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

24,598 篇 会议
1,214 篇 期刊文献
40 册 图书
31 篇 学位论文
3 篇 资讯

馆藏范围

25,886 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

15,226 篇 工学
- 8,941 篇 计算机科学与技术...
- 4,787 篇 软件工程
- 4,573 篇 电气工程
- 2,995 篇 信息与通信工程
- 2,102 篇 控制科学与工程
- 1,495 篇 光学工程
- 1,417 篇 机械工程
- 1,341 篇 电子科学与技术（可...
- 1,183 篇 仪器科学与技术
- 1,001 篇 生物医学工程（可授...
- 525 篇 材料科学与工程（可...
- 518 篇 生物工程
- 442 篇 测绘科学与技术
- 411 篇 交通运输工程
- 402 篇 航空宇航科学与技...
- 286 篇 安全科学与工程
- 261 篇 化学工程与技术
- 216 篇 土木工程
5,973 篇 理学
- 4,030 篇 物理学
- 1,462 篇 数学
- 608 篇 生物学
- 404 篇 系统科学
- 328 篇 化学
- 321 篇 统计学（可授理学、...
3,089 篇 医学
- 2,696 篇 临床医学
- 524 篇 特种医学
- 301 篇 基础医学(可授医学...
1,310 篇 管理学
- 978 篇 管理科学与工程(可...
- 374 篇 图书情报与档案管...
- 223 篇 工商管理
175 篇 农学
135 篇 法学
93 篇 教育学
80 篇 经济学
61 篇 军事学
61 篇 艺术学
51 篇 文学
1 篇 哲学

主题

4,700 篇 image processing
2,073 篇 real-time system...
1,756 篇 image segmentati...
1,648 篇 cameras
1,175 篇 real time system...
1,033 篇 image edge detec...
980 篇 feature extracti...
890 篇 image reconstruc...
868 篇 hardware
781 篇 image coding
733 篇 object detection
720 篇 computer vision
701 篇 image color anal...
697 篇 signal processin...
694 篇 field programmab...
574 篇 streaming media
565 篇 image recognitio...
544 篇 image enhancemen...
534 篇 computer archite...
490 篇 image resolution

机构

74 篇 beijing key labo...
38 篇 beijing key labo...
31 篇 school of comput...
27 篇 university of ch...
23 篇 univ chinese aca...
22 篇 school of electr...
21 篇 college of compu...
19 篇 华中科技大学
19 篇 school of inform...
19 篇 beijing institut...
18 篇 hubei province k...
18 篇 ieee
15 篇 shanghai jiao to...
15 篇 radar research l...
13 篇 chitkara univers...
13 篇 university of el...
13 篇 hubei province k...
12 篇 johns hopkins un...
11 篇 university of sc...
11 篇 school of inform...

作者

20 篇 li li
17 篇 jae wook jeon
16 篇 zhang lei
15 篇 liu yang
14 篇 liu jun
13 篇 jie yang
13 篇 wei li
12 篇 p. pirsch
11 篇 li xin
11 篇 kang jin u.
11 篇 li yang
10 篇 xu xin
10 篇 yu wang
10 篇 zeng tao
10 篇 wei liu
10 篇 wang jian
10 篇 hao zhang
10 篇 li tao
10 篇 yang yang
9 篇 wang lei

语言

24,853 篇 英文
576 篇 中文
409 篇 其他
41 篇 土耳其文
6 篇 日文
5 篇 德文
4 篇 葡萄牙文
4 篇 俄文
3 篇 西班牙文

检索条件"任意字段=Conference on Real-Time Image Processing 2007"

共 25886 条记录，以下是381-390 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：

Research on dynamic mosaic method of panoramic view images of articulated vehicle 3

Research on dynamic mosaic method of panoramic view images o...

引用

3rd International conference on Electronics, Electrical and Information Engineering, ICEEIE 2023

作者： Zheng, Zhiyu Deng, Zhiying Zhuang, Shaowei Li, Haoran Ling, Rongchao Eagle Drive Tech Shenzhen CO. LTD 501 5 Floor T1 BeihangBuilding Yuehai Street Nanshan Area Shenzhen518057 China

ISBN: (纸本)9781510671423

Aiming at the problem that there are many blind areas in the perimeter of articulated vehicle, this paper presents a real-time dynamic Mosaic method of multi-vehicle grouping image. Firstly, the image is obtained by fisheye camera for distortion correction, perspective transformation and image Mosaic, and the Mosaic of single car is generated. Then the image of each car is loaded to the graphics processing unit (GPU) by the way of texture mapping to achieve acceleration;Finally, a multi-car image Mosaic model is established and the Angle signal at the articulation point is combined to realize the real-time dynamic Mosaic of multi-car perimeter images. The algorithm is transplanted to the embedded platform and tested on the real vehicle. The results show that the panoramic dynamic Mosaic image based on this method can clearly display the vehicle perimeter objects. © 2023 SPIE.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of a Remote Monitoring Robot System for Solitary Elderly Individuals 39

Design and Implementation of a Remote Monitoring Robot Syste...

引用

39th Youth Academic Annual conference of Chinese-Association-of-Automation (YAC)

作者： Xu, Siyu Wen, Yizhou Haerbin Engn Univ UoS JEI Haerbin Peoples R China

ISBN: (纸本)9798350390780;9798350379228

Addressing the limitations of existing solitary elderly monitoring systems, this paper employs embedded technology, mobile communication technology, and artificial intelligence image processing technology to develop a remote monitoring robot system for the children or guardians of solitary elderly individuals. This robot system aims to overcome the shortcomings of traditional fixed camera monitoring systems, achieving more flexible and efficient remote monitoring of the elderly with a cheaper solution. The hardware part of the robot system uses the CH32V307VCT6 microcontroller as the processor, combined with the HC-SR04 sensor for obstacle avoidance detection, utilizes an LED pillbox to remind the elderly to take their medication, employs a K210 camera module to monitor falling behavior, and achieves wireless communication through the esp8266 module. The hardware programming uses MRS IDE, the server side adopts Bafa Cloud and MQTT transmission protocol, and the mobile app is created through WeChat Developer Tools. At the same time, a vision algorithm based on deep learning is used to determine whether the elderly person has fallen. Test results prove that this intelligent monitoring system for the elderly, based on embedded technology, performs well in terms of real-time performance, accuracy, and stability.

关键词： Remote monitoring robotics embedded technology image processing

来源：评论

学校读者我要写书评

暂无评论

real-time Detection to Avoid Accidents of Interaction Between Humans and Collaborative Robot Using image processing and Machine Learning 11

Real-time Detection to Avoid Accidents of Interaction Betwee...

引用

11th IEEE International conference on Computational Cybernetics and Cyber-Medical Systems, ICCC 2024

作者： Vu, TienDung Nguyen, Duy-Thai Nguyen, Dinh-Tien Vu Toan, Thang Tran, Van-Thuc School of Mechanical Engineering Hanoi University of Science and Technology Precision Engineering & Smart Measurements Lab Hanoi Viet Nam School of Mechanical Engineering Hanoi University of Science and Technology Hanoi Viet Nam

ISBN: (纸本)9798350350142

In recent years, the integration of collaborative robots, also known as cobots, into various industrial and service sectors has shown promising results in increasing productivity and efficiency. However, as these robots work alongside human operators, ensuring the safety of human-robot interactions remains a critical challenge. Accidents arising from unintended collisions or improper robot behavior can have severe consequences for both human operators and the operational environment. The safety condition for humans in the interaction space is always the most important requirement in such systems. Active collision detection to avoid accidents has been a challenge due to the uncertain cognition of humans. In this research, the real-time detection system recognizes human activities in the co-working space by applying image processing and machine learning. The system design is aimed at low cost with 2D cameras but high efficiency with up to 90% correcting detection. The results showed the potential of applying real-time detection in industries to protect humans. © 2024 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

real-time image Recognition System based on Ultra-Low-Latency Spiking Neural Networks 2

Real-time Image Recognition System based on Ultra-Low-Latenc...

引用

2nd IEEE International conference on Signal, Information and Data processing, ICSIDP 2024

作者： Lan, Bin Zhang, Xi Dong, Heng Xu, Ming Beijing Institute of Technology Chongqing Innovation Center Chongqing401120 China Beijing Institute of Technology Beijing100081 China Beijing Institute of Technology Innovation Equipment Research Institute Sichuan TianFu New Area Chengdu610299 China Beijing100081 China

ISBN: (纸本)9798331515669

Remote sensing technology plays an important role in many tasks such as natural disaster detection, weather and climate monitoring and military defense. Currently, remote sensing image processing predominantly relies on Convolutional Neural Networks (CNNs) and Transformers, which require a huge amount of multiplication and addition operations, bringing pressure to the deployment of satellite platforms with strict power consumption and computing power constraints. Spiking neural network (SNN), where the signal is encoded as a spike train instead of analog values, significantly reduces energy consumption compared to traditional artificial neural network. This paper proposes an all-input parallel deployment approach that minimizes or eliminates interactions with off-chip memory, thereby accelerating inference speed and reducing power consumption. We deployed LeNet ultra-low latency SNN on the Xilinx VC709 Board. Experimental results demonstrate that the proposed accelerator achieves a processing speed of 1240 frames per second, an accuracy rate of 98.14%, and a power consumption of only 0.745 Watts, making it well-suited for the low power and real-time requirements of remote sensing tasks. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A real-time processing Algorithm for Multi-Plot Marine Targets based on Radar image Decomposition 12

A Real-Time Processing Algorithm for Multi-Plot Marine Targe...

引用

12th IEEE International conference on Control, Automation and Information Sciences, ICCAIS 2023

作者： Vo, Xung Ha Nguyen, Trung Kien Nguyen, Phung Bao Duong, Van Minh Radar Institute 17 Hoang Sam Str. Cau Giay Hanoi Viet Nam Academy of Military Science and Technology 17 Hoang Sam Str. Cau Giay Hanoi Viet Nam Le Quy Don Technical University 236 Hoang Quoc Viet Hanoi Viet Nam

ISBN: (纸本)9798350328783

This paper investigates a new method for real-time estimating marine target's center of gravity coordinates based on radar image processing to enhance the performance of tracking surface targets without changing the hardware architecture of radar. The proposed method includes two stages: The first is determining an optimal number of layers for radar image decomposition. The second is estimating the target's local maximum regions-plots having the most reflected energies, let us say centroid coordinates, then calculating the target's center of gravity coordinates based on multiple estimated centroids. The method's functionality is verified by analyzing real-time datasets of the marine radar Coast Watcher 100. The experimental results confirm that the proposed method can real-time estimate reliably the target center of gravity coordinates in the marine environment while reducing the processing time significantly compared to the other methods. More importantly, besides the coordinates, the research is also able to roughly estimate other characteristics of marine targets, such as parts of a target that reflect the most energy and their area and the target's direction of movement, which have not been studied in the existing studies and radar. These characteristics provide a solid background for classifying, recognizing neighboring targets, and target tracking problems. © 2023 IEEE.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

Illuminating Solar Potential: A real-time Deep Learning, IoT, and image processing Approach to Ground-Based Cloud Movement Forecasting for Enhanced Solar Energy Management 1

Illuminating Solar Potential: A Real-Time Deep Learning, IoT...

引用

1st International conference for Women in Computing, InCoWoCo 2024

作者： Perera, P.K.M. Karunarathna, K.B.S. Hewawalpita, S. Dassanayake, S.M. University of Moratuwa Faculty of Business Department of Decision Science Sri Lanka

ISBN: (纸本)9798331518943

Cloud movement impacts the performance of photovoltaic (PV) power plants by causing sudden fluctuations in output power, leading to voltage instability in connected electricity networks. This paper introduces a novel and cost-effective deep learning solution for forecasting shortterm cloud movement to regulate PV power output. The methodology involves capturing raw image data through a PyCamera connected to a Raspberry Pi, followed by rigorous pre-processing and cloud detection techniques. Using colourbased segmentation, morphological operations, and contour analysis, the developed pipeline accurately identifies cloud regions in images and predicts their movement for the subsequent time interval. The proposed algorithm is designed to be efficient, lightweight, and suitable for deployment on low-cost processors. This study successfully implements and optimizes a cloud detection system for resource-constrained environments using the Raspberry Pi 4 Model B. The method significantly improves inference speed and model efficiency while addressing the high latency constraints associated with embedded devices with execution periods measured in seconds. The model performance metrics validate the approach, with an accuracy of 89.84%, indicating the practical potential of the model for real-time applications, offering a promising solution towards the integration of effective cloud forecasting into cost-sensitive energy management systems. © 2024 IEEE.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Industries with Aerial Vehicle using Mobile for Surveillance 2

Revolutionizing Industries with Aerial Vehicle using Mobile ...

引用

2nd International conference on Sustainable Computing and Smart Systems (ICSCSS)

作者： Surendar, V Raghavendran, P. S. Poojitha, P. T. Shivali, S. Sakthivel, G. Lokesh, M. Kongu Engn Coll Dept EEE Perundurai India

ISBN: (数字)9798350379990

ISBN: (纸本)9798350391558;9798350379990

Revolutionizing industries with aerial vehicles using mobile for surveillance is the proposed title of this paper. The availability of drones has created several opportunities, particularly in the areas of agriculture, transportation, and security. This study is a follow-up to the creation of a drone controlled by Wi-Fi-based UAV and advanced image processing. To provide simple and seamless control, a mobile application has been released. Drone-taken photos and videos can also be processed and studied right away. Increasing the degree of autonomous vehicle operations, improving the accuracy of picture identification/analysis algorithms, and ensuring continuous communication between the drone and the control software are perhaps the key objectives of this work. The image processing component aims to take into account sophisticated improvements such as terrain analysis, object detection, and anomaly detection, which are crucial, particularly in the context of security surveillance. Ensuring steady and long-range connectivity while taking certain environmental elements into account can be critical. Enhancing the image processing technique to run smoothly on the off-board drone's hardware constraints is also a crucial step. However, integrating hardware and software continues to be a major challenge in the implementation of a dependable, high-accuracy, real-time analog-to-digital conversion system. The purpose of this research is to develop novel ways for improving UAV systems by integrating tough control systems with complicated image analysis capabilities. Keeping the aforementioned limits in mind, the purpose of this work is to improve understanding of how to create more self-sufficient and adaptive drones that can contribute to a broader range of professions or do more specific activities with minimal human interaction.

关键词： Wireless Fidelity Unmanned Aerial Vehicle App Cutting-edge Drone image processing

来源：评论

学校读者我要写书评

暂无评论

FPGA-based real-time laser beam profiling and stabilization system for quantum simulation applications 26

FPGA-based real-time laser beam profiling and stabilization ...

引用

26th Euromicro conference on Digital System Design (DSD) / 49th Euromicro conference on Software Engineering and Advanced Applications (SEAA)

作者： Marti, Stefano Mustafa, Enis Bisson, Giacomo Anand, Pratyush Fabritius, Philipp Esslinger, Tilman Akin, Abdulkadir Swiss Fed Inst Technol Dept Informat Technol & Elect Engn Zurich Switzerland Swiss Fed Inst Technol Dept Phys Zurich Switzerland

ISBN: (纸本)9798350344196

Lasers are imperative in quantum simulation experiments to trap and cool atoms. With the growing complexity of experimental setups, precise control and stability of the position and exotic shape of lasers have become essential for high-fidelity operations. However, disturbances such as temperature fluctuations, mechanical vibrations, deformation of materials, and acoustic noise pose challenges to fulfill these requirements. In this paper, we propose and evaluate the first system for stabilizing the laser's beam position using two high-resolution cameras with high frame-rates, and image processing in a field-programmable gate array (FPGA) with low latency and subsequent in-loop feedback to the laser control. The proposed image processing hardware extracts the Gaussian beam distribution from two 5 MP cameras at 47 fps and 435 ns latency. These are fed to four proportional-integral-derivative (PID) controllers implemented on the FPGA. The PID modules provide feedback through parallel digital-to-analog converter (DAC) channels for steering mirrors to stabilize the beam within 5 mu m accuracy. Using two cameras at distinct sample distances on the optical axis allows for controlling the incidence angle of the laser beam onto the image planes. The current system is a building block for future extensions allowing real-time phase-feedback on optical lattices, stabilization of independent optical tweezers in an array, and focus position stabilization of transverse electromagnetic (e.g. TEM01) modes enabling large-scale quantum simulations.

关键词： FPGA laser beam stabilization real-time image processing quantum optics

来源：评论

学校读者我要写书评

暂无评论

Fire Detection Using image processing in Industries 5

Fire Detection Using Image Processing in Industries

引用

5th International conference on Intelligent Communication Technologies and Virtual Mobile Networks, ICICV 2024

作者： Kumaresan, V. Abdul Fashin, A. Aheilan, M. Azhageshwar, F. Sujay, L. Kongu Engineering College Department of Electrical and Electronics Engineering Erode India

ISBN: (纸本)9798350385649

Nowadays, fire in the workplace causes significant damage because it is not used early on due to a lack of awareness. As a result, all machines in the industry could be damaged. The most prevalent causes of fire include static electricity, overheating, error by humans, external factors, and mechanical failure. This study addresses concerns with existing solutions by incorporating functionality such as alert and detection. To get real-time detection results, the fire detection unit was created using PythonCV and an image processing model. To detect fire images, an image pre-processing technique called the Haar Cascade Classifier was used. The trained model was tested and compared with other cutting-edge methods. A big fire scale and negative photos of fire in various indoor and outdoor environments were used. The video camera has no specific requirements. The camera will keep monitoring the situation in the room as long as the device is powered ON. If the camera detects a fire, the image is evaluated using an image processing model, the buzzer sounds, and an alarm message is delivered to the user's smartphone via Email. © 2024 IEEE.

关键词： Fires

来源：评论

学校读者我要写书评

暂无评论

PriCE: Privacy-Preserving and Cost-Effective Scheduling for Parallelizing the Large Medical image processing Workflow over Hybrid Clouds 30th

PriCE: Privacy-Preserving and Cost-Effective Scheduling for ...

引用

30th European conference on Parallel and Distributed processing (Euro-Par)

作者： Wang, Yuandou Kanwal, Neel Engan, Kjersti Rong, Chunming Grosso, Paola Zhao, Zhiming Univ Amsterdam Multiscale Networked Syst Amsterdam Netherlands Univ Stavanger Dept Elect Engn & Comp Sci Stavanger Norway

ISBN: (纸本)9783031695766;9783031695773

Running deep neural networks for large medical images is a resource-hungry and time-consuming task with centralized computing. Outsourcing such medical image processing tasks to hybrid clouds has benefits, such as a significant reduction of execution time and monetary cost. However, due to privacy concerns, it is still challenging to process sensitive medical images over clouds, which would hinder their deployment in many real-world applications. To overcome this, we first formulate the overall optimization objectives of the privacy-preserving distributed system model, i.e., minimizing the amount of information about the private data learned by the adversaries throughout the process, reducing the maximum execution time and cost under the user budget constraint. We propose a novel privacy-preserving and cost-effective method called PriCE to solve this multi-objective optimization problem. We performed extensive simulation experiments for artifact detection tasks on medical images using an ensemble of five deep convolutional neural network inferences as the workflow task. Experimental results show that PriCE successfully splits a wide range of input gigapixel medical images with graph-coloring-based strategies, yielding desired output utility and lowering the privacy risk, makespan, and monetary cost under user's budget.

关键词： Privacy Cost-effectiveness Hybrid Clouds Medical image splitting Multi-Objective Optimization Scheduling

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 << < 35 36 37 38 39 40 41 42 43 44 > >>

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：