检索结果-内蒙古大学图书馆

36th International Technical Meeting of the Satellite Division of the Institute of Navigation, ION GNSS+ 2023

作者： Zhao, Haoli Tang, Jianhao Li, Zhenni Wu, Zhuoyu Xie, Shengli Wu, Zhaofeng Liu, Ming Kumara, Banage T.G.S. School of Automation Guangdong University of Technology Guangzhou510006 China Guangdong-HongKong-Macao Joint Laboratory for Smart Discrete Manufacturing Guangzhou510006 China 111 Center for Intelligent Batch Manufacturing Based on IoT Technology Guangzhou510006 China Key Laboratory of Intelligent Detection and The Internet of Things in Manufacturing Guangzhou510006 China Guangdong Key Laboratory of IoT Information Technology Guangzhou510006 China Techtotop Microelectronics Technology Co. Ltd. Guangzhou510000 China Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong Department of Computing and Information Systems Sabaragamuwa University of Sri Lanka Belihuloya Sri Lanka

ISBN: (纸本)9780936406350

With the wide applications of the Global Navigation Satellite System (GNSS) in autonomous driving scenarios, the demand for high-precision positioning of navigation systems has increased dramatically in complex multipath environments. Conventional model-based methods are constrained by strict assumptions about noise models and can hardly model complex environment errors. In contrast, approaches based on artificial intelligent learning have become an important direction to solving the problem of high-precision positioning because learning-based approaches only require simple assumptions. However, current learning-based approaches are facing the following issues. The existing Graph Neural Network-based (GNN) method could hardly adapt to dynamically changing driving environment scenarios since it considers positioning discretely. On the other hand, existing Reinforcement Learning-based (RL) approaches ignore the relationship between multi-constellation satellites, resulting in an inadequate description of the driving correction environment observations. In this paper, we construct a GNN-driven recurrent reinforcement learning method to consider the GNSS measurement of multi-constellation satellites and to learn real-time correction strategy in the dynamic driving environment. To establish a comprehensive positioning correction environment, we construct a multi-constellation graph observation, based on the feature vector concerning GNSS measurement of multi-constellation satellites and edges for satellites in and between constellations. To make more effective use of GNSS measurements, we employ the graph embedding module to deal with the multi-constellation graph inputs, to extract hidden topological features to form the brief states about relationships between multi-constellation satellites for the RL environment. Finally, we construct a recurrent actor-critic structured RL model with cumulative reward and continuous action space to exploit historical information and a

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improve Cross-domain Mixed Sampling with Guidance Training for Adaptive Segmentation

arXiv

引用

arXiv 2024年

作者： Zhou, Wenlve Zhou, Zhiheng Wang, Tianlei Zeng, Delu School of Electronic and Information Engineering South China University of Technology Guangdong Guangzhou510641 China Key Laboratory of Big Data and Intelligent Robot Ministry of Education South China University of Technology Guangzhou510641 China The Department of Intelligent Manufacturing Wuyi University Jiangmen529020 China

Unsupervised Domain Adaptation (UDA) endeavors to adjust models trained on a source domain to perform well on a target domain without requiring additional annotations. In the context of domain adaptive semantic segmentation, which tackles UDA for dense prediction, the goal is to circumvent the need for costly pixel-level annotations. Typically, various prevailing methods baseline rely on constructing intermediate domains via cross-domain mixed sampling techniques to mitigate the performance decline caused by domain gaps. However, such approaches generate synthetic data that diverge from real-world distributions, potentially leading the model astray from the true target distribution. To address this challenge, we propose a novel auxiliary task called Guidance Training. This task facilitates the effective utilization of cross-domain mixed sampling techniques while mitigating distribution shifts from the real world. Specifically, Guidance Training guides the model to extract and reconstruct the target-domain feature distribution from mixed data, followed by decoding the reconstructed target-domain features to make pseudo-label predictions. Importantly, integrating Guidance Training incurs minimal training overhead and imposes no additional inference burden. We demonstrate the efficacy of our approach by integrating it with existing methods, consistently improving performance. The implementation will be available at https://***/Wenlve-Zhou/Guidance-Training. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Super-resolution reconstruction algorithm for terahertz imaging below diffraction limit

引用

Chinese Physics B 2023年第3期32卷 608-612页

作者：王莹祁峰张子旭汪晋宽 School of Communication Science and Engineering Northeastern UniversityShenyang 110819China Key Laboratory of Opto-Electronic Information Processing Chinese Academy of SciencesShenyang 110016China Shenyang Institute of Automation Chinese Academy of SciencesShenyang 110016China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of SciencesShenyang 110169China University of Chinese Academy of Sciences Beijing 100049China University of Technology Sydney NSW 2007Australia

Terahertz(THz)imaging has drawn significant attention because THz wave has a unique capability to transient,ultrawide spectrum and low photon ***,the low resolution has always been a problem due to its long wavelength,limiting their application of fields practical *** this paper,we proposed a complex one-shot super-resolution(COSSR)framework based on a complex convolution neural network to restore superior THz images at 0.35 times wavelength by extracting features directly from a reference measured sample and groundtruth without the measured *** with real convolution neural network-based approaches and complex zero-shot super-resolution(CZSSR),COSSR delivers at least 6.67,0.003,and 6.96%superior higher imaging efficacy in terms of peak signal to noise ratio(PSNR),mean square error(MSE),and structural similarity index measure(SSIM),respectively,for the analyzed ***,the proposed method is experimentally demonstrated to have a good generalization and to perform well on measured *** COSSR provides a new pathway for THz imaging super-resolution(SR)reconstruction below the diffraction limit.

关键词： terahertz image processing complex convolution neural network

来源：评论

学校读者我要写书评

暂无评论

3D Lane Detection From Front or Surround-View Using Joint-Modeling & Matching

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on intelligent Vehicles 2024年 1-14页

作者： Zhou, Haibin Zhou, Huabing Chang, Jun Lu, Tao Ma, Jiayi Hubei Key Laboratory of Intelligent Robot Wuhan Institute of Technology Wuhan China Computer Science School Wuhan University Wuhan China Electronic Information School Wuhan University Wuhan China

3D lanes offer a more comprehensive understanding of the road surface geometry than 2D lanes, thereby providing crucial references for driving decisions and trajectory planning. While many efforts aim to improve prediction accuracy, we recognize that an efficient network can bring results closer to lane modeling. However, if the modeling data is imprecise, the results might not accurately capture the real-world scenario. Therefore, accurate lane modeling is essential to align prediction results closely with the environment. This study centers on efficient and accurate lane modeling, proposing a joint modeling approach that combines Bézier curves and interpolation methods. Furthermore, based on this lane modeling approach, we developed a Global2Local Lane Matching method with Bézier Control-Point and key-Point, which serve as a comprehensive solution that leverages hierarchical features with two mathematical models to ensure a precise match. We also introduce a novel 3D Spatial Encoder, representing an exploration of 3D surround-view lane detection research. The framework is suitable for front-view or surround-view 3D lane detection. By directly outputting the key points of lanes in 3D space, it overcomes the limitations of anchor-based methods, enabling accurate prediction of closed-loop or U-shaped lanes and effective adaptation to complex road conditions. This innovative method establishes a new benchmark in front-view 3D lane detection on the Openlane dataset and achieves competitive performance in surround-view 2D lane detection on the Argoverse2 dataset. IEEE

关键词： Interpolation

来源：评论

学校读者我要写书评

暂无评论

Improving Urban Canyons Based on a Graph Transformer

引用

Navigation, Journal of the Institute of Navigation 2024年第4期71卷

作者： Zheng, Shaolong Zeng, Kungan Li, Zhenni Wang, Qianming Xie, Kan Liu, Ming Xie, Shengli School of Automation Guangdong University of Technology Guangzhou China Guangdong–HongKong–Macao Joint Laboratory for Smart Discrete Manufacturing Guangzhou China 111 Center for Intelligent Batch Manufacturing Based on Internet of Things Technology Guangzhou China Techtotop Microelectronics Technology Co. Ltd Guangzhou China Department of Electronic and Computer Engineering Hong Kong University of Science and Technology China Key Laboratory of Intelligent Detection and the Internet of Things in Manufacturing Guangzhou China Guangdong Provincial Key Laboratory of Intelligent Systems and Optimization Integration Guangzhou China

Signals from global navigation satellite systems (GNSSs) in urban areas suffer from serious multipath errors caused by building blockages and reflections. The use of deep neural networks offers great potential for predicting and eliminating com-plex multipath/non-line-of-sight (NLOS) errors. However, existing methods for predicting the original signals face two remaining challenges. The first challenge is an inability to effectively exploit irregular GNSS measurement data caused by an inconsistent number of visible satellites in different epochs. The second challenge is degradation in the generalization performance of the multipath/NLOS prediction model when using data collected from different locations and periods. To address these challenges, this paper proposes a novel graph transformer neural network (GTNN) for predicting satellite visibility that effectively learns environment representations from irregular GNSS measurements to both alleviate multipath interference and improve the generalization performance of the multipath prediction model. To learn from irregular GNSS measurements, a sky satellite graph is constructed as input to a graph neural network by using satellites captured in the same epoch, which can represent the spatial relationships between satellites and enable the model to learn satellite-related features sufficiently well. To improve the generalization ability of our multipath prediction model, a multihead attention mechanism is introduced to aggregate satellite node information by computing the correlation between satellites to extract the environment representation around the receiver. Based on the constructed sky satellite graph and the multihead attention mechanism, our novel GTNN for predicting satellite visibility can not only handle irregular GNSS measurements but can also learn an environment representation via graph attention. Comparative experiments were conducted on real-world GNSS measurement data in urban areas, demonstrating that

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

A method for estimating the contribution of an object to scene semantics 4

A method for estimating the contribution of an object to sce...

引用

4th International Conference on Computer Vision and Information technology, CVIT 2023

作者： Lin, Zhiyuan Zhu, Feng Wang, Jianyu Wang, Qun Zhao, Pengfei Key Laboratory of Opto-Electronic Information Processing Chinese Academy of Sciences Shenyang110016 China Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang110169 China University of Chinese Academy of Sciences Beijing100049 China Faculty of Robot Science and Engineering Northeastern University Shenyang110169 China

ISBN: (纸本)9781510672864

The amount of semantic contribution of each object in an image to understand the scene is different. Understanding the relative importance of objects in a scene for scene semantics is critical for various computer vision applications, such as scene recognition and image captioning. In this paper, we refer to the contribution of an object to scene semantics as the degree of its gist and propose a method for Estimating the degree of the Gist of an Instance (EGoI). In the EGoI method, an object gist degree is estimated by the semantic features comparison strategy and the semantic distance comparison strategy. In the first strategy, the image is represented as a scene graph first, then the aggregation features and the node features of different graph node combinations are calculated to estimate the instance gist that is not in the combination of the nodes. In the second strategy, the captions of the complete and incomplete images are generated, then the semantic distance of these captions is used to estimate the instance gist deleted in the scene. Different strategies for estimating the gist degree of instances are tested in the experiments. The results show that the proposed method can effectively quantify the contribution of an instance to scene semantics. Among these strategies, the method that compares semantic features has better discriminative power for the gist degree of various instances in the scene. © 2024 SPIE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

An Accurate Error Compensation Method for Multi-Axis Parallel Machine Through Singularized Jacobi Geometric Parameter Correction and Coupling Error Evaluation

SSRN

引用

SSRN 2023年

作者： Luo, Yuheng Gao, Jian Chen, Disai Zhang, Lanyu State Key Laboratory of Precision Electronic Manufacturing Technology and Equipment Guangdong University of Technology Guangzhou510006 China Key Laboratory of Intelligent Inspection and Manufacturing IoT of Ministry of Education Guangdong University of Technology Guangzhou510006 China

Jacobian model is widely used for error compensation of multi-axis parallel mechanisms. However, the deviation between the nominal geometrical parameters and actual parameters in the Jacobi model and the equivalent replacement and high-order rounding operations in Jacobi modeling process will result in the indefinite equation solving problem and modeling error problem, which inevitably induces certain residual errors of the Jacobi model compensation method. To tackle these problems, this paper proposes an optimal Jacobian correction method through a geometrical parameter singularized Jacobian correction model and a coupling error evaluation modular for multi-axis parallel mechanism. In this method, a new singularized geometrical error solution method (SESM) is constructed to obtain the Jacobian correction parameters accurately instead of iteration. The method can solve the indefinite equation problem and partial posture non-solution problem. The SESM can also compensate the modeling error induced by the equivalent infinitesimal replacement and the high-order small amount ignorance operation. Considering that the Jacobian model with different singularized geometrical parameter will have certain coupling effect and result in different compensation effect, a sensitivity-based error predictive evaluation method (EPEM) is proposed to determine the optimal correction parameter of the Jacobian model for the pose of the entire workspace and thus realize an accurate pose error compensation. The proposed method is tested on a three-axis parallel mechanism. Experimental results demonstrated the effectiveness and advancement of the proposed method, which can further reduce the position and orientation error by 64.93% and 55.29%, respectively, by comparison with the uncorrected Jacobian compensation method. This method provides us a new approach for error modeling, equation solving, and parameter correction for multi-axis mechanism error compensation and precision equipment deve

关键词： Error compensation

来源：评论

学校读者我要写书评

暂无评论

Effect of irradiation on temperature performance of dispersioncompensation no-core cascade optical-fiber sensor coated with polydimethylsiloxane film

引用

Nuclear Science and Techniques 2022年第9期33卷 10-20页

作者： Fang Wang Qiu-Feng Wu Yu-Rong Jiang Chan Jin Xiao-Hui Wang Ben-Shang Zhang Chun-Wang Ma College of Electronic and Electrical Engineering Henan Normal UniversityXinxiang 453007China Key Laboratory of Optoelectronic Sensing Integrated Application of Henan Province Xinxiang 453007China School of Physics Henan Normal UniversityXinxiang 453007China Engineering Laboratory of Intelligent Additive Manufacturing of Henan Province Xinxiang 453007China Key Laboratory of Interfacial Physics Technology Project Chinese Academy of SciencesShanghai 201800China Institute of Isotope Research Henan Academy of SciencesZhengzhou 450000China

A temperature measurement device can produce data deviations and can even be damaged in a high-dose radiation *** reduce the radiation damage to such a device and improve the temperature measurement accuracy in a radiation environment,a temperature sensor based on optical-fiber sensing technology is *** sensor has a cascade structure composed of a single-mode fiber(SMF),a dispersion-compensation fiber(DCF),a nocore fiber(NCF),and another SMF(SDNS).The DCF and NCF are coated with a polydimethylsiloxane(PDMS)film,which is a heat-sensitive material with high thermal optical and thermal expansion *** experiments,PDMS was found to produce an irradiation crosslinking effect after irradiation,which improved the temperature sensitivity of the SDNS *** experimental results showed that within a range of 30–100℃,the maximum temperature sensitivity after irradiation was 62.86 pm/℃,and the maximum transmission sensitivity after irradiation was 3.353×10^(-2)dB/℃,which were 1.22 times and 2.267 times the values before irradiation,*** addition,repeated temperature experiments verified that the SDNS sensor coated with the PDMS film had excellent temperature ***,it was found that with an increase in the irradiation intensity,the irradiation crosslinking degree of PDMS increased,and the temperature sensitivity of the sensor was *** proposed sensor could potentially be applied to temperature measurement in a nuclear-radiation environment.

关键词： ^(60)Co-γirradiation Optical-fiber sensor Temperature performance PDMS Radiation crosslinking

来源：评论

学校读者我要写书评

暂无评论

CMME-YOLO: Composite Microscale Multi-stream Enhanced Model for PCB Defect Detection 19th

CMME-YOLO: Composite Microscale Multi-stream Enhanced Model ...

引用

19th Chinese Conference on Image and Graphics Technologies and Applications, IGTA 2024

作者： Xie, Zhihua Zou, Xiaowei Zhou, Zhiwu Key Lab of Advanced Electronic Materials Jiangxi Science and Technology Normal University Nanchang China Nanchang Key Laboratory of Failure Perception & Green Energy Materials Intelligent Manufacturing Nanchang China

ISBN: (纸本)9789819799183

To address the challenges of excessive model parameters and low detection accuracy in print circuit board (PCB) defect detection, this paper proposes a novel PCB defect detection model based on the improved YOLOv8 (You Only Look Once v8), named CMME-Yolo. Specifically, the proposed model leverages the sliding window mechanism and the receptive field synthesis mechanism into the original YOLOv8 backbone. Particularly, this scheme proposes a fine aware aggregation paradigm to enhance the recognition of small-scale defects in PCB images and boost the detailed representation in YOLOv8. After effectively capturing fine-grained features from PCB images in the backbone, subtle features are strengthened through the SPD-Conv (Space-to-Depth) module in the neck, thus fulfilling fusion through multi-stream features. Finally, to achieve adaptive aggregation of fine-grained perceptual features, these processed features are fed into the bridge rectifier of the feature pyramid system—the Parallel Multi-stream Fine Aware Aggregation module (PMSFA). Extensive experiments are conducted on the PCB defect dataset released by Peking University to validate the effectiveness of the proposed model. The experimental results show that compared with the original YOLOv8, our approach achieved the improvement in mean Average Precision (mAP)@0.5 and mAP@0.5:0.95 by 4.9% and 12.1%, respectively. Meanwhile, the number of model parameters is reduced by approximately 14% compared with the original YOLOv8. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Electric rectifiers

来源：评论

学校读者我要写书评

暂无评论

Molecular dynamics simulation and experimental study of laser-assisted machining of SiCp/Al composites

引用

Procedia CIRP 2025年 133卷 2-7页

作者： Feijie Cui Hang Zhang Minghui Yang Ben Deng Jiawei Lv Rong Yan Fangyu Peng School of Mechanical Science and Engineering Huazhong University of Science and Technology Wuhan 430074 China School of Mechanical and Electronic Engineering Wuhan University of Technology Wuhan 430070 China State Key Laboratory of Intelligent Manufacturing Equipment and Technology Huazhong University of Science and Technology Wuhan 430074 China

High-quality machining of SiCp/Al composite faces a number of challenges due to the presence of hard and brittle SiC particles, making it a typical difficult-to-machine material. Conventional machining (CM) inevitably leads to high cutting forces and poor surface quality, which significantly limit the potential applications of SiCp/Al composites. Laser-assisted machining (LAM) has been evidenced that it can remarkably improve the machinability of SiCp/Al composites, however, the microscopic removal mechanism of the material under the effect of laser remains to be investigated in depth. In this paper, the molecular dynamics (MD) simulation and Transmission Electron Microscope (TEM) experiments are employed to carry out further research. A MD model for LAM of SiCp/Al composites is established, which is applied to analyze the dynamic evolution of the cutting forces and the dislocations of the material during the machining. The results show that with the rise of laser power, the dislocation density inside the Al matrix decreases gradually. The coordinated deformation ability of SiCp/Al composites is enhanced, and the cutting force tends to decrease. The high consistency between experimental and simulation results verifies the validity of the MD model.

关键词：

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：