检索结果-内蒙古大学图书馆

2024 China Automation Congress, CAC 2024

作者： Su, Wei Xu, Ge Zhao, Xiao Zhang, Yanduo Qin, Tao School of Mechanical Engineering Hubei University of Arts and Science Xiangyang441053 China School of Computer Hubei University of Arts and Science Xiangyang441053 China Hubei Key Laboratory of Intelligent Robot Wuhan Institute of Technology Wuhan430073 China

ISBN: (纸本)9798350368604

The air-ground collaborative robotic system has garnered significant attention due to its potential applications in complex scenarios such as search and rescue and extraterrestrial exploration. However, existing research encounters substantial challenges related to efficient and reliable path planning in large scale environments. In this study, we explore the creation of maps in unknown environments without GPS by unmanned aerial vehicles (UAVs) to assist unmanned ground vehicles (UGVs) in rapid and advanced global path planning. Our approach begins with a UAV equipped with a camera, using the ORB-SLAM3 algorithm to generate a sparse point cloud map. Next, we apply the Statistical Outlier Removal (SOR) algorithm to filter out point cloud noise. To obtain a map of navigable paths, we employ the Random Sample Consensus (RANSAC) algorithm to extract the point cloud information representing the traversable ground. Finally, the processed 3D point cloud map is converted into a 2D grid map, resulting in an obstacle map suitable for UGV global path planning. Additionally, we employ the A* algorithm for path planning, considering critical factors such as path width and gradient. The proposed system demonstrates significant application potential in unknown environment exploration. UAVs can pre-scan unfamiliar terrains to facilitate efficient UGV navigation. The results indicate that our integrated method significantly enhances the efficiency and reliability of path planning in collaborative robotic systems. © 2024 IEEE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

CFinDEE: A Chinese Fine-Grained Financial Dataset for Document-Level Event Extraction 24

CFinDEE: A Chinese Fine-Grained Financial Dataset for Docume...

引用

33rd Companion of the ACM World Wide Web Conference, WWW 2023

作者： Zhang, Tian Liu, Maofu Zhou, Bingying School of Computer Science and Technology Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan University of Science and Technology Wuhan China

ISBN: (纸本)9798400701726

Document-level event extraction faces numerous challenges in accurately modeling real-world financial scenarios, particularly due to the inadequacies in existing datasets regarding data scale and fine-grained annotations. The development of datasets is a crucial factor in driving research progress;therefore, we present a high-quality Chinese document-level event extraction dataset, CFinDEE. This dataset, grounded in real-world financial news, defines 22 event types and 116 argument roles, annotating 26,483 events and 107,096 event arguments. CFinDEE aims to address these shortcomings by providing more comprehensive annotations and data augmentation, offering richer resources for document-level event extraction in the financial domain. CFinDEE extends data both horizontally and vertically, where horizontal expansion enriches the types of financial events, enhancing the diversity of the dataset;vertical expansion, by increasing the scale of the data, effectively boosts the practical value of the dataset. Experiments conducted on multiple advanced models have validated the high applicability and effectiveness of the CFinDEE dataset for document-level event extraction tasks in the financial field. © 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Expansion

来源：评论

学校读者我要写书评

暂无评论

Julolidine functionalized benzimidazoline-doped fullerene derivatives for efficient and stable perovskite solar cells

引用

Interdisciplinary Materials 2024年第3期3卷 369-379页

作者： Yanqing Zhu Chenglong Li JiaHui Chen Yuxi Zhang Jianfeng Lu Min Hu Wangnan Li Fuzhi Huang Yi-Bing Cheng Hyesung Park Shengqiang Xiao State Key Laboratory of Silicate Materials for Architectures Wuhan University of TechnologyWuhanChina State Key Laboratory of Advanced Technology for Materials Synthesis and Processing Wuhan University of TechnologyWuhanChina School of Electronic and Electrical Engineering Hubei Province Engineering Research Centre for Intelligent Micro-Nano Medical Equipment and Key TechnologiesWuhan Textile UniversityWuhanChina Hubei Key Laboratory of Low Dimensional Optoelectronic Material and Devices Hubei University of Arts and ScienceXiangyangHubeiChina KU-KIST Graduate School of Converging Science and Technology Korea UniversitySeoulRepublic of Korea Department of Integrative Energy Engineering Korea UniversitySeoulRepublic of Korea Hubei Key Laboratory of Fuel Cell WuhanChina

Fullerene derivatives are highly attractive materials in solar cells,organic thermoelectrics,and other ***,the intrinsic low electron mobility and electrical conductivity restrict their potential device performance,such as perovskite solar cells(PSCs).Herein,we successfully enhanced the electric properties and morphology of phenyl-C61-butyric acid methyl ester(PCBM)by n-doping it with a benzimidazoline derivative,9-(1,3-dimethyl-2,3-dihydro-1H-benzoimidazol-2-yl)-julolidine(JLBI-H)via a solution *** found the n-doping can not only improve the conductivity and optimize the band alignment but also enable the PCBM to have a constantly strong charge extraction ability in a wide temperature from 173 to 373 K,which guarantees a stable photovoltaic performance of the corresponding PSCs under a wide range of operating *** the JLBI-H-doped PCBM,we improved the efficiency from 17.9%to 19.8%,along with enhanced stability of the nonencapsulated devices following the aging protocol of ISOS-D-1.

关键词： charge extraction electron mobility n-doping PSCs wide operation temperature

来源：评论

学校读者我要写书评

暂无评论

Multi Scale SAR Image Target Detection Algorithm Based on RT-DETR 5

Multi Scale SAR Image Target Detection Algorithm Based on RT...

引用

5th International Conference on Consumer Electronics and Computer Engineering, ICCECE 2025

作者： Zhao, Wenhao Zheng, Gengsheng School of Computer Science and Engineering School of Artificial Intelligence Hubei Key Laboratory of Intelligent Robot Wuhan Institute of Technology Wuhan China

ISBN: (纸本)9798331533113

To address low detection accuracy in SAR images due to complex backgrounds, large scale variations, and small targets, an improved algorithm SRA-DETR based on RT-DETR is proposed. It uses repBlock on four backbone branches to reduce parameters and enhance speed, incorporates a self-Attention vision transformer for feature similarity extraction, and employs SE-CBAM for small target detection to suppress background interference. Adaptive path downsampling improves feature retention and background filtering compared to nearest neighbor methods. SRA-DETR decreases parameters by 40% and computational complexity by 20%, achieving aP50 of 96.6% and increasing mAP from 77.9% to 80.1% over the original RT-DETR. © 2025 IEEE.

关键词： Attention mechanism Downsampling Feature extraction Remote sensing images

来源：评论

学校读者我要写书评

暂无评论

Gesture Recognition with Complex Background Based on Improved Convolutional Neural Network 21

Gesture Recognition with Complex Background Based on Improve...

引用

5th International Conference on Electronic Information Technology and Computer Engineering, EITCE 2021

作者： Li, Lei Wei, Wei Chen, Deng Ou-Yang, Wei Jiang, Haochen Hubei Province Key Laboratory of Intelligent Robot Wuhan Institute of Technology Wuhan Hubei China

ISBN: (纸本)9781450384322

Vision based gesture recognition is a research hotspot in the field of human-computer interaction. Existing techniques are inefficient to deal with situations of drastic illumination changes and complex background. This paper is based on the basis of edge detection, individual difference is fused for threshold segmentation to improve the accuracy of hand cutting. In the stage of feature extraction and classification, constructing basic convolutional neural network and support vector machine is used for gesture recognition of geographic information in complex environment. Experiments were carried out on 14 gestures in complex background and skin color like scenes, and the average recognition rate was 98.73%. Our method can effectively segment and recognize gestures in various complex backgrounds and skin color backgrounds, meet the needs of engineering projects, with low hardware requirements. © 2021 ACM.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Optimised design of cross-shaft parameters based on response surface optimisation model with MOGA

引用

International Journal of Wireless and Mobile Computing 2024年第2期26卷 198-206页

作者： Xiong, Sijie Xie, Yuanmin Zou, Chunlong Mao, Yanfeng Cao, Yongcheng Key Laboratory of Metallurgical Equipment and Control Technology of Ministry of Education Wuhan University of Science and Technology Hubei Wuhan China Research Centre for Biomimetic Robot and Intelligent Measurement and Control Wuhan University of Science and Technology Hubei Wuhan China Precision Manufacturing Research Institute Wuhan University of Science and Technology Hubei Wuhan China Hubei University of Automotive Technology Hubei Shiyan China Technology Research and Development Hubei Jingmen Wusan Machinery Equipment Manufacturing Co. Ltd. Jingmen Hubei China

Cross-shaft is the core component of the cross-type universal coupling and has a vital transmission function. This paper proposes Sparse Grid and the Kriging interpolation to construct a response surface model to solve the problem of long design cycles, low reliability and high susceptibility to cross-shaft fatigue deformation. The critical dimensions of the cross-shaft are used as design variables, and the maximum equivalent force and deformation are reduced as the optimisation objective. Then experimental points are obtained by Sparse Grid Initialisation and then the response surface model is obtained with high accuracy by Kriging interpolation, and finally, the optimised design of the cross-shaft is completed using MOGA in this paper. Compared with the original structural solution, the maximum deformation of the cross-shaft is reduced by 0.4717 mm (22.35%), the maximum equivalent force is reduced by 130.35 Mpa (17.21%) and the mass increased by only 4.17%. © 2024 Inderscience Enterprises Ltd.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Industrial Parts Detection Based on Deep Learning 21

Industrial Parts Detection Based on Deep Learning

引用

5th International Conference on Electronic Information Technology and Computer Engineering, EITCE 2021

作者： Jiang, Haochen Wei, Wei Chen, Deng Feng, Chenguang Hubei Province Key Laboratory of Intelligent Robot Wuhan Institute of Technology Wuhan Hubei China

ISBN: (纸本)9781450384322

Object detection is the core technique of industrial sorting based on machine vision. However, traditional object detection algorithm is difficult to solve sorting tasks in complex industrial scenarios. To this end, this paper proposes an industrial parts detection network based on deep learning. This method is to use the object detection network to detect the parts on the conveyor belts and obtain the category and location information of the parts. In order to improve the network's detection accuracy of multi-scale parts, this paper use the K-Means algorithm to redesign the size of the anchor. In addition, we construct a private dataset for model training and use dataset augmentation to expand our dataset, then using the pre-trained weights based on the VOC dataset for transfer learning. Experiments based on self-constructed dataset show that the mAP of our method achieves 97.03%, which can satisfy the requirements of practical applications. © 2021 ACM.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Electrical Cabinet Parts Detection Based on Deep Learning 21

Electrical Cabinet Parts Detection Based on Deep Learning

引用

5th International Conference on Electronic Information Technology and Computer Engineering, EITCE 2021

作者： Feng, Chenguang Wei, Wei Chen, Deng Jiang, Haochen Hubei Province Key Laboratory of Intelligent Robot Wuhan Institute of Technology Wuhan Hubei China

ISBN: (纸本)9781450384322

The detection of electrical cabinet parts is crucial for the production of electrical cabinets. However, detection methods based on machine vision always suffer from the problems of low robustness and accuracy. To solve the problem, this paper proposes an electrical cabinet parts detection method based on deep learning. This method is to uses the object detection model to detect the collected electrical cabinet images and obtain the coordinates and category of the parts. We construct a private dataset to train the model, and use data augmentation to expand the self-constructed dataset. In addition, this method uses transfer learning to accelerate model training. Experiments based on the self-constructed dataset show that the mAP of our method is 94.26%, which can satisfy the requirements of practical applications. © 2021 ACM.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Reverse modelling method of transmission tower based on intelligent identification of key points of point cloud projection

引用

International Journal of Wireless and Mobile Computing 2023年第3-4期24卷 390-399页

作者： He, Fan Hu, Yimin Liu, Yong Li, Guoyang Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering Hubei Province Engineering Technology Research Center for Construction Quality Testing Equipments China Three Gorges University Yichang Hubei China State Grid Shiyan Electric Power Supply Company Transmission Maintenance Branch State Grid Shiyan Hubei China

At present, neither image-based oblique photographic modelling nor laser point cloud modelling can generate high-precision solid models of transmission towers. In this paper, a fast reverse modelling method based on deep learning for the identification of key points of the transmission tower point cloud plane projection and high accuracy is proposed. This method first transforms the 3D point cloud data into two-dimensional image data through orthographic projection, then uses CNN and LSTM two deep learning networks to predict the number of variable key points in the image and finally calculates the corresponding coordinates in 3D space through the key points in the twodimensional image. Through this method, the size and position of transmission tower components are obtained, which can realise fast and high-precision reverse modelling of transmission tower. © 2023 Inderscience Enterprises Ltd.

关键词： Computerized tomography

来源：评论

学校读者我要写书评

暂无评论

A CSMA/CA based MAC protocol for hybrid Power-line/Visible-light communication networks:Design and analysis

引用

Digital Communications and Networks 2024年第2期10卷 481-497页

作者： Sheng Hao Huyin Zhang Fei Yang Chenghao Li Jing Wang School of Computer Science Central China Normal UniversityWuhan430079PR China Hubei Key Laboratory of intelligent Robot(Wuhan Institute of Technology) Wuhan430079PR China School of Computer Science Wuhan UniversityWuhan430079China School of Information Science and Engineering Shandong Normal UniversityJinan250000China School of Computer Science Hubei University of TechnologyWuhan430079China

Hybrid Power-line/Visible-light Communication(HPVC)network has been one of the most promising Cooperative Communication(CC)technologies for constructing Smart Home due to its superior communication reliability and hardware *** research on HPVC networks focuses on the performance analysis and optimization of the Physical(PHY)layer,where the Power Line Communication(PLC)component only serves as the backbone to provide power to light Emitting Diode(LED)*** designing a Media Access Control(MAC)protocol remains a great challenge because it allows both PLC and Visible Light Communication(VLC)components to operate data transmission,i.e.,to achieve a true HPVC network *** solve this problem,we propose a new HPC network MAC protocol(HPVC MAC)based on Carrier Sense Multiple Access/Collision Avoidance(CSMA/CA)by combining IEEE 802.15.7 and IEEE 1901 ***,we add an Additional Assistance(AA)layer to provide the channel selection strategies for sensor stations,so that they can complete data transmission on the selected channel via the specified CSMA/CA mechanism,*** on this,we give a detailed working principle of the HPVC MAC,followed by the construction of a joint analytical model for mathematicalmathematical validation of the HPVC *** the modeling process,the impacts of PHY layer settings(including channel fading types and additive noise feature),CSMA/CA mechanisms of 802.15.7 and 1901,and practical configurations(such as traffic rate,transit buffer size)are comprehensively taken into ***,we prove the proposed analytical model has the ***,through extensive simulations,we characterize the HPVC MAC performance under different system parameters and verify the correctness of the corresponding analytical model with an average error rate of 4.62%between the simulation and analytical results.

关键词： Hybrid power-line/Visible light communication (HPVC)networks MAC protocol CSMA/CA IEEE 802.15.7 IEEE 1901 Performance analysis

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：