检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

18,307 篇 会议
195 篇 期刊文献
31 册 图书

馆藏范围

18,530 篇 电子文献
3 种 纸本馆藏

日期分布

学科分类号

13,356 篇 工学
- 9,706 篇 计算机科学与技术...
- 6,577 篇 软件工程
- 3,574 篇 控制科学与工程
- 2,457 篇 信息与通信工程
- 2,299 篇 电气工程
- 1,723 篇 光学工程
- 1,509 篇 机械工程
- 1,119 篇 生物工程
- 905 篇 电子科学与技术（可...
- 859 篇 生物医学工程（可授...
- 782 篇 仪器科学与技术
- 571 篇 动力工程及工程热...
- 537 篇 交通运输工程
- 507 篇 安全科学与工程
- 502 篇 材料科学与工程（可...
- 454 篇 化学工程与技术
- 342 篇 土木工程
- 335 篇 网络空间安全
5,342 篇 理学
- 2,349 篇 物理学
- 2,276 篇 数学
- 1,230 篇 生物学
- 594 篇 统计学（可授理学、...
- 588 篇 系统科学
- 444 篇 化学
2,414 篇 管理学
- 1,719 篇 管理科学与工程(可...
- 822 篇 图书情报与档案管...
- 682 篇 工商管理
1,085 篇 医学
- 962 篇 临床医学
- 556 篇 基础医学(可授医学...
- 362 篇 药学(可授医学、理...
362 篇 法学
258 篇 经济学
249 篇 农学
216 篇 教育学
63 篇 军事学
25 篇 艺术学
20 篇 文学
3 篇 哲学

主题

1,580 篇 computer vision
361 篇 deep learning
314 篇 computer archite...
283 篇 cameras
259 篇 computational mo...
251 篇 object detection
241 篇 control systems
236 篇 computer science
217 篇 image segmentati...
214 篇 feature extracti...
209 篇 internet of thin...
187 篇 access control
174 篇 machine vision
158 篇 neural networks
134 篇 real-time system...
132 篇 face recognition
131 篇 process control
130 篇 data mining
128 篇 support vector m...
121 篇 visualization

机构

49 篇 school of contro...
47 篇 chitkara univers...
46 篇 school of comput...
29 篇 maharishi school...
24 篇 karnataka bangal...
21 篇 school of comput...
19 篇 maharishi school...
17 篇 chitkara univers...
17 篇 college of compu...
15 篇 school of comput...
14 篇 dept. of compute...
14 篇 chitkara univers...
14 篇 university of ch...
14 篇 college of compu...
13 篇 school of comput...
12 篇 school of comput...
12 篇 centre of interd...
12 篇 school of comput...
12 篇 school of comput...
11 篇 school of comput...

作者

19 篇 wang lei
18 篇 li yang
17 篇 wang wei
16 篇 yang yang
14 篇 liu yang
13 篇 wang hui
12 篇 wang ping
12 篇 wang jian
12 篇 sato jun
11 篇 zhang tao
11 篇 sakaue fumihiko
11 篇 zhang lei
11 篇 huang tinglei
11 篇 liu lei
11 篇 li bo
10 篇 lei wang
10 篇 li xin
10 篇 wang jing
10 篇 li li
9 篇 ahmad jalal

语言

17,978 篇 英文
448 篇 其他
115 篇 中文
16 篇 俄文
7 篇 西班牙文
2 篇 法文
2 篇 土耳其文
1 篇 德文

检索条件"任意字段=Proceedings of the 3rd International Conference on Control and Computer Vision"

共 18533 条记录，以下是4921-4930 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

Design of RFID Access control System Based on Raspberry Pie

Design of RFID Access Control System Based on Raspberry Pie

引用

Signal Processing, Communications and Engineering Management conference (ISPCEM), international

作者： Yu Haixia Xu Yifan Zhang Hanze Wang Zhenyu City Institute Dalian University of Technology Dalian China

This paper focuses on the research background and status of the system design of RAFID access control based on raspberry pie, the construction of hardware circuits, the working principle of each module, the design of software programs and the process of physical debugging. The main reason for setting up the topic is to change the original human guard. Although the original human guard was flexible, but the irreversible personnel mobilization could not be quickly adjusted, resulting in management loopholes. The modern access control system not only reduces labor costs, but also makes flow management more standardized. In this paper, through the detection of face feature information and RFID card identification code, the data collected is transmitted to the raspberry pie through the trigger module (photo module and RFID module), and the raspberry dispatch database or photo library is compared and verified. If the match is successful, it will also be transferred to the computer to display the measured results, and then let the driver module operate to open the valve. This raspberry pie design raspberry pie as the core module, the function of RFID plus face recognition is the innovation of this access system, as long as one of the two recognition successes can open the door valve. This design, through the face recognition principle, RFID recognition principle, WiFi communication methods and other aspects of mastery and analysis, has planned and designed to complete the convergence between various modules, and finally completed the design, to achieve access control systems of two recognition modes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

YOLOv8-Powered Real-Time Car Damage Detection

YOLOv8-Powered Real-Time Car Damage Detection

引用

Intelligent Data Communication Technologies and Internet of Things (IDCIoT), international conference on

作者： Yogeshwaran S Ramith Jagathese J R. Vasanthi CSE Department St. Joseph's Institute Of Technology Chennai Tamil Nadu India

ISBN: (数字)9798331527549

ISBN: (纸本)9798331527556

The increased interest in automated and precise vehicle damage detection tasks has influenced the advances of deep learning and computer vision technologies. This research presents a novel method for automatic vehicle damage assessment based on YOLOv8, one of the latest and powerfull detection models. The model's aim is to assist users in inspecting vehicles in cases where different category of damage such as broken lights, door and others are present. It is done by accurately identifying and classifying the damages without depending on manual effort which is produce issues like inaccurate and time consuming. For eight image damage categories extensive dataset has been prepared, that was used for modeling. To achieve good-quality models, the Roboflow tool was employed for the purpose of picture resizing and augmentation, which assures high-quality training and therefore enhances models. As the main tool for damage detection, YOLOv8 has also been trained over 5000 epochs to detect more complex images. The cumulated metrics include mean Average Precision, precision, and recall. From the data collected, it was established that the YOLOv8 model has been efficient in detecting damages in vehicles with enhanced ability than there was in previous versions of the model. This automated solution is particularly promising for use in the insurance and automobile damage assessment industries as it makes damage assessments more accurate and faster. There are future applications for this model and also made suggestions including increasing the dataset to account for more damage types and using techniques like transfer learning to increase the accuracy of the system.

关键词： Training Deep learning computer vision Accuracy Computational modeling Transfer learning Object detection Data models Real-time systems Automobiles

来源：评论

学校读者我要写书评

暂无评论

Implementation Of M-A-C Convention For Wireless AD HOC

Implementation Of M-A-C Convention For Wireless AD HOC

引用

Advance Computing and Innovative Technologies in Engineering (ICACITE), international conference on

作者： Yogesh Kumaran S Sunanda Das Department of Computer Science and Engineering Faculty of Engineering and Technology Jain (Deemed-to-be University) Bangalore India

In this post, we discuss how to boost quality when faced with high loads and rapid diminishing. In order to improve bandwidth utilization and delay efficiency, a methodology was presented in the Transactions of the IEEE conference on Connectivity (ICC), that employed either a sensible path or a relayed path depending on rate comparability. Unfortunately, since direct route or intermediary path dependability are less reliable amid dimming circumstances, speed decreases. was demonstrated to outperform due to higher communication stability offered by the secondary relay line in terms of typical capacity and latency metrics. Despite being superior to the direct way, only utilises the broadcast path as a supplementary alternative path, thus it is unable to benefit significantly from the relay method's 4 percentage. The collaborating Proposed method we progress in this editorial, called extremely rapid relay-based conscientious, researchers estimate the transceiver ratio of the starting point, reroute, and citation links and seems to be using broadcaster remains a central to consistently select between the relay path and the successful and prosperous for feedback and control and delay achievements.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Image-based Road Marking Classification and Vector Data Derivation from Mobile Mapping 3D Point Clouds 16

Image-based Road Marking Classification and Vector Data Deri...

引用

16th international Joint conference on computer vision, Imaging and computer Graphics Theory and Applications (VISIGRAPP) / 16th international conference on computer vision Theory and Applications (VISAPP)

作者： Wolf, Johannes Pietz, Tobias Richter, Rico Discher, Soeren Doellner, Juergen Univ Potsdam Fac Digital Engn Hasso Plattner Inst Potsdam Germany

ISBN: (纸本)9789897584886

Capturing urban areas and infrastructure for automated analysis processes becomes ever more important. Laserscanning and photogrammetry are used for scanning the environment in highly detailed resolution. In this work, we present techniques for the semantic classification of 3D point clouds from mobile mapping scans of road environments and the detection of road markings. The approach renders 3D point cloud input data into images for which U-Net as an established image recognition convolutional neural network is used for the semantic classification. The results of the classification are projected back into the 3D point cloud. An automated extraction of vector data is applied for detected road markings, generating detailed road marking maps. Different approaches for the vector data generation are used depending on the type of road markings, such as arrows or dashed lines. The automatically generated shape files created by the presented process can be further used in various GIS applications. Our results of the implemented out-of-core techniques show that the approach can efficiently be applied on large datasets of entire cities.

关键词： GIS LiDAR Point Cloud Rendering Digital Image Analysis

来源：评论

学校读者我要写书评

暂无评论

End-to-End Encryption for Chat App with Dynamic Encryption Key 3

End-to-End Encryption for Chat App with Dynamic Encryption K...

引用

3rd international conference on Advances in Computing, Communication control and Networking, ICAC3N 2021

作者： Prabhune, Samira Sharma, Sonal Computer Science Jain University Bangalore India

ISBN: (纸本)9781665438117

With millions of users' End-to-End encryption has been converted into an ordinary characteristic in popular mobile chat relevance's (apps). Most imperative chat apps have added end-to-end encryption characteristics in the two years, several mutually with Facebook Messenger, and What's App. This paper illustrates how dissimilar concerns in an app can add up to the probable for severe vectors adjacent to end-to-end solitude despite their creature several layers of security. To overcome the app is anticipated in the chats are secured by the dynamic key encryption by md5 algorithm. Only user 1 and user 2 are going to know the message this secures the chats from unwanted users. In the middle attacker and server, those who are trying to attack will get to know the garbage value of message. The XOR operation is used for encrypting the message and to provide security for user1 and user2 of the message. The md5 is utilized as key the key is engendered for every message by three parameters and this gives next altitude of security to the chat app. If the key is hacked by the attacker, the second key for the message is tricky to hack this augment the involvedness of the app and secures much more. In exacting, the app illustrates how a dynamic key is utilized for encryption which protects the message with facilitate of a dynamic key. It secures the chat app by generating the key dynamically. © 2021 IEEE.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

R2I: A Deep Fault Diagnosis Semantic Segmentation System Based on Knowledge Distillation in Photovoltaic Panels

R2I: A Deep Fault Diagnosis Semantic Segmentation System Bas...

引用

Energy, Power and Electrical Engineering (EPEE), international conference on

作者： Xiaoyanghao Lei Kai Ma Junyi Zhao Department of Electrical and Electronic Engineering University of Liverpool Liverpool United Kingdom Department of Computer Science Xi'an Jiaotong-liverpool University Suzhou China

With the growing adoption of photovoltaic power systems, ensuring the reliable and efficient operation of photovoltaic panels is critical. However, defects such as cracks, dirt, and failures are common during long-term use. Manual inspection is subjective and resource intensive. Recent computer vision and machine learning techniques present new opportunities for automated diagnosis. This paper reviews photovoltaic panel defect detection using deep learning. Two main approaches exist: visible light and infrared imaging. Earlier works employed object detection with lower precision. Newer methods use semantic segmentation for pixel-level accuracy. However, most focus on single modalities and datasets. Transfer learning across diverse data could improve generalization. Few works estimate defect areas, needed for automated analysis. This paper proposes a dual-modality semantic segmentation approach with knowledge transfer learning. It shares representations across visible and infrared datasets via distillation. A lightweight network reduces parameters and computations for deployment. Soft targets provide latent features transferable to new data. An algorithm estimates defect area proportions to assess hazard levels. The multi-modal transferable learning system aims to advance automated, accurate photovoltaic panel defect diagnosis. Key innovations include tackling insufficient data via shared knowledge, reducing model complexity, improving generalization, and pioneering defect severity assessment. This can facilitate intelligent photovoltaic inspection to ensure system health, safety and longevity.

关键词：

来源：评论

学校读者我要写书评

暂无评论

3D Object Detection with Normal-map on Point Clouds 16

3D Object Detection with Normal-map on Point Clouds

引用

作者： Miao, Jishu Hirakawa, Tsubasa Yamashita, Takayoshi Fujiyoshi, Hironobu Chubu Univ 1200 Matsumoto Cho Kasugai Aichi Japan

ISBN: (纸本)9789897584886

In this paper, we propose a novel point clouds based 3D object detection method for achieving higher-accuracy of autonomous driving. Different types of objects on the road has a different shape. A LiDAR sensor can provide a point cloud including more than ten thousand points reflected from object surfaces in one frame. Recent studies show that hand-crafted features directly extracted from point clouds can achieve nice detection accuracy. The proposed method employs YOLOv4 as feature extractor and gives Normal-map as additional input. Our Normal-map is a three channels bird's eye view image, retaining detailed object surface normals. It makes the input information have more enhanced spatial shape information and can be associated with other hand-crafted features easily. In an experiment on the KITTI 3D object detection dataset, it performs better than conventional methods. Our method can achieve higher-precision 3D object detection and is less affected by distance. It has excellent yaw angle predictability for the object, especially for cylindrical objects like pedestrians, even if it omits the intensity information.

关键词： Object Detection Deep Learning Point Cloud Processing Autonomous Vehicles

来源：评论

学校读者我要写书评

暂无评论

A Web Application for Customer Segment based Black Friday Sales Forecast 3

A Web Application for Customer Segment based Black Friday Sa...

引用

3rd international conference on Advances in Computing, Communication control and Networking, ICAC3N 2021

作者： Patil, Tanisha G. Venkatesh, Varsha Patil, Vanitha R. Purohit, Kanchan. A. Karwa, Shivangi Bangalore Institute of Technology Computer Science and Engineering Bengaluru India

ISBN: (纸本)9781665438117

The study shows how factors internal to the sales forecasting process can introduce bias. Black Friday is upon us, and retailers everywhere stock up on inventory at dramatic discounts. The products aren't accessible to some clients due to poor arrangements, despite good sales. Managing a small staff and keeping potential customers in mind is more of a concern for shopkeepers. Despite some attempts at effective inventory management and sales forecast, the results have not been favorable. A prediction model has proven effective in managing this issue. By analyzing the previous spending patterns of clients, a precise and efficient algorithm can predict future spending. A variety of data analysis strategies, including regressors and classifiers, are employed to evaluate specificity and accuracy. Then, different algorithms are used to implement machine learning techniques. An extensive report of sales for Black Friday 2019 has been compiled. To calculate the volume, we took into account various factors, including age group, occupation, product category, city, etc. A store that wishes to predict sales could do so from this information. We have deployed our Flask-based user interface after determining which model is the best fit. © 2021 IEEE.

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Ml Algorithms & Stream Lit Web Application 3

Comparative Analysis of Ml Algorithms & Stream Lit Web Appli...

引用

3rd international conference on Advances in Computing, Communication control and Networking, ICAC3N 2021

作者： Shukla, Saurabh Maheshwari, Arushi Johri, Prashant Galgotias University School of Computer Science and Engineering Greater Noida India

ISBN: (纸本)9781665438117

Prediction of Approval of Consumer Personal Loans Applications using different Machine Learning (ML) Algorithms and convert it into a web app by using stream lit library in a very simple and efficient way. Out of the available ML algorithms a comparative analysis is performed to check which one proves out to be the best possible with maximum accuracy. This project basically provides the assumption or probability of approval or denial of the personal loan any candidate applies for. As soon as the customer provides in his or her details and all domains that are required. Various models are used to test whether the given details of the customer are okay to provide loan or not. If yes, it displays a message"loan approved"and further functionalities can be done. Else it displays a message as "Loan denied". Understanding of Test and Train Data. Implementation of steps like Feature Engineering, Feature Selection, Exploratory Data Analysis (EDA), Model Training etc. Usage of different models to train the data like below. LR, RF, XGB. Compares the accuracy from different models. The customer is asked to fill in the details required whoever wishes to apply for the loan. According to the given data if it's suitable and all the conditions are satisfied, the user gets a message related approval of the loan else it displays a message of denial. © 2021 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

iMAP: Implicit Mapping and Positioning in Real-Time 18

iMAP: Implicit Mapping and Positioning in Real-Time

引用

18th IEEE/CVF international conference on computer vision (ICCV)

作者： Sucar, Edgar Liu, Shikun Ortiz, Joseph Davison, Andrew J. Imperial Coll London Dyson Robot Lab London England Imperial Coll London Robot Vis Lab London England

ISBN: (纸本)9781665428125

We show for the first time that a multilayer perceptron (MLP) can serve as the only scene representation in a real-time SLAM system for a handheld RGB-D camera. Our network is trained in live operation without prior data, building a dense, scene-specific implicit 3D model of occupancy and colour which is also immediately used for tracking. Achieving real-time SLAM via continual training of a neural network against a live image stream requires significant innovation. Our iMAP algorithm uses a keyframe structure and multi-processing computation flow, with dynamic information-guided pixel sampling for speed, with tracking at 10 Hz and global map updating at 2 Hz. The advantages of an implicit MLP over standard dense SLAM techniques include efficient geometry representation with automatic detail control and smooth, plausible filling-in of unobserved regions such as the back surfaces of objects.

关键词： 3D modeling

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共500页 << < 489 490 491 492 493 494 495 496 497 498 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：