检索结果-内蒙古大学图书馆

Infrared Dim Small Target Detection Algorithm Based on Adaptive Attention Transformer Network

Journal of Shanghai Jiaotong University (science) 2025年 1-13页

作者： Ding, Leqi Xia, Yilin Wang, Biyun 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

This paper presents a novel algorithm for detecting infrared dim small targets in complex backgrounds by integrating both global and local feature information. The proposed method employs an adaptive attention transformer network which addresses challenges associated with computational complexity and information redundancy in traditional self-attention mechanisms. A global context aggregation module is designed to address the loss of small target features in high-level feature maps. This module compensates for spatial distribution information during the multi-scale feature fusion process, ensuring the preservation of target features. Comparison experiments were conducted on two datasets, NUAA-SIRST and IRSTD-1k. The proposed algorithm achieved 0.784 for mIoU and 0.878 for F-measure on NUAA-SIRST, 0.632 for mIoU and 0.807 for F-measure on IRST-1k, all of which are the highest values. The proposed algorithm shows a significant improvement over other existing detection algorithms, demonstrating its capability to accurately extract both local and global features of targets with high recall rates and low false alarm rates across various scenarios. The ablation study results highlight the significant improvements contributed by the key modules to the proposed algorithm. (Figure presented.) © Shanghai Jiao Tong University 2025.

关键词： A adaptive attention global context aggregation module infrared dim small target detection TP391.4 Transformer network

来源：评论

学校读者我要写书评

暂无评论

HYBRID-DRIVEN MODEL FOR TEMPERATURE PREDICTION IN WET CLUTCHES 10

HYBRID-DRIVEN MODEL FOR TEMPERATURE PREDICTION IN WET CLUTCH...

引用

10th International Symposium on Test Automation and Instrumentation, ISTAI 2024

作者： Huang, Yuanbin Li, Le Wang, Qian Wang, Liyong Key Laboratory of Modern Measurement and Control Technology in Ministry of Education Beijing Information Science and Technology University Beijing China

ISBN: (纸本)9781837242672

A hybrid-driven model for predicting the temperature at the friction interface of wet clutch friction components was developed, employing a radial basis function neural network algorithm. This model uses temperature data obtained from wet clutch test bench experiments to compensate for the results from a thermo-mechanical coupled numerical simulation model of the friction components. The hybrid model inputs include load pressure, relative speed, radial position of the friction components, and numerically simulated temperatures at the friction interface, to output predicted temperatures under specific operating conditions. The results indicate that the predicted temperatures of the friction components under various conditions align well with experimental values, with a maximum mean relative error of 0.033 and all prediction intervals having a coefficient of determination higher than 0.97. Thus, the hybrid-driven model demonstrates high accuracy and stability in predictions, and possesses strong adaptability and predictive capabilities for different temperature distributions at the friction interface. © The Institution of Engineering & technology 2024.

关键词： Radial basis function networks

来源：评论

学校读者我要写书评

暂无评论

REVIEW OF RESEARCH ON OCCLUSION ISSUES IN RGB-D DYNAMIC SCENE 3D RECONSTRUCTION 10

REVIEW OF RESEARCH ON OCCLUSION ISSUES IN RGB-D DYNAMIC SCEN...

引用

10th International Symposium on Test Automation and Instrumentation, ISTAI 2024

作者： Dong, Yuanqiu Wu, Guoxin Zhang, Guolong Zhou, Linglong Qi, Yinyan The Ministry of Education Key Laboratory of Modern Measurement and Control Technology Beijing Information Science & Technology University Beijing China

ISBN: (纸本)9781837242672

As innovation proceeds to advance,3D recreation innovation has ended up a critical portion of the field of computer vision. Among these, 3D reproduction innovation based on RGB-D information sources has ended up a well known approach in later a long time. Right now, the more develop inactive 3D recreation calculations have ended up progressively successful for reproducing stationary objects. Be that as it may, their adequacy lessens when parts of the scene are blocked. This paper briefly presents particular approaches to address impediment issues and the fundamental concepts of energetic 3D remaking innovation based on RGB-D information sources. The points of interest and current investigate status of energetic 3D reproduction focusing on impediment issues utilizing RGB-D information sources are examined. Moreover, the most recent progressions in 3D remaking of energetic scenes are summarized, and proposed future investigate bearings. © The Institution of Engineering & technology 2024.

关键词： 3D reconstruction

来源：评论

学校读者我要写书评

暂无评论

REARCH ON DOUBLE CUBIC INTERPOLATION COMBINED WITH GAUSSIAN FITTING SUB-PIXEL EDGE DETECTION METHOD 10

REARCH ON DOUBLE CUBIC INTERPOLATION COMBINED WITH GAUSSIAN ...

引用

10th International Symposium on Test Automation and Instrumentation, ISTAI 2024

作者： Qi, Yinyan Wu, Guoxin Li, Yao Dong, Yuanqiu The Ministry of Education Key Laboratory of Modern Measurement and Control Technology Beijing Information Science & Technology University Beijing China

ISBN: (纸本)9781837242672

With the rapid advancements in intelligent manufacturing technology, the realization of fast and accurate measurements in aerospace, instrumentation, machinery and equipment, automotive electronics, and other sectors has become a research hotspot. Image positioning technology and edge detection methods, with their advantages of being fast, non-contact, and precise, have been widely employed. How to improve the accuracy of image measurement lies in solving the problem of accurate positioning of image edge detection, based on the problem of inaccurate extraction of directional information and large error in contour size of image edge detection technology proposes an improved sub-pixel edge detection algorithm with Gaussian fitting by double cubic interpolation. Based on preprocessing for pixel-level edge feature extraction, pixel-level edge points are acquired utilizing the least squares fitting algorithm. The normal section is determined by computing the normal intercept line, while the normal isometric line is identified through the Gaussian integration method. Sub-pixel fitting points are obtained via boundary fitting, and the final grey value is derived using an edge detection algorithm that combines double cubic interpolation and Gaussian fitting on the fitted points. The experimental results demonstrate that, through comparative testing of this method, it has been verified that it exhibits the highest image quality and is superior to most current algorithms. An improvement in the algorithm by 0.021%, 0.025%, and 0.031% in edge localization accuracy compared to the Zernike moment algorithm, Gaussian fitting algorithm, and bicubic interpolation algorithm has been achieved, effectively verifying that the image quality detected by this method is relatively high. In comparison with the point cloud method regarding fitting error, it was observed that the error index increased by 0.025% under strong burst light conditions, 0.026% under normal burst light conditions, an

关键词： Interpolation

来源：评论

学校读者我要写书评

暂无评论

THE ADAPTIVE MPC controlLER OF AUTONOMOUS DRIVING FORMULA FOR TRAJECTORY TRACKING 10

THE ADAPTIVE MPC CONTROLLER OF AUTONOMOUS DRIVING FORMULA FO...

引用

10th International Symposium on Test Automation and Instrumentation, ISTAI 2024

作者： Chen, Bowen Su, Qinghua Song, Yue Yin, Zehao Wang, Liyong Key Laboratory of Modern Measurement and Control Technology Ministry of Education Beijing Information Science & Technology University Beijing China

ISBN: (纸本)9781837242672

Autonomous driving technology has gradually been applied in real life, and it has also been improved in the China Collegiate Electric Vehicle Racing. However, as one of the critical components of autonomous driving technology, trajectory tracking control still faces challenges. This paper designs a trajectory tracking controller by building a vehicle's three-degree-of-freedom dynamics model and adopting adaptive model predictive control. It adjusts the prediction horizon of the vehicle's trajectory tracking controller in real-time based on the curvature of the desired trajectory to improve the effect of trajectory tracking. Experimental results show that the tracking effect of the adaptive prediction time-domain trajectory tracking controller in the S-curve is improved by 4.97% and 11.36% compared to the fixed prediction time-domain trajectory tracking controller, respectively. For the formula track conditions, the tracking effect of the controller proposed in this paper is improved by 0.71% compared to the fixed prediction time-domain trajectory tracking controller, with an average tracking error of 5.65%. © The Institution of Engineering & technology 2024.

关键词： Adaptive control systems

来源：评论

学校读者我要写书评

暂无评论

DEEP CNN FUSING ATTENTION AND LGBM CLASSIFIER FOR HIGH-ACCURACY HAND GESTURE RECOGNITION 10

DEEP CNN FUSING ATTENTION AND LGBM CLASSIFIER FOR HIGH-ACCUR...

引用

10th International Symposium on Test Automation and Instrumentation, ISTAI 2024

作者： You, Zhicong Lu, Wangdong Zhu, Chunmei Key Laboratory of Modern Measurement & Control Technology Ministry of Education Beijing Information Science & Technology University Beijing China

ISBN: (纸本)9781837242672

Gesture recognition has been widely used in automation and medical and smart-home. The adaptability and accuracy of traditional machine learning algorithms are limited by feature extraction and classifier selection, and the recognition accuracy is low as well as the robustness is poor. In our work, an improved CNN (Convolutional Neural Networks) combined with an LGBM (Lightweight Gradient Boosting Machine) hand gesture recognition method is proposed to improve the performance of hand gesture recognition. The method designs a 4-layer CNN structure and integrates a CBAM (Convolutional Block Attention Module) in the network to enhance the model's ability to learn and extract features. Furthermore, the extracted features are fed into an LGBM classifier for gesture classification, which improves the accuracy of gesture classification and reduces the risk of model overfitting. The accuracy of the 16 types of static gesture recognition reaches 97.89% in our dataset. An improvement of more than 10% is obtained in comparison with traditional machine learning classification algorithms. It demonstrates promising prospects for gesture recognition. © The Institution of Engineering & technology 2024.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

FAULT DIAGNOSIS METHOD BASED ON THE TIMESNET MODEL UNDER VARIABLE SPEED AND STRONG NOISE 10

FAULT DIAGNOSIS METHOD BASED ON THE TIMESNET MODEL UNDER VAR...

引用

10th International Symposium on Test Automation and Instrumentation, ISTAI 2024

作者： Qiao, Wan Liu, Xiuli Huang, Jinpeng Wu, Guoxin Key Laboratory of Modern Measurement and Control Technology Ministry of Education Beijing Information Science and Technology University Beijing China

ISBN: (纸本)9781837242672

Aiming at the fault diagnosis of rotating machinery in industrial production, which faces the problems of signal noise, variable speed and other interferences that lead to inconspicuous fault features, and the traditional methods rely on manual experience for feature extraction and lack of robustness, the present study introduces a novel fault diagnosis approach utilizing the TimesNet model. This method takes the temporal multi-periodicity as the starting point, and the one-dimensional original signal is divided into multiple two-dimensional signals by different sizes of the period respectively. Subsequently, Inception-Attention modeling is applied to extract intricate time and space information. The experiments use the planetary gearbox dataset to verify the influence of different parameters and structures of TimesNet on the diagnostic effect, and carry out comparative tests with five time-series classification models, which provide some reference value for the application of TimesNet in fault diagnosis. © The Institution of Engineering & technology 2024.

关键词： Epicyclic gears

来源：评论

学校读者我要写书评

暂无评论

APPLICATION OF WAVELET KURTOSIS CONVOLUTIONAL NEURAL NETWORK MODEL IN ROLLING BEARING FAULT DIAGNOSIS 10

APPLICATION OF WAVELET KURTOSIS CONVOLUTIONAL NEURAL NETWORK...

引用

10th International Symposium on Test Automation and Instrumentation, ISTAI 2024

作者： Men, Dachao Jiang, Zhanglei Liu, Xiuli Zheng, Wei Li, Zihan Zha, Zhendong Key Laboratory of Modern Measurement & Control Technology Ministry of Education Beijing Information Science & Technology University Beijing China

ISBN: (纸本)9781837242672

Aiming at the problem of substantial noise in the actual industrial environment, where the intelligent diagnostic model exhibits weak anti-noise performance and the interpretability of the extracted features is not strong, the wavelet kurtosis convolutional neural network model integrating signal processing technology and deep learning neural networks has been proposed. Firstly, the standard CNN convolution kernel has been replaced with a wavelet basis function to form a wavelet convolution layer, and the input signal undergoes decomposition into various frequency components via the wavelet filter in this layer;Secondly, a kurtosis loss layer has been used to filter the high kurtosis value components that contain more fault features, so as to achieve the filtration of the noise and the accurate localisation of the fault signals;Lastly, the efficacy of the proposed model has been verified in the rolling bearing dataset and diagnostic model. The results showed that the model can reach 90% diagnostic accuracy under -4db Gaussian white noise interference, which was higher than other diagnostic models, and had good generalisation and noise resistance. © The Institution of Engineering & technology 2024.

关键词： White noise

来源：评论

学校读者我要写书评

暂无评论

Fuze dual-channel ballistic height fusion and prediction algorithm based on FCI-KF 4

Fuze dual-channel ballistic height fusion and prediction alg...

引用

4th International Conference on Defence technology, ICDT 2024

作者： Wu, Dan Zhang, Ke Wang, Xin Xu, Ruichen Yang, Jingang Xi'an Institute of Electromechanical Information Technology Xi'an China Science and Technology on Electromechanical Dynamic Control Laboratory Xi'an China

To improve the measurement accuracy of the ballistic height and anti-interference ability of fuze in complex environments, the fuze dual-channel ballistic height fusion and prediction algorithm based on Fast Covariance Intersection fusion Kalman Filter (FCI-KF) is proposed. Firstly, the state model and observation model are established, the improved Kalman Filter (KF) algorithm is used to predict the height of the single-channel and then the Fast Covariance Intersection (FCI) algorithm is used to fuse the dual-channel data. This algorithm does not need to calculate the cross-covariance matrix between channels, hence the amount of calculation is small, which is convenient for engineering realization. Finally, the algorithm is simulated and verified, the simulation results show that the measurement accuracy of the proposed algorithm can be significantly improved compared with the original measurement, and the measurement accuracy of the ballistic height is better than that of the traditional methods using only one channel, which verifies the effectiveness of the algorithm. © 2024 Institute of Physics Publishing. All rights reserved.

关键词： Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Unintentional emissions of polychlorinated naphthalenes in China:Sources,composition,and historical trends

引用

Journal of Environmental sciences 2025年第2期148卷 221-229页

作者： Ye Huang Lin Huang Ying Li Nazupar Sidikjan Yunshan Zhang Yan Chen Yangmin Chen Ye Li Wei Du Long Chen YanWu Shanshan Zhang Jing Yang Wenjun Meng Guofeng Shen Min Liu Shu Tao Key Laboratory of Geographic Information Science of the Ministry of Education School of Geographic SciencesEast China Normal UniversityShanghai 200241China Yunnan Provincial Key Laboratory of Soil Carbon Sequestration and Pollution Control Faculty of Environmental Science&EngineeringKunming University of Science&TechnologyKunming 650500China Laboratory of Earth Surface Processes College of Urban and Environmental SciencePeking UniversityBeijing 100871China

Polychlorinated naphthalenes(PCNs)are detrimental to human health and the *** the commercial production of PCNs banned,unintentional releases have emerged as a significant environmental ***,relevant information is still *** this study,provincial emissions for eight PCNs homologues from 37 sources in the Chinese mainland during the period of 1960-2019 were estimated based on a source-specific and time-varying emission factor *** results showed that the total PCNs emissions in 2019 reached 757.0 kg with Hebei ranked at the top among all the provinces and iron&steel industry as the biggest ***-chlorinated PCNs comprised 90%of emissions by mass,while highly chlorinated PCNs dominated in terms of toxicity,highlighting divergent priorities for mitigating emissions and safeguarding human *** emissions showed an overall upward trend from 1960 to 2019 driven by emission increase from iron&steel industry in terms of source,and from North China and East China in terms of geographic ***-capita emissions followed an inverted U-shaped environmental Kuznets curvewhile emission intensities decreased with increasing per-capita Gross Domestic Product(GDP)following a nearly linear pattern when log-transformed.

关键词： PCNs Emission inventory Emission factor Composition profile Emission intensity Chinese mainland

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：