 datasets, respectively. © 2024 Copyright held by the owner/author(s).

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Non-Line-of-Sight Identification and Localization Using UWB Based on Deep Learning 24

Non-Line-of-Sight Identification and Localization Using UWB ...

引用

4th Asia-Pacific Artificial Intelligence and Big Data Forum, AIBDF 2024

作者： Huang, Kangni Yu, Meng Song, Penghui Long, Keliu Jiangxi Provincial Key Laboratory of Multidimensional Intelligent Perception and Control Jiangxi University of Science and Technology Jiangxi Ganzhou China

ISBN: (纸本)9798400710865

Due to its characteristics of high precision, high reliability, and low power consumption, UWB technology is widely used in indoor positioning. However, the performance of UWB positioning systems can be affected by issues such as multipath effects and signal attenuation in both non-line-of-sight (NLOS) and line-of-sight (LOS) environments. This paper proposes an algorithm for NLOS and LOS state identification and localization using UWB, based on deep learning. First, a recognition model suitable for NLOS and LOS environments is established by analyzing UWB channel models and signal characteristics. Then, a method for identifying NLOS and LOS states is designed using deep learning techniques, with classification accuracy metrics introduced to evaluate model performance. To validate the proposed positioning algorithm, a UWB node positioning system is designed and tested in real environments. Experiments were conducted in two different environments-a basement and a lounge-to verify the positioning performance. Subsequently, the deep learning-based NLOS error identification and mitigation algorithm proposed in this paper was tested. The experiments compared the effects of different deep learning algorithms on NLOS error identification and mitigation. Results show that the positioning algorithm using the Convolutional Neural Network Long Short-Term Memory (CNN-LSTM) model performs best in identifying and mitigating NLOS errors, achieving the highest positioning accuracy. The study results demonstrate that the proposed algorithm not only has theoretical value but also shows great potential for practical applications. © 2024 Copyright held by the owner/author(s).

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Group Formation control of Cyber-Physical Systems via Distributed Cloud Computing

IEEE Transactions on Industrial Cyber-Physical Systems

引用

IEEE Transactions on Industrial Cyber-Physical Systems 2025年 3卷 341-350页

作者： Ren, Hongru Long, Yinren Li, Hongyi Huang, Tingwen Guangdong University of Technology School of Automation Guangdong-Hong Kong Joint Laboratory for Intelligent Decision and Cooperative Control Guangdong Provincial Key Laboratory for Intelligent Decision and Cooperative Control Guangzhou510006 China Southwest University College of Electronic and Information Engineering Chongqing400715 China Shenzhen University of Advanced Technology Faculty of Computer Science and Control Engineering Shenzhen518055 China

This paper investigates the group formation control problem for cyber-physical systems (CPSs) with random communication constraints. The distributed cloud computing system is constructed to divide agents into groups and establish communication between agents. A data-driven predictive control strategy is proposed by combining networked predictive control and model-free adaptive control method. The desired group formation control performance can be achieved and the three-channel random communication constraints of CPSs are actively compensated. Thisstrategy does not require the system model and relies solely on the system's I/O data for adaptive learning. Further analyses concludes the conditions for simultaneous reach stability and group formation of the closed-loop CPSs using the data-driven predictive control strategy. The effectiveness of the proposed strategy is validated by simulation results. © 2023 IEEE.

关键词： Distributed cloud

来源：评论

学校读者我要写书评

暂无评论

Visualizing experimental investigation on gas-liquid replacements in a microcleat model using the reconstruction method

引用

Deep Underground science and Engineering 2023年第3期2卷 295-303页

作者： Shaojie Chen Jicheng Zhang Dawei Yin Faxin Li Jialin Lu Peiyang Zhu College of Energy and Mining Engineering Shandong University of Science and TechnologyQingdaoChina State Key Laboratory of Strata Intelligent Control and Green Mining Shandong University of Science and TechnologyQingdaoChina

Cleats are the main channels for fluid transport in coal ***,the microscale flow characteristics of both gas and water phases in primary cleats have not been fully studied as ***,the local morphological features of the cleat were determined using image processing technology and a transparent cleat structure model was constructed by microfluidic lithography using the multiphase fluid visualization test ***,the effect of microchannel tortuosity characteristics on two‐phase flow was analyzed in this *** results are as follows:(1)The local width of the original cleat structure of coal was strongly *** cleats showed contraction and expansion in the horizontal direction and undulating characteristics in the vertical direction.(2)The transient flow velocity fluctuated due to the structural characteristics of the primary *** water‐driven gas interface showed concave and convex instability during flow,whereas the gas‐driven water interface presented a relatively stable concave surface.(3)The meniscus advanced in a symmetrical pattern in the flat channel,and the flow stagnated due to the influence of undulation points in a partially curved *** flow would continue only when the meniscus surface bypassed the stagnation point and reached a new equilibrium position.(4)Enhanced shearing at the gas-liquid interface increased the gas‐injection pressure,which in turn increased residual liquids in wall grooves and liquid films on the wall surface.

关键词： dynamic contact angle flow visualization instantaneous velocity microcleat residual liquid

来源：评论

学校读者我要写书评

暂无评论

A Multimodal EEG Identification Method for Complex aerospace Target Recognition

A Multimodal EEG Identification Method for Complex Aerospace...

引用

2022 Chinese Automation Congress, CAC 2022

作者： Xu, Song Wang, Lina Liu, Zhenfei Beijing Aerospace Automatic Control Institute National Laboratory of Aerospace Intelligent Control Technology Beijing China

ISBN: (纸本)9781665465335

Accurate recognition of aerospace targets in complex flight scenarios is the primary crucial link to achieve intelligent decision-making and control of aircraft. In the face of open complex flight environments with variants, camouflage and deception, traditional target recognition methods cannot meet the needs of practical applications, and the performance of computer automatic image analysis methods is far from human recognition ability. This paper innovatively proposes a complex aerospace target recognition method based on multimodal EEG identification: proposes EEG signal acquisition and pre-processing techniques under complex visual stimulation, and accurately obtains EEG representation information under relevant visual stimulation;design a multi-wavelet analysis-based time-frequency feature extraction method and multi-scale time-domain feature extraction technology, and obtain effective discriminatory EEG features under different stimulation. The method is designed to obtain multimodal EEG features with effective discriminative ability under different stimuli. The experimental results show that the proposed method can effectively identify the target of interest, which is of great significant for promoting the development of intelligent perception and recognition models for new generation unmanned systems. © 2022 IEEE.

关键词： Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Multi-Agent Reinforcement Learning with Region Division and Leader-Follower Communication

Multi-Agent Reinforcement Learning with Region Division and ...

引用

2024 China Automation Congress, CAC 2024

作者： Wang, Chao Xu, Xiang Shenzhen Key Laboratory of Control Theory and Intelligent Systems School of System Design and Intelligent Manufacturing Southern University of Science and Technology Shenzhen China

ISBN: (纸本)9798350368604

The integration of multi-agent reinforcement learning (MARL) into complex systems has paved new ways for collaborative problem-solving. However, traditional approaches to MARL frequently encounter the challenge of achieving efficient communication among agents, essential for coordinated action. This paper introduces a region division and leader-follower(RDLF) communication algrithm with the MARL framework. RDLF divides the environment into several regions, each managed by a leader agent that coordinates the actions of follower agents and handling inter-region communication. This hierarchical structure reduces unnecessary communication, enhancing learning efficiency. Experimental results in multi-particle environments demonstrate RDLF’s superiority over existing MARL algorithms, especially with increasing agent numbers. RDLF effectively addresses scalability and communication challenges in large-scale multi-agent systems, providing a robust foundation for its application in complex and dynamic environment. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Variations in Right Ascension of Ascending Node of Sun-Synchronous Orbit under the Lunar and Solar Perturbations

Variations in Right Ascension of Ascending Node of Sun-Synch...

引用

2023 China Automation Congress, CAC 2023

作者： Wang, Yuan Wan, Bei Wang, Wenyan Liu, Shenggang Han, Chan School of Astronautics Beihang University Beijing China Shanghai Aerospace Control Institute Shanghai China Shanghai Key Laboratory of Aerospace Intelligent Control Technology Shanghai China

ISBN: (纸本)9798350303759

Earth-observation satellites carrying synthetic aperture radar (SAR) instruments are typically deployed on the exact repeat-ground-track (RGT) sun-synchronous orbit (SSO) in order to achieve effective repeat-pass SAR interferometry. The exact RGT maintenance of these satellites have stringent requirements on the variation modeling accuracy of right ascension of ascending node (RAAN). Due to the significant effects of third-body attraction on the orbital plane evolutions, variations of RAAN under the lunar and solar perturbations are modeled for the SSO with local time of descending node at 00:00, 06:00, 12:00, and 18:00. An analytic method for RAAN variation modeling is proposed based on the quasi-mean element method. Coupling effects between the J2 perturbation and third-body attractions are considered to achieve a high precision of the variation model. Comparisons with precise numerical orbit propagator show that the analytical method provides good results for lunar and solar perturbation modeling on the variations of RAAN. The maximum relative error is only 2.6% and 5% for lunar and solar perturbations, respectively. © 2023 IEEE.

关键词： Orbits

来源：评论

学校读者我要写书评

暂无评论

MAGPNet: Multi-Domain Attention-Guided Pyramid Network for Infrared Small Object Detection

引用

Journal of Shanghai Jiaotong University (science) 2024年 1-18页

作者： Ding, Leqi Wang, Biyun Yao, Lixiu Cai, Yunze Department of Automation Shanghai Jiao Tong UniversityKey Laboratory of System Control and Information Processing of Ministry of Education Shanghai200240 China National Key Laboratory of Air-based Information Perception and Fusion Henan Luoyang471009 China Shanghai Institute of Aerospace Control Technology Infrared Detection Technology R&D Center of China Aerospace Science and Technology Corporation Shanghai201109 China

To overcome the obstacles of poor feature extraction and little prior information on the appearance of infrared dim small targets, we propose a multi-domain attention-guided pyramid network (MAGPNet). Specifically, we design three modules to ensure that salient features of small targets can be acquired and retained in the multi-scale feature maps. To improve the adaptability of the network for targets of different sizes, we design a kernel aggregation attention block with a receptive field attention branch and weight the feature maps under different perceptual fields with attention mechanism. Based on the research on human vision system, we further propose an adaptive local contrast measure module to enhance the local features of infrared small targets. With this parameterized component, we can implement the information aggregation of multi-scale contrast saliency maps. Finally, to fully utilize the information within spatial and channel domains in feature maps of different scales, we propose the mixed spatial-channel attention-guided fusion module to achieve high-quality fusion effects while ensuring that the small target features can be preserved at deep layers. Experiments on public datasets demonstrate that our MAGPNet can achieve a better performance over other state-of-the-art methods in terms of the intersection of union, Precision, Recall, and F-measure. In addition, we conduct detailed ablation studies to verify the effectiveness of each component in our network. © 2024, Shanghai Jiao Tong University.

关键词： Software engineering

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：