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

14,140 篇 会议
291 篇 期刊文献
196 册 图书
6 篇 学位论文

馆藏范围

14,633 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

7,883 篇 工学
- 5,294 篇 计算机科学与技术...
- 2,557 篇 软件工程
- 2,529 篇 电气工程
- 1,448 篇 信息与通信工程
- 934 篇 控制科学与工程
- 745 篇 光学工程
- 548 篇 生物医学工程（可授...
- 531 篇 电子科学与技术（可...
- 512 篇 仪器科学与技术
- 486 篇 机械工程
- 358 篇 生物工程
- 245 篇 测绘科学与技术
- 182 篇 材料科学与工程（可...
- 173 篇 航空宇航科学与技...
- 148 篇 交通运输工程
- 111 篇 安全科学与工程
- 96 篇 化学工程与技术
3,827 篇 理学
- 2,635 篇 物理学
- 1,004 篇 数学
- 411 篇 生物学
- 276 篇 系统科学
- 256 篇 统计学（可授理学、...
- 132 篇 化学
1,610 篇 医学
- 1,422 篇 临床医学
- 250 篇 特种医学
- 185 篇 基础医学(可授医学...
- 113 篇 药学(可授医学、理...
782 篇 管理学
- 470 篇 管理科学与工程(可...
- 338 篇 图书情报与档案管...
- 98 篇 工商管理
67 篇 农学
60 篇 法学
37 篇 教育学
30 篇 经济学
27 篇 文学
20 篇 军事学
19 篇 艺术学
1 篇 哲学

主题

2,875 篇 image processing
1,507 篇 image segmentati...
1,202 篇 signal processin...
658 篇 feature extracti...
625 篇 cameras
590 篇 signal processin...
589 篇 image edge detec...
530 篇 image coding
522 篇 image reconstruc...
469 篇 real-time system...
417 篇 algorithm design...
354 篇 image analysis
352 篇 image color anal...
331 篇 image enhancemen...
327 篇 deep learning
311 篇 object detection
307 篇 pixel
299 篇 real time system...
298 篇 hardware
294 篇 computer archite...

机构

22 篇 signal and image...
19 篇 samara national ...
14 篇 school of electr...
12 篇 department of el...
11 篇 samara national ...
11 篇 univ texas san a...
10 篇 school of electr...
10 篇 center for signa...
9 篇 information syst...
9 篇 institute of ima...
9 篇 tongji universit...
9 篇 university of ch...
8 篇 school of electr...
8 篇 univ chinese aca...
8 篇 university of to...
8 篇 purdue univ sch ...
8 篇 electrical compu...
8 篇 image processing...
8 篇 information syst...
8 篇 samara national ...

作者

19 篇 anon
13 篇 de-shuang huang
13 篇 jagdish chand ba...
11 篇 p. pirsch
10 篇 jie yang
10 篇 panetta karen
10 篇 j.m. mendel
9 篇 c.-c.j. kuo
9 篇 mahalanobis a
9 篇 r. chellappa
8 篇 miller jwv
8 篇 semenishchev e.
8 篇 frank hannig
8 篇 hannig frank
7 篇 busch christoph
7 篇 zelensky a.
7 篇 bovik alan c.
7 篇 jerry m. mendel
7 篇 kupriyanov a.v.
7 篇 wei li

语言

14,393 篇 英文
140 篇 其他
81 篇 中文
20 篇 土耳其文
6 篇 德文
3 篇 葡萄牙文
2 篇 西班牙文
2 篇 俄文
1 篇 法文
1 篇 波兰文

检索条件"任意字段=Conference on Image Processing - Algorithms and Systems III"

共 14633 条记录，以下是181-190 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：

Lossless Medical image Compression Using ROI Segmentation with Deep Learning Techniques

Lossless Medical Image Compression Using ROI Segmentation wi...

引用

International conference on Inventive Computation Technologies (ICICT)

作者： Velidi Sai Baba Molaka Ramakrishna Reddy Kombathula Lakshmi Karthik Gandham Lakshmi Tharun Katreddy Surya Mithra Dept. of Information Technology Sagi Rama Krishnam Raju Engineering College Bhimavaram Andhra Pradesh India

ISBN: (数字)9798331512248

ISBN: (纸本)9798331512255

With The increasing use of medical imaging has put a greater requirement on fast and efficient storage and transmission. Compression algorithms need to strike a balance between reducing file sizes without distortion of valuable diagnostic information. In this paper, a hybrid lossless compression method is proposed that uses deep learning-based ROI segmentation. A U-Net model is used specifically to segment the cardiac anatomy on CT scans accurately. Lossless compression is used to preserve large diagnostic areas, and lossy compression is used to compress small areas. The approach strikes an effective balance between the two to yield high compression ratio without compromising medical integrity. Experimental evidence proves its efficacy in minimizing storage needs without compromising diagnostic accuracy. This work recognizes the potential of deep learning for medical image processing and paves the way for upcoming AI-based compression methods.

关键词： Heart Deep learning Learning systems image segmentation image coding Accuracy Computed tomography Transform coding Memory Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

Learning to Reconstruct Signals With Inexact Sensing Operator via Knowledge Distillation

Learning to Reconstruct Signals With Inexact Sensing Operato...

引用

International conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Roman Jacome Leon Suarez Romario Gualdrón-Hurtado Luis Gonzalez Henry Arguello Department of Electrical Electronics and Telecommunications Engineering Universidad Industrial de Santander Bucaramanga Colombia Department of Systems and Informatics Engineering Universidad Industrial de Santander Bucaramanga Colombia

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

In computational optical imaging and wireless communications, signals are acquired through linear coded and noisy projections, which are recovered through computational algorithms. Deep model-based approaches, i.e., neural networks incorporating the sensing operators, are the state-of-the-art for signal recovery. However, these methods require exact knowledge of the sensing operator, which is often unavailable in practice, leading to performance degradation. Consequently, we propose a new recovery paradigm based on knowledge distillation. A teacher model, trained with full or almost exact knowledge of a synthetic sensing operator, guides a student model with an inexact real sensing operator. The teacher is interpreted as a relaxation of the student since it solves a problem with fewer constraints, which can guide the student to achieve higher performance. We demonstrate the improvement of signal reconstruction in computational optical imaging for single-pixel imaging with miscalibrated coded apertures systems and multiple-input multiple-output symbols detection with inexact channel matrix.

关键词： Wireless communication Computational modeling Symbols Optical imaging Signal reconstruction Robustness Sensors Speech processing Knowledge transfer image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Dynamic SpikFormer: Low-Latency & Energy-Efficient Spiking Neural Networks with Dynamic Time Steps for Vision Transformers

Dynamic SpikFormer: Low-Latency & Energy-Efficient Spiking N...

引用

International conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Gourav Datta Zeyu Liu Anni Li Peter A. Beerel Dept. of Electrical Computer & Systems Engineering Case Western Reserve University Cleveland USA Ming Hsieh Dept. of Electrical and Computer Engineering University of Southern California Los Angeles USA

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Spiking Neural Networks (SNNs) have emerged as a popular spatio-temporal computing paradigm for complex vision tasks. Recently proposed SNN training algorithms have significantly reduced the number of time steps (down to 1) for improved latency and energy efficiency, however, they target only convolutional neural networks (CNN). These algorithms, when applied to the recently spotlighted vision transformers (ViT), either require a large number of time steps or fail to converge. Based on the analysis of the histograms of the ANN and SNN activation maps, we hypothesize that each ViT block has a different sensitivity to the number of time steps. We propose a novel training framework that dynamically allocates the number of time steps to each ViT module depending on a trainable score assigned to each timestep. In particular, we generate a scalar binary time step mask that filters spikes emitted by each neuron in a leaky-integrate-and-fire (LIF) layer. The resulting SNNs have high activation sparsity and require only accumulate operations (AC), except for the input embedding layer, in contrast to expensive multiply-and-accumulates (MAC) needed in traditional ViTs. This yields significant improvements in energy efficiency. We evaluate our training framework and resulting SNNs on image recognition tasks including CIFAR10, CIFAR100, and imageNet with different ViT architectures. We obtain a test accuracy of 95.97% with 4.97 time steps with direct encoding on CIFAR10.

关键词： Training Computer vision Sensitivity Neurons Signal processing algorithms Spiking neural networks Transformers Energy efficiency Convolutional neural networks Speech processing

来源：评论

学校读者我要写书评

暂无评论

Research on the Application of Virtual Reality Technology in Digital Protection of Cultural Heritage Landscape

Research on the Application of Virtual Reality Technology in...

引用

Electronics, Energy systems and Power Engineering (EESPE), IEEE International conference on

作者： Yan Huang Yu Huang Nanning University Nanning China

ISBN: (数字)9798350389579

ISBN: (纸本)9798350389586

This paper puts forward a kind of digital protection system based on VR, which uses 3D modeling and dynamic rendering to provide high quality digital protection and exhibition platform. First, the cultural heritage landscape is modeled with high precision through laser scanning and drone photogrammetry technology to obtain three-dimensional point cloud data. Subsequently, an efficient dynamic rendering algorithm is designed, which can enhance the realism and immersion of the landscape by simulating physical properties such as lighting, shadows, reflection and refraction. To ensure that the system can still run smoothly under high load, image processing optimization technology is used to stabilize the rendering frame rate at more than 60 frames per second and perform well under multiple dynamic scenes switching. At last, the paper builds a virtual reality simulation environment based on Unity and Unreal Engine. The experiment shows that the system can reconstruct the cultural heritage scene exactly, the rendering effect is high, and the user experience rate reaches 92%.

关键词： Solid modeling Three-dimensional displays Heuristic algorithms Virtual environments Rendering (computer graphics) Visual effects User experience image restoration Cultural differences Protection

来源：评论

学校读者我要写书评

暂无评论

Multi-Model Deep Learning Framework for Plant Disease Detection and Classification using YOLOv5, Xception, and DenseNet

Multi-Model Deep Learning Framework for Plant Disease Detect...

引用

Visual Analytics and Data Visualization (ICVADV), International conference on

作者： Kunal K. Meshram Sarika Khandelwal Jyoti Kumre Department of Computer Science and Engineering G H Raisoni College of Engineering Nagpur India

ISBN: (数字)9798331521394

ISBN: (纸本)9798331521400

Plant diseases lead to food loss and yield reduction, which is a serious challenge to food security globally. Researchers have suggested deep learning models, which are trained using plant disease data like PlantVillage and PlantDoc, as a means of solving this issue. The traditional solutions usually do not work under practical agricultural environments. This research combines machine learning (ML) models and image processing methods for agricultural use. This study utilizes the algorithms, such as MobileNet, VGG16, YOLOv8, and Faster R-CNN, to upgrade plant disease identification and classification. Our method utilizes deep learning architectures for both object detection and plant disease classification. We offer real-time crop analysis to help farmers make informed decisions, achieve maximum productivity, and enhance sustainable agriculture. Leveraging previous work, we seek to enhance performance through DenseNet and Xception for classification and YOLOv5 for object detection. We also use a Flask-based, easy-to-use front-end for authentication-based client testing.

关键词： YOLO Deep learning Productivity Plant diseases image processing Visual analytics Food security Metadata Real-time systems Testing

来源：评论

学校读者我要写书评

暂无评论

Multi-Sensor Satellite image Cloud Classification with Deep Learning

Multi-Sensor Satellite Image Cloud Classification with Deep ...

引用

Data Science, Agents & Artificial Intelligence (ICDSAAI), International conference on

作者： Rakesh Asery Burungale Swapnil Birudev Pankaj Saini Bigdata Research & Supercomputing CSIR-Fourth Paradigm Institute Bangalore India

ISBN: (数字)9798331537555

ISBN: (纸本)9798331537562

Advancements in remote sensing (RS) have greatly increased the availability of satellite imagery, enabling diverse applications. However, cloud-cover remains a significant challenge, obstructing the acquisition and analysis of optical satellite images. This necessitates advanced cloud classification techniques as a crucial preprocessing step. The proposed MobileNetV2-based convolutional neural network architecture demonstrates unprecedented cloud classification capabilities, effectively processing imagery across diverse spatial resolutions ranging from 10 to 56 meters. By leveraging sophisticated machine learning algorithms, the model transcends traditional pixel-based thresholding techniques, capturing complex inter-pixel spatial correlations with remarkable precision. Experimental validation across heterogeneous datasets including IRS (AWiFS, LISS-iii), Landsat, and Sentinel platforms reveals exceptional performance metrics, consistently achieving classification accuracies exceeding 99.94%.

关键词： Accuracy Satellites Clouds Scalability Landsat Robustness Satellite images Convolutional neural networks Spatial resolution Remote sensing

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Review of Hybrid V2X Communication and Edge processing Techniques for Real-Time Emergency Vehicle Detection and Prioritization in Urban Traffic systems

A Comprehensive Review of Hybrid V2X Communication and Edge ...

引用

Device Intelligence, Computing and Communication Technologies, (DICCT), International conference on

作者： Jerim Justin Lokkeshkumar R Vijayasri P Department of Electronics and Communication Engineering Chennai Institute of Technology Chennai Tamil Nadu India

ISBN: (数字)9798331543358

ISBN: (纸本)9798331543365

This review paper presents the use of hybrid Vehicle-to-Everything (V2X) communication systems to detect and prioritize emergency vehicles in congested urban areas. To reduce response times, researchers are merging edge processing with Dedicated Short-Range Communication (DSRC) and Cellular Vehicle-to-Everything (C-V2X). The technology provides extremely fast, low-latency connections, which are essential for real-time applications, by utilizing recent developments in 5G and edge computing. To increase detection accuracy in noisy urban settings, researchers are experimenting with multi-sensor fusion systems that combine GPS, acoustic sensors, and AI-powered vision. Adaptive traffic signal preemption algorithms that dynamically modify traffic flows to grant priority access to emergency vehicles are also being investigated in some research. Despite its promise, there are still obstacles to be addressed, such as interoperability problems and network congestion. However, the benefits might be enormous: quicker emergency reactions, more seamless traffic patterns, and generally more effective urban transportation systems. In the upcoming years, we should witness some fascinating breakthroughs as researchers continue to hone these technologies.

关键词： Accuracy Reviews 5G mobile communication image edge detection Urban areas Vehicular ad hoc networks Real-time systems Dedicated short range communication Vehicle-to-everything Edge computing

来源：评论

学校读者我要写书评

暂无评论

LLM-Based Task Planning for Mobile Robots Using a Novel SLAM Method for Materials Distribution

LLM-Based Task Planning for Mobile Robots Using a Novel SLAM...

引用

International conference on Autonomous Robots and Agents, ICARA

作者： Aphilak Lonklang Pedro Alejandro Cordero Jara Haichen Xu Wentao Zhang Natabara Máté Gyöngyössy János Botzheim Department of Artificial Intelligence Faculty of Informatics ELTE Eötvös Loránd University Budapest Hungary

ISBN: (数字)9798331509231

ISBN: (纸本)9798331509248

This paper presents a novel autonomous mobile robot system for material distribution, integrating dynamic map generation, natural language processing (NLP), and efficient path-planning for real-world factory applications. The system begins with a top-view image capture of the environment using a fisheye-lens camera, followed by image correction and color-based object detection to identify stations and generate an occupancy map for navigation, eliminating the need for traditional SLAM techniques. User interaction is facilitated through an NLP module connected to a large language model (LLM) trained on predefined assembly manuals, enabling the robot to interpret requests and determine the required materials for specific assembly tasks. The global path-planning is managed by the Improved RRT* with Reduced Random Map Size (IRRT*-RRMS) algorithm, ensuring optimal and efficient motion in dynamic environments. Experimental validation using a TurtleBot3 Waffle Pi equipped with an OpenManipulator-X demonstrates the system's effectiveness, particularly in handling assembly model H, which includes bolts, nuts, and screws.

关键词： Simultaneous localization and mapping Navigation Heuristic algorithms Robot vision systems Object detection Fasteners Natural language processing Mobile robots Assembly Autonomous robots

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Approach for Detection and Reduction of different types of noises in gray scale images

A Hybrid Approach for Detection and Reduction of different t...

引用

International Symposium on Advanced Computing and Communication (ISACC)

作者： Amanpreet Kaur Sandhu University Institute of Computing Chandigarh University Gharuan Mohali Punjab India

ISBN: (数字)9798331523893

ISBN: (纸本)9798331523909

image denoising is a critical task in various fields such as digital photography, medical imaging, satellite or remote sensing, and, also preserving important image details while removing noise is essential. This paper introduces the Hybrid Adaptive Median-Gaussian Filter (HAMGF), a novel method designed to effectively mitigate both salt-and-pepper and Gaussian noise especially in grayscale images. The proposed HAMGF technique combines adaptive median filtering, which dynamically adjusts the window size to remove impulsive noise, with adaptive Gaussian filtering, which varies the smoothing strength based on local image variance to reduce Gaussian noise. However, the proposed hybrid technique is implemented on a variety of noisy images, demonstrating its ability to outperform traditional filtering methods that are typically specialized for single noise types. HAMGF not only excels in reducing noise but also in preserving critical image features or details, such as edges and fine textures, making it particularly suited for applications requiring high-fidelity image restoration. The results highlight the flexibility and robustness of HAMGF, showcasing its potential for broader adoption in noise reduction tasks. The proposed research work demonstrates an important advancement in the area of image processing which is offering a versatile as well as powerful tool for the enhancement of image quality across varied domains.

关键词： Smoothing methods Filtering Gaussian noise image edge detection Noise reduction Adaptive filters Filtering algorithms image restoration Remote sensing image denoising

来源：评论

学校读者我要写书评

暂无评论

A Vision-Based System for Real-Time Monitoring of Water Quality in Natural and Artificial Reservoirs

A Vision-Based System for Real-Time Monitoring of Water Qual...

引用

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

作者： Shripad Bhatlawande Shrihari Mohole Yash Pahade Swati Shilaskar Aditya Munjale Vishwakarma Institute of technology Pune India

ISBN: (数字)9798331527549

ISBN: (纸本)9798331527556

Manual sampling and laboratory testing are the mainstays of traditional water quality monitoring methods, which causes delays in data processing and decision-making. This study proposes an enhanced monitoring of water quality system that uses machine learning algorithms to classify and segment water samples in real-time, thereby overcoming these restrictions. Water samples are classified as “Clean” or “Polluted” having an accuracy of 83.99% using a CNN model. The CNN model, trained over 20 epochs, effectively learns patterns from the dataset to deliver precise results. Additionally, a U-Net model is implemented for image segmentation, generating masks that accurately highlight areas of interest within the water samples, with a segmentation accuracy of 68%. Streamlit's intuitive interface makes it simple for users to upload images and get immediate feedback on water quality. This system helps to improve the health of the environment monitoring with automating the method of water quality evaluation. It does this by providing a simpler, quicker, and scalable solution that enables prompt, data-driven actions.

关键词： image segmentation Accuracy Water quality Manuals Streaming media User interfaces Reservoirs Water pollution Real-time systems Testing

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 << < 15 16 17 18 19 20 21 22 23 24 > >>

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：