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

4,746 篇 会议
55 册 图书
12 篇 期刊文献

馆藏范围

4,813 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

3,155 篇 工学
- 2,813 篇 计算机科学与技术...
- 2,227 篇 软件工程
- 1,264 篇 信息与通信工程
- 759 篇 控制科学与工程
- 691 篇 生物工程
- 668 篇 光学工程
- 530 篇 电气工程
- 454 篇 生物医学工程（可授...
- 419 篇 电子科学与技术（可...
- 299 篇 网络空间安全
- 182 篇 安全科学与工程
- 163 篇 机械工程
- 160 篇 仪器科学与技术
- 159 篇 交通运输工程
- 152 篇 动力工程及工程热...
- 152 篇 化学工程与技术
- 142 篇 石油与天然气工程
1,643 篇 理学
- 709 篇 生物学
- 637 篇 物理学
- 604 篇 数学
- 242 篇 化学
- 180 篇 统计学（可授理学、...
827 篇 管理学
- 463 篇 图书情报与档案管...
- 443 篇 管理科学与工程(可...
- 119 篇 工商管理
434 篇 医学
- 364 篇 临床医学
- 247 篇 基础医学(可授医学...
- 214 篇 药学(可授医学、理...
- 106 篇 公共卫生与预防医...
125 篇 法学
- 109 篇 社会学
95 篇 农学
45 篇 经济学
44 篇 文学
33 篇 教育学
12 篇 军事学

主题

320 篇 image processing
312 篇 deep learning
231 篇 image segmentati...
191 篇 signal processin...
172 篇 image classifica...
167 篇 image enhancemen...
162 篇 computer vision
140 篇 image recognitio...
138 篇 convolutional ne...
136 篇 feature extracti...
125 篇 training
115 篇 machine learning
96 篇 computer applica...
83 篇 neural networks
83 篇 computational mo...
79 篇 visualization
78 篇 object detection
71 篇 natural language...
69 篇 semantics
68 篇 artificial intel...

机构

24 篇 chitkara univers...
17 篇 maharishi school...
15 篇 lovely professio...
15 篇 tianjin universi...
13 篇 university of ch...
12 篇 the islamic univ...
12 篇 beijing institut...
11 篇 school of comput...
11 篇 centre of interd...
10 篇 peng cheng labor...
10 篇 graphic era hill...
9 篇 national univers...
9 篇 sun yat-sen univ...
9 篇 school of comput...
9 篇 vivekananda glob...
9 篇 college of compu...
8 篇 harbin engineeri...
8 篇 school of comput...
8 篇 maharishi school...
8 篇 gla university d...

作者

13 篇 chauhan rahul
11 篇 yang yang
10 篇 anand vatsala
8 篇 kukreja vinay
8 篇 gupta rupesh
7 篇 luo xiaonan
7 篇 zhao yang
6 篇 bin wang
6 篇 pei jihong
6 篇 kumar ankit
6 篇 choudhury tanupr...
6 篇 zhu ce
6 篇 ce zhu
6 篇 kumar gaurav
6 篇 bing li
6 篇 li wei
5 篇 gill kanwarparta...
5 篇 zhiguo cao
5 篇 nagaraj p.
5 篇 singh kamred udh...

语言

4,761 篇 英文
51 篇 其他
17 篇 中文
1 篇 土耳其文

检索条件"任意字段=2023 IEEE International Conference on Image Processing and Computer Applications, ICIPCA 2023"

共 4813 条记录，以下是4701-4710 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：

image Quality Analysis and Verification for Vehicle Photos Using Deep Learning

Image Quality Analysis and Verification for Vehicle Photos U...

引用

international conference on Computing Communication Control and Automation (ICCUBEA)

作者： K. Rajeswari S.R. Vispute Jatin Gupta Kirti Dhadwad Rushikesh Ghuge M. Ashwin Reena Kharat Mukesh Ahirrao Department of Computer Engineering Pimpri Chinchwad College Of Engineering Pune India SSBT's College Of Engineering Jalgaon India

This paper offers a thorough overview of the state of the art in image quality assessment, vehicle detection, and number plate extraction. This research would serve as the foundation for building an automated system for vehicle verification in online vehicle Leasing applications. In order to accurately assess vehicle conditions, confirm vehicle identity, and guarantee compliance with rules, these duties are essential in avoiding bottlenecks that could occur during manual verification in vehicle leasing applications. The best approaches for each task are determined through a thorough examination and comparison of the available models, taking into account elements like accuracy, resilience, and real-time processing capabilities. In order to support the creation and application of effective and precise systems for picture quality evaluation, vehicle detection, and number plate extraction, this research paper seeks to serve as a useful resource for professionals working in the auto leasing industry or for other vehicle related purposes. In this Paper, We Use SRGAN(Super Resolution Generative Adversarial Network) for image Quality Evaluation of Vehicle with Threshold Value Of 0.93 i.e Lower value than Threshold indicated Poor image Quality And Greater Value than Threshold Indicates Good image Quality. We also use three different pre-trained models (Inception, Xception and Mobile Net) for Vehicle Detection, where we use a “Vehicle Detection image Dataset” from kaggle containing Vehicle and Non - Vehicle images. After Training and Testing the data set with all three models, We come into conclusion that Mobile -net give most accurate result with about 99.4% accuracy. For Number Plate Extraction we use LPRNet Algorithm which give us a mean accuracy of about 0.9.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of Secure and Privacy-preserving DNS at the 5G Edge

Performance Evaluation of Secure and Privacy-preserving DNS ...

引用

ieee Internatonal conference on Mobile Adhoc and Sensor Systems (MASS)

作者： Yacoub Hanna Diana Pineda Kemal Akkaya Abdullah Aydeger Ricardo Harrilal-Parchment Hamdah Albalawi Advanced Wireless and Security Lab Florida International University Miami FL USA Dept. of Electrical Engineering and Computer Science Florida Institute of Technology Melbourne FL USA

With the improved network performance and efficiency, 5G has been a very appealing alternative for various applications and devices, including but not limited to Industrial IoT (IIoT) applications. However, since IIoT applications require real-time transmission guarantees for time-critical data, optimizing the 5G network performance has attracted much research recently by pushing critical services to the 5G edge. One of such services is Domain Name System (DNS) which is typically offered by ISPs to serve 5G networks. However, due to its heavy role on Internet traffic, DNS has seen many attacks in the past in terms of its authenticity of records and exposure of user requests. Therefore, there have been many variants of DNS protocol such as DNSSEC and DNS over TLS (DoT) to address these security and privacy issues. As such these new protocols need to be integrated into 5G edge and their overhead should be investigated for their potential use in time-critical applications. In this paper, we consider deploying secure and privacy-preserving DNS to the 5G base stations and investigate the feasibility and performance of such an edge computing approach. To this end, we utilize SDN capabilities and forward packets to a local SDN controller for extracting and processing DNS queries. Thus, the DNS packets are served at the 5G edge with optional security and privacy features without being forwarded to remote ISP servers. Our approach is implemented in a virtualized 5G testbed network, and we present various DNS performance results via different metrics and scenarios.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Dual-Energy Metal Artifact Redcution Method for DECT image Reconstruction

A Dual-Energy Metal Artifact Redcution Method for DECT Image...

引用

Annual international conference of the ieee Engineering in Medicine and Biology Society (EMBC)

作者： Tianling Lyu Wei Zhao Wei Gao Jian Zhu Yan Xi Yang Chen Wentao Zhu Zhejiang Lab Hangzhou China School of Physics Beihang University Beijing China Beihang Hangzhou Innovation Institute Hangzhou China Department of Computer Science and Technology Laboratory of Imaging Science and Technology Southeast University Nanjing China Department of Radiation Physics and Technology Cancer Hospital Affiliated to Shandong First Medical University Jinan China Shanghai First-Imaging Tech Shanghai China Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing Southeast University Nanjing China

Metal implants are one of the culprits for image quality degradation in CT imaging, introducing so-called metal artifacts. With the help of the virtual-monochromatic imaging technique, dual-energy CT has been proven to be effective in metal artifact reduction. However, the virtual monochromatic images with suppressed metal artifacts show reduced CNR compared to polychromatic images. To remove metal artifacts on polychromatic images, we propose a dual-energy NMAR (deNMAR) algorithm in this paper that adds material decomposition to the widely used NMAR framework. The dual energy sinograms are first decomposed into water and bone sinograms, and metal regions are replaced with water on the reconstructed material maps. Prior sinograms are constructed by polyenergetically forward projecting the material maps with corresponding spectra, and they are used to guide metal trace interpolation in the same way as in the NMAR algorithm. We performed experiments on authentic human body phantoms, and the results show that the proposed deNMAR algorithm achieves better performance in tissue restoration compared to other compelling methods. Tissue boundaries become clear around metal implants, and CNR rises to 2.58 from ~1.70 on 80 kV images compared to other dual-energy-based algorithms.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Survey of Low-Light image Enhancement 22

A Survey of Low-Light Image Enhancement

引用

Proceedings of the 2022 5th international conference on Artificial Intelligence and Pattern Recognition

作者： Wangjuan Wei Xi'an University of Posts & Telecommunications China

ISBN: (纸本)9781450396899

Abstract: image sensors imaging in low-light environments can cause problems such as high image noise, low contrast, and failure to represent large amounts of detailed information, which affect not only human eye observation but also applications related to computer vision and low-light image processing. The use of image enhancement methods and deep learning methods can improve the contrast of low-light images and improve the image quality. The article first introduces the traditional low-illumination image enhancement algorithms categorized and summarizes the improvement process of these algorithms in recent years, then introduces the low-illumination image enhancement methods based on deep learning, and finally introduces the existing low-illumination image datasets and the evaluation criteria of the enhanced images.

关键词： Low-illumination image enhancement Retinex theory deep learning

来源：评论

学校读者我要写书评

暂无评论

Collaborative Edge-Cloud AI for IoT Driven Secure Healthcare System

Collaborative Edge-Cloud AI for IoT Driven Secure Healthcare...

引用

Annual ieee Systems conference

作者： Lav Gupta Department of Computer Science University of Missouri – St. Louis St. Louis MO

In healthcare applications like monitoring patients in ICUs and performing precision robotic surgeries, IoT and sensor networks have become indispensable. These sensors generate a large amount of data that, when processed and visually presented to a medical professional, assists in the more accurate diagnosis and treatment of ailments. For some time now, hospital administrations have been taking advantage of public cloud(referred to as main clouds in this paper) resources to store and process patient data using the advanced AI analytical tools that these clouds provide. However, taking all the medical sensor data to the main cloud encounters network congestion and latencies that may negatively impact the outcomes. In this situation the power of edge-AI may appear appealing, but the state-of-the-art does not allow all the tasks of training complex AI models and drawing inference from them to take place at the edge. Techniques of complexity reduction like pruning and quantization have been applied to reduce storage and processing burden, but they compromise accuracy of the models. Researchers now agree on the necessity of collaborative edge-main cloud AI for demanding *** is, however, necessary to realize that the multi-layer IoT-Edge-Main Cloud arrangement has an expanded attack surface. Any malicious attack on the dataflows among various layers may threaten patients’ quality of life or even their lives. Although AI can be used to secure these dataflows, using large neural network models centrally on the main cloud results in long training and inference dispersion times. We propose a collaborative, hierarchically merged technique to help train large neural network models in real-time. This is achieved by synthesizing the main cloud model using the trained layers of the edge models, resulting in a dramatic reduction in the training times of the model in the main cloud while achieving high detection accuracy. As we shall see in the description, this method rem

关键词： Training Cloud computing Adaptation models image edge detection Neural networks Collaboration Medical services

来源：评论

学校读者我要写书评

暂无评论

Intelligent Visual Tracking Robots Using Cascade PID Controllers

Intelligent Visual Tracking Robots Using Cascade PID Control...

引用

Signal, Control and Communication (SCC), international conference on

作者： Rihem Farkh Ghislain Oudinet Florian Sananes Sultan Alzahrani Saad Alhuwaimel Thibaut De Leruyelle ISEN Toulon Toulon France Health Sector KACST Digital Health Institute Riyadh Saudia Arabia King Abdulaziz City For Science and Technology Riyadh Saudia Arabia

ISBN: (数字)9798350326390

ISBN: (纸本)9798350326406

A tracking system is useful for a variety of robotic applications, including obstacle detection, autonomous path planning and surveillance. One of the most difficult issues in computer vision is visual object tracking, which involves estimating the position of a target in an image series. Utilizing color information for visual tracking poses a formidable challenge due to variations in illuminant, shadows, shading, specular highlights, cameras, and object geometry. Consequently, color measurements exhibit significant fluctuations throughout an image series. A camera is frequently used for object tracking to acquire information on construction robot motion, which may subsequently be used in coordination controls. The paper presents a mobile robot vision system that allows the robot to recognize and track objects based on their color. A new approach is proposed for stable tracking of mobile robot using combined algorithm based on computer vision techniques and a cascade proportional integral derivative controllers (PID). Within a system designed for controlling the speed of a DC motor, the goal of a PID controller is to maintain speed at a specified reference value while dynamically accepting new set point values. The combination of feedback encoder and PID controllers can be employed to control motor speeds in the presence of noise and load disturbances

关键词： Visualization computer vision Target tracking image color analysis Robot kinematics Surveillance Robot vision systems

来源：评论

学校读者我要写书评

暂无评论

Monkeypox Detection from Various Types of Poxes: A Deep Learning Approach

Monkeypox Detection from Various Types of Poxes: A Deep Lear...

引用

international conference for Convergence of Technology (I2CT)

作者： Anik Pramanik Fayazunnesa Chowdhury Salma Sultana Md. Mahbubur Rahman Md. Hasan Imam Bijoy Md. Sadekur Rahman Department of Computer Science and Engineering Daffodil International University Dhaka Bangladesh Department of Statistics Jahangirnagar University Dhaka Bangladesh

According to World Health Organization (WHO) statistics, monkeypox has been identified as an epidemic in 127 nations so far, and it is spreading quickly over the globe. While the rashes and skin lesions associated with monkeypox usually mimic those of other poxes, including chickenpox and measles. Due to these similarities, it could be challenging for medical professionals to identify monkeypox based just on the appearance of lesions and rashes. Because monkeypox was uncommon before in the current outbreak, healthcare professionals lack knowledge in this area. But the scientific community has demonstrated a rising interest in implementing Artificial Intelligence in Monkeypox prediction and detection from digital skin images as a result of the success of image processing approaches in COVID-19 detection. In this study, we have applied three cutting-edge deep learning models which are InceptionV3, MobileNetV3, and DenseNet201, referred to as transfer learning models, to detect monkeypox on skin images using the publicly available Monkeypox Skin image Dataset 2022 with four classes. According to our research, transfer learning models can detect monkeypox with a top 93.59% accuracy for the InceptionNet-V3 pre-trained model from three implemented algorithms on digitized skin images. For further research, larger training images are required to train those deep learning models to achieve a higher vigorous detection rate.

关键词： Deep learning Training Transfer learning Organizations Medical services Skin Lesions

来源：评论

学校读者我要写书评

暂无评论

LRRU: Long-short Range Recurrent Updating Networks for Depth Completion

LRRU: Long-short Range Recurrent Updating Networks for Depth...

引用

international conference on computer Vision (ICCV)

作者： Yufei Wang Bo Li Ge Zhang Qi Liu Tao Gao Yuchao Dai Northwestern Polytechnical University and Shaanxi Key Laboratory of Information Acquisition and Processing Chang’an University

Existing deep learning-based depth completion methods generally employ massive stacked layers to predict the dense depth map from sparse input data. Although such approaches greatly advance this task, their accompanied huge computational complexity hinders their practical applications. To accomplish depth completion more efficiently, we propose a novel lightweight deep network framework, the Long-short Range Recurrent Updating (LRRU) network. Without learning complex feature representations, LRRU first roughly fills the sparse input to obtain an initial dense depth map, and then iteratively updates it through learned spatially-variant kernels. Our iterative update process is content-adaptive and highly flexible, where the kernel weights are learned by jointly considering the guidance RGB images and the depth map to be updated, and large-to-small kernel scopes are dynamically adjusted to capture long-to-short range dependencies. Our initial depth map has coarse but complete scene depth information, which helps relieve the burden of directly regressing the dense depth from sparse ones, while our proposed method can effectively refine it to an accurate depth map with less learnable parameters and inference time. Experimental results demonstrate that our proposed LRRU variants achieve state-of-the-art performance across different parameter regimes. In particular, the LRRU-Base model outperforms competing approaches on the NYUv2 dataset, and ranks 1st on the KITTI depth completion benchmark at the time of submission. Project page: https://***/LRRU/.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Inductorless Analog Time-Delays for Nonlinear RF Signal processing Circuits in 180nm CMOS

Inductorless Analog Time-Delays for Nonlinear RF Signal Proc...

引用

Microwaves Antennas and Propagation conference (MAPCON)

作者： Nimasha Hiruni Silva Arjuna Madanayake Soumyajit Mandal Justin Delva Electrical and Computer Engineering Florida International University Miami USA Instrumentation Division Brookhaven National Laboratory Brookhaven USA Lockheed Martin Corporation Boston USA

Extremely low latency and low power consumption is crucial for emerging spectrum sensing, electronic warfare, and wireless communications applications such as phased-array beamforming for wideband signals, convolutional neural networks (CNNs) at high RF bandwidths for AI/ML inference on RF waveforms, and tunable multi-band microwave filters. Analog computers implemented in high performance integrated circuit (IC) platforms based on CMOS radio-frequency (RF) IC technologies have significant potential for such edge computing applications. The fast and low-latency response of analog RFICs ensures that tight performance specifications in terms of both latency and power consumption can be met without compromising on computational throughput. The analog computing approach also allows sensors to directly communicate with edge processors and produce intelligent action outputs at low latency without the power overhead of digitization incurred by conventional edge computing systems. Many of the necessary analog computations require a true time delay (TDD) analog memory as a fundamental building block. This paper discusses recent work on realizing analog memory using TTD elements for radar, communications, and AI/ML applications. The circuits were designed in TSMC 180nm CMOS technology and simulated at the transistor level using Cadence Spectre.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Understanding the Robustness of 3D Object Detection with Bird'View Representations in Autonomous Driving

Understanding the Robustness of 3D Object Detection with Bir...

引用

conference on computer Vision and Pattern Recognition (CVPR)

作者： Zijian Zhu Yichi Zhang Hai Chen Yinpeng Dong Shu Zhao Wenbo Ding Jiachen Zhong Shibao Zheng Institute of Image Communication and Network Engineering Shanghai Jiao Tong University Dept. of Comp. Sci. and Tech. THBI Lab Institute for AI Tsinghua University BNRist Center Zhongguancun Laboratory Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Information Materials and Intelligent Sensing Laboratory of Anhui Province School of Computer Science and Technology Anhui University SAIC Motor AI Lab

3D object detection is an essential perception task in autonomous driving to understand the environments. The Bird's-Eye-View (BEV) representations have significantly improved the performance of 3D detectors with camera inputs on popular benchmarks. However, there still lacks a systematic understanding of the robustness of these vision-dependent BEV models, which is closely related to the safety of autonomous driving systems. In this paper, we evaluate the natural and adversarial robustness of various representative models under extensive settings, to fully understand their behaviors influenced by explicit BEV features compared with those without BEV. In addition to the classic settings, we propose a 3D consistent patch attack by applying adversarial patches in the 3D space to guarantee the spatiotemporal consistency, which is more realistic for the scenario of autonomous driving. With substantial experiments, we draw several findings: 1) BEV models tend to be more stable than previous methods under different natural conditions and common corruptions due to the expressive spatial representations; 2) BEV models are more vulnerable to adversarial noises, mainly caused by the redundant BEV features; 3) Camera-LiDARfusion models have superior performance under different settings with multi-modal inputs, but BEV fusion model is still vulnerable to adversarial noises of both point cloud and image. These findings alert the safety issue in the applications of BEV detectors and could facilitate the development of more robust models.

关键词：

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482页 << < 467 468 469 470 471 472 473 474 475 476 > >>

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：