检索结果-内蒙古大学图书馆

IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems

作者： Jiajun Cheng Yaoyan Wu Weitao Gao Jun Fu Faculty of Robot Science and Engineering Northeastern University Shenyang Liaoning China State Key Laboratory of Dynamic Testing Technology School of Electrical and Control Engineering North University of China Taiyuan Shanxi China

Electronic payments have become the primary mode of payment today, and bank card recognition is widely used in industries such as mobile, mobile banking, and third-party payments. To address issues such as low fault tolerance due to factors such as complex backgrounds, significant perspective distortion that is difficult to recover, and high illumination variation, we propose a Bank Card Number Recognition algorithm based on ASFF + YOLOv7 and Multi-Scale Feature Line Fusion. The algorithm comprises two parts: the front-end dataset generation stage introduces an efficient semi-automatic traditional bank card dataset generation algorithm, which reduces the manual annotation cost while ensuring relative accuracy and significantly improves work efficiency. In the back-end recognition stage, we have improved the traditional deep learning model for the long-tail digit string dataset, achieving a precision of 99.19% and a recall rate of 98.65%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The Resource Optimization Scheduling Algorithm of Ad-hoc Cloud robotics for Complex Collaborative Tasks

The Resource Optimization Scheduling Algorithm of Ad-hoc Clo...

引用

第33届中国控制与决策会议

作者： Jiang Jingqi Ji Peng Wang Xianxin Liu Qifeng College of Information Science and Engineering Northeastern University Faculty of Robot Science and Engineering Northeastern University

Multi-robotics cooperation to complete specific complex tasks is the key problem in the field of robotics research,and ad-hoc cloud technology provides a good computing power carrier for multi robot *** this paper,an ad-hoc cloud resource scheduling algorithm based on reinforcement learning is ***,the task scheduling process is modeled,and the resource scheduling model and resource scheduling performance index are ***,a resource prescheduling algorithm based on Q-Learning is designed to pre schedule the simulated task *** this basis,a resource optimal scheduling model based on DQN is proposed,which uses neural network instead of Q-table to realize the evaluation and learning of ad-hoc cloud *** can be seen from the experimental results that the algorithm proposed in this paper effectively realizes the resource scheduling task of ad-hoc cloud platform,and can provide powerful technical support for multi robot collaborative sharing computing.

关键词： Ad-hoc cloud robotics Resource optimization scheduling Q-learning DQN sharing computing

来源：评论

学校读者我要写书评

暂无评论

Real-time 3D Single Object Tracking with Transformer

arXiv

引用

arXiv 2022年

作者： Shan, Jiayao Zhou, Sifan Cui, Yubo Fang, Zheng The Faculty of Robot Science and Engineering Northeastern University Shenyang China Science and Technology on Near-Surface Detection Laboratory Wuxi China

LiDAR-based 3D single object tracking is a challenging issue in robotics and autonomous driving. Currently, existing approaches usually suffer from the problem that objects at long distance often have very sparse or partially-occluded point clouds, which makes the features extracted by the model ambiguous. Ambiguous features will make it hard to locate the target object and finally lead to bad tracking results. To solve this problem, we utilize the powerful Transformer architecture and propose a Point-Track-Transformer (PTT) module for point cloud-based 3D single object tracking task. Specifically, PTT module generates fine-tuned attention features by computing attention weights, which guides the tracker focusing on the important features of the target and improves the tracking ability in complex scenarios. To evaluate our PTT module, we embed PTT into the dominant method and construct a novel 3D SOT tracker named PTT-Net. In PTT-Net, we embed PTT into the voting stage and proposal generation stage, respectively. PTT module in the voting stage could model the interactions among point patches, which learns context-dependent features. Meanwhile, PTT module in the proposal generation stage could capture the contextual information between object and background. We evaluate our PTT-Net on KITTI and NuScenes datasets. Experimental results demonstrate the effectiveness of PTT module and the superiority of PTT-Net, which surpasses the baseline by a noticeable margin, ∼10% in the Car category. Meanwhile, our method also has a significant performance improvement in sparse scenarios. In general, the combination of transformer and tracking pipeline enables our PTT-Net to achieve state-of-the-art performance on both two datasets. Additionally, PTT-Net could run in real-time at 40FPS on NVIDIA 1080Ti GPU. Our code is open-sourced for the research community at https://***/shanjiayao/PTT. © 2022, CC BY.

关键词： Optical radar

来源：评论

学校读者我要写书评

暂无评论

Distributed adaptive protocols design based load frequency control for multi-area interconnected power system

Distributed adaptive protocols design based load frequency c...

引用

第40届中国控制会议

作者： Shengnan Zhang Zhenwei Liu Huaguang Zhang Junyi Wang College of Information Science and Engineering Northeastern University Faculty of Robot Science and Engineering Northeastern University

This paper studies the load frequency control（LFC） problem of the multi-area interconnected power system. A fully distributed adaptive design based LFC scheme is used based on the idea of multi-agent system（MAS）. Firstly, a model transformation on the multi-area interconnected power system is proposed so that a new system model with external disturbances is obtained in term of MAS. Then, an adaptive leader-following consensus protocol is used, which do not need any information about communication topology and the upper bound of external disturbances. Finally, the case studies are performed to verify the effectiveness of the proposed schemes.

关键词： Load frequency control Model transformation Adaptive leader-following consensus protocol

来源：评论

学校读者我要写书评

暂无评论

Study on a NiTiHfTa shape memory alloy with high-pressure torsion and subsequent annealing 9

Study on a NiTiHfTa shape memory alloy with high-pressure to...

引用

9th International Conference on Mechanical engineering, Materials, and Automation Technology, MMEAT 2023

作者： Zhang, Jintao Hu, Peng Wang, Shibo Zhang, Yu Huang, Yi Ding, Hua School of Materials Science and Engineering Northeastern University Shenyang110819 China Key Laboratory of Light Structural Materials of Liaoning Province Northeastern University Shenyang110819 China Department of Design and Engineering Faculty of Science and Technology Bournemouth University Dorset PooleBH12 5BB United Kingdom Materials Research Group Department of Mechanical Engineering University of Southampton SouthamptonSO17 1BJ United Kingdom

ISBN: (纸本)9781510668584

An alloy with the composition of 49.6Ni-35.4Ti-9Hf-6Ta (at%) was processed by high-pressure torsion (HPT) and post-HPT annealing treatment. The microhardness of HPT-processed samples increased obviously, and amorphous feature appeared in 2 turns sample. The microhardness further increased and amorhozation was enhanced in 16 turns sample. After annealing at 750 ℃ for 3h, almost full crystallization occurs in 16 turns sample. In-situ high temperature X-ray diffraction experiment reveals that martensite to austenite transformation took place, indicating the alloy would exhibit SMA effect. © 2023 SPIE.

关键词： Annealing

来源：评论

学校读者我要写书评

暂无评论

Incremental 2D Grid Map Generation from RGB-D Images 11

Incremental 2D Grid Map Generation from RGB-D Images

引用

11th International Conference on Electronics, Communications and Networks, CECNet 2021

作者： Ye, Tingfeng Zhang, Juzhong Wan, Yingcai Cui, Ze Yang, Hongbo School of Mechatronic Engineering and Automation Shanghai University Shanghai China Suzhou Institute of Biomedical Engineering and Technology Chinese Academy of Science Suzhou China Dept. Faculty of Robot Science and Engineering Northeastern University Shenyang China

ISBN: (纸本)9781643682402

In this paper, we extend RGB-D SLAM to address the problem that sparse map-building RGB-D SLAM cannot directly generate maps for indoor navigation and propose a SLAM system for fast generation of indoor planar maps. The system uses RGBD images to generate positional information while converting the corresponding RGBD images into 2D planar lasers for 2D grid navigation map reconstruction of indoor scenes under the condition of limited computational resources, solving the problem that the sparse point cloud maps generated by RGB-D SLAM cannot be directly used for navigation. Meanwhile, the pose information provided by RGB-D SLAM and scan matching respectively is fused to obtain a more accurate and robust pose, which improves the accuracy of map building. Furthermore, we demonstrate the function of the proposed system on the ICL indoor dataset and evaluate the performance of different RGB-D SLAM. The method proposed in this paper can be generalized to RGB-D SLAM algorithms, and the accuracy of map building will be further improved with the development of RGB-D SLAM algorithms. © 2022 The authors and IOS Press.

关键词： Navigation

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of YOLO Models in Varying Conditions: A Study on Object Detection and Tracking

Performance Evaluation of YOLO Models in Varying Conditions:...

引用

International Conference on Computer and Applications (ICCA)

作者： Ahmed S. Mekled Slim Abdennadher Omar M. Shehata Multi-Robot Systems (MRS) Research Group Cairo Egypt Faculty of Engineering and Materials Science German University Cairo Egypt Faculty of Engineering German University Cairo Egypt Computer Science Faculty of Informatics German International University Egypt Faculty of Engineering Ain Shams University Cairo Egypt

ISBN: (数字)9798350367560

ISBN: (纸本)9798350367577

Object detection and tracking are essential components in autonomous systems, enabling accurate environmental perception and real-time decision-making. Despite the widespread use of advanced frameworks such as YOLO, RCNN, SSD, FPN, and RetinaNet in applications like autonomous driving and surveillance, these systems often experience degraded performance in images with poor lighting conditions caused by adverse weather and other external factors. Recent developments have introduced various deep-learning and image-processing techniques to address these challenges. This paper provides an extensive evaluation of three state-of-the-art object detection models-YOLOv5, YOLOv8, and YOLOv9 under diverse experimental conditions, including varying confidence thresholds (50%, 60%, 70%, and 80%), different object poses, lighting conditions (day and night), and camera configurations (static and dynamic). The evaluation is conducted using key performance metrics such as mean Average Precision (µAP), Intersection over Union (IoU), Multiple Object Tracking Accuracy (MOTA), Multiple Object Tracking Precision (MOTP), Identity F1 score (IDF1), precision, and recall. The study offers a comprehensive analysis of the models' performance and suitability for different real-world applications, delivering practical insights for model selection and deployment. Additionally, it highlights potential areas for future research aimed at enhancing model robustness and effectiveness in challenging environments.

关键词： YOLO Performance evaluation Analytical models Technological innovation Accuracy Surveillance Lighting Real-time systems Robustness Object tracking

来源：评论

学校读者我要写书评

暂无评论

UGNA-VPR: A Novel Training Paradigm for Visual Place Recognition Based on Uncertainty-Guided NeRF Augmentation

arXiv

引用

arXiv 2025年

作者： Shen, Yehui Zhang, Lei Li, Qingqiu Zhao, Xiongwei Wang, Yue Lu, Huimin Chen, Xieyuanli College of Intelligence Science and Technology National University of Defense Technology China Faculty of Robot Science and Engineering Northeastern University China School of Electronic and Information Engineering Harbin Institute of Technology Shenzhen China State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and Control Zhejiang University China SIASUN Robot& Automation Co. Ltd China School of Computer Science Fudan University China

Visual place recognition (VPR) is crucial for robots to identify previously visited locations, playing an important role in autonomous navigation in both indoor and outdoor environments. However, most existing VPR datasets are limited to single-viewpoint scenarios, leading to reduced recognition accuracy, particularly in multi-directional driving or feature-sparse scenes. Moreover, obtaining additional data to mitigate these limitations is often expensive. This paper introduces a novel training paradigm to improve the performance of existing VPR networks by enhancing multi-view diversity within current datasets through uncertainty estimation and NeRF-based data augmentation. Specifically, we initially train NeRF using the existing VPR dataset. Then, our devised self-supervised uncertainty estimation network identifies places with high uncertainty. The poses of these uncertain places are input into NeRF to generate new synthetic observations for further training of VPR networks. Additionally, we propose an improved storage method for efficient organization of augmented and original training data. We conducted extensive experiments on three datasets and tested three different VPR backbone networks. The results demonstrate that our proposed training paradigm significantly improves VPR performance by fully utilizing existing data, outperforming other training approaches. We further validated the effectiveness of our approach on self-recorded indoor and outdoor datasets, consistently demonstrating superior results. Our dataset and code have been released at https://***/nubot-nudt/UGNA-VPR. Copyright © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A robot Visual SLAM Algorithm Based on Cloud Computing 2020

A Robot Visual SLAM Algorithm Based on Cloud Computing

引用

2020 International Conference on Computing, Networks and Internet of Things, CNIOT 2020

作者： Ji, Peng Liu, Qifeng Chu, Hao Northeastern University Faculty of Robot Science and Engineering Shenyang Liaoning China

ISBN: (纸本)9781450377713

Visual SLAM is becoming a hot spot mobile robot navigation. When executing SLAM tasks, traditional robots have many shortcomings, Huge data processing and computing tasks, which consumed much storage and computing resource. There is a high demand for storage and computing resources, which is in contradiction with the limited resources of the airborne hardware. Based on the advantages of cloud computing's computing resource sharing mechanism, this thesis combines robot with cloud computing to research the mobile robot's navigation using visual SLAM. Considering that robot visual SLAM is a computationally intensive task, a cloud computing service platform for robot Los SLAM is constructed. The platform is based on Openstack management platform to build a virtual environment, and uses Docker container technology to complete the design of functional service image. The full use of the platform performance makes the application of sophisticated and advanced algorithms in low-cost robots possible. On this basis, an improved visual SLAM algorithm based on ORB features is designed to realize the robot's effective perception for the unknown environment on the cloud service platform. The results of the algorithm is verified that the service platform can effectively unload the tasks of the robot to the cloud, and reduce the hardware performance requirements of the robot. At the same time, modular functional service forms can expand the functions and use scenarios of robots, break the limits of traditional robots dealing with a single scene, and help to enhance the intelligence of robots. © 2020 ACM.

关键词： Containers

来源：评论

学校读者我要写书评

暂无评论

Difference in formation of plasma electrolytic oxidation coatings on MgLi alloy in comparison with pure Mg

引用

Journal of Magnesium and Alloys 2021年第5期9卷 1745-1760页

作者： Ting Wu Carsten Blawert Xiaopeng Lu Maria Serdechnova Mikhail L.Zheludkevich Institute of Surface Science Helmholtz-Zentrum Hereon21502 GeesthachtGermany Shenyang National Laboratory for Materials Science Northeastern University110819 ShenyangChina Institute for Materials Science Faculty of EngineeringKiel UniversityKaiserstrasse 224143 KielGermany

In order to study the substrate lattice structure(Li addition)on the growth of plasma electrolytic oxidation(PEO)coatings,Mg Li alloy(11.36 wt.%of Li,cubic)and pure Mg(hexagonal)were treated under a pulsed direct PEO mode in a phosphate electrolyte for different periods of *** results revealed that the presence of Li and Li-rich phases in the cubic Mg alloy seems to be essential for the treatment result rather than the original lattice structure.A modified discharge behavior of Mg Li alloy finally led to a different microstructure of the *** unstable coatings of Mg Li alloy tended to dissolve rapidly though shared the similar composition to that of pure *** was incorporated only in the primary conversion products at the interface of coating/Mg *** spite of the advanced efficiency of energy input during processing,the more porous and thinner PEO coatings on the Mg Li alloy were less resistant to abrasion and corrosion.

关键词： Plasma electrolytic oxidation Magnesium lithium alloy Pure magnesium Microstructure

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：