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

39,964 篇 会议
5,702 篇 期刊文献
316 篇 学位论文
101 册 图书
85 篇 专利
6 篇 资讯
2 件 标准

馆藏范围

46,176 篇 电子文献
4 种 纸本馆藏

日期分布

学科分类号

29,042 篇 工学
- 17,440 篇 计算机科学与技术...
- 9,437 篇 电气工程
- 9,122 篇 软件工程
- 6,880 篇 信息与通信工程
- 3,121 篇 控制科学与工程
- 2,690 篇 电子科学与技术（可...
- 2,621 篇 光学工程
- 2,571 篇 机械工程
- 2,041 篇 仪器科学与技术
- 1,313 篇 生物医学工程（可授...
- 925 篇 生物工程
- 830 篇 安全科学与工程
- 750 篇 交通运输工程
- 700 篇 材料科学与工程（可...
- 544 篇 测绘科学与技术
- 528 篇 航空宇航科学与技...
- 413 篇 土木工程
- 386 篇 化学工程与技术
9,878 篇 理学
- 6,465 篇 物理学
- 2,534 篇 数学
- 1,120 篇 生物学
- 694 篇 系统科学
- 611 篇 统计学（可授理学、...
- 502 篇 化学
5,860 篇 医学
- 5,327 篇 临床医学
- 629 篇 特种医学
- 471 篇 基础医学(可授医学...
2,236 篇 管理学
- 1,581 篇 管理科学与工程(可...
- 715 篇 图书情报与档案管...
- 388 篇 工商管理
285 篇 法学
251 篇 农学
167 篇 艺术学
159 篇 教育学
145 篇 经济学
106 篇 军事学
79 篇 文学
1 篇 哲学
1 篇 历史学

主题

5,776 篇 image processing
3,004 篇 real-time system...
2,955 篇 cameras
2,420 篇 image segmentati...
2,136 篇 streaming media
1,793 篇 feature extracti...
1,715 篇 image coding
1,625 篇 real time system...
1,376 篇 image edge detec...
1,361 篇 computer vision
1,346 篇 object detection
1,312 篇 hardware
1,218 篇 image color anal...
1,212 篇 image reconstruc...
1,013 篇 video coding
949 篇 motion estimatio...
898 篇 deep learning
890 篇 field programmab...
869 篇 video compressio...
867 篇 computer archite...

机构

78 篇 beijing key labo...
53 篇 univ chinese aca...
38 篇 beijing key labo...
30 篇 中国科学院长春光...
29 篇 shanghai jiao to...
27 篇 microsoft resear...
24 篇 中北大学
23 篇 华中科技大学
23 篇 tsinghua univers...
23 篇 school of inform...
21 篇 univ sci & techn...
20 篇 天津大学
19 篇 university of sc...
19 篇 tsinghua univ de...
18 篇 microsoft res as...
17 篇 hubei province k...
17 篇 beijing institut...
16 篇 长安大学
16 篇 national institu...
16 篇 nanyang technol ...

作者

39 篇 agostini luciano
33 篇 li li
27 篇 zhang lei
26 篇 jie yang
24 篇 p. pirsch
23 篇 liu yang
22 篇 li yang
21 篇 bovik alan c.
20 篇 wang lei
20 篇 luciano agostini
19 篇 wiegand thomas
19 篇 li xin
19 篇 jing zhang
18 篇 hamidouche wassi...
17 篇 jian wang
17 篇 wang jing
17 篇 wang jian
16 篇 van gool luc
15 篇 eckehard steinba...
15 篇 ikenaga takeshi

语言

43,519 篇 英文
1,962 篇 中文
585 篇 其他
67 篇 土耳其文
20 篇 日文
15 篇 俄文
11 篇 法文
7 篇 西班牙文
6 篇 葡萄牙文
5 篇 德文
1 篇 罗马尼亚文
1 篇 斯洛文尼亚文

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

共 46176 条记录，以下是4941-4950 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：

Insights on Assessing image processing Approaches Towards Health Status of Plant Leaf 3

Insights on Assessing Image Processing Approaches Towards He...

引用

3rd International conference on Smart Technologies in Computing, Electrical and Electronics, ICSTCEE 2022

作者： Harsha, R. Veena, K.V. School of Electronics and Communication Engineering REVA UNIVERSITY Bengaluru560064 India

ISBN: (纸本)9781665456647

With the advancement of digital imaging in agriculture and crop production, ideas are being adopted for real-time health status. In all parts of the plant, the leaf is a direct indicator of its health status, so the use of a variety of image processing techniques can benefit the process of providing educational conditions for plant life. Currently, there are a variety of methods, e.g., feature extraction, classification, identification, class development and additional dependencies found in the use of the learning machine;research shows many contributions to this challenge. However, it has not yet come to realize the best way. Therefore, this paper highlights the obvious strengths and weaknesses associated with existing photographic techniques to identify the disease status by inserting a photograph of the leaves of the plant. This research also contributes to highlighting open-ended research problems so that there are complete words about success. © 2022 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Back2Seg: Joint Background Estimation and Bacteria Segmentation on Optical Endomicroscopy images

Back2Seg: Joint Background Estimation and Bacteria Segmentat...

引用

European Signal processing conference (EUSIPCO)

作者： Mehmet Demirel Bethany Mills Erin Gaughan Kevin Dhaliwal James R. Hopgood IDCOM School of Engineering University of Edinburgh Edinburgh UK Edinburgh Medical School University of Edinburgh Edinburgh UK

ISBN: (数字)9789464593617

ISBN: (纸本)9798331519773

Pneumonia, a lung infection typically caused by bacteria, requires swift and accurate diagnosis, especially in critical care. Optical endomicroscopy (OEM) facilitates real-time acquisition of in vivo and in situ optical biopsies, aiding in the quick identification of bacteria. However, the challenge of visually analyzing the vast number of images generated by the OEM in real-time can lead to delays in necessary treatments. To address this, we introduce Back2Seg, a novel approach for the segmentation of bacteria in OEM image sequences. Prior research mainly focused on exploiting bacteria motion or relied on less accurate unsupervised background estimation methods. In this regard, to enhance the background estimation and thus bacteria segmentation, Back2Seg employs a two-stage architecture with one sub-network dedicated to estimating the background using a Convolutional Neural Network (CNN)-Transformer architecture and the other is a dual-input network, processing both the original and the estimated background sequences to accurately segment the bacteria. Our experiments demonstrate that Back2Seg effectively integrates the advantages of both supervised and unsupervised learning techniques, showing a 4.62% increase in correlation with annotations over unsupervised models and a 1.05 reduction in root mean squared error (RMSE), outperforming the top supervised approach.

关键词： image segmentation Biomedical optical imaging Accuracy Motion segmentation Estimation Bacteria Optical imaging Adaptive optics real-time systems image sequences

来源：评论

学校读者我要写书评

暂无评论

SCI-Gaussian: Optimizing 3D Gaussian Radiance Fields from a Snapshot Compressive image

SCI-Gaussian: Optimizing 3D Gaussian Radiance Fields from a ...

引用

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

作者： Xiaoyue Li Yunhao Li Xiaodong Wang Xin Yuan Mark D. Butala Gaoang Wang The College of Information Science and Electronic Engineering Zhejiang University Hangzhou China Zhejiang University-University of Illinois Urbana-Champaign Institute Zhejiang University Haining China The College of Computer Science and Technology Zhejiang University Hangzhou China School of Engineering Westlake University Hangzhou China James Watt School of Engineering University of Glasgow Scotland United Kingdom

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Snapshot compressive imaging (SCI) is a compressed sensing (CS)-based high-speed imaging modality. Recent efforts have explored the underlying 3D representation from only an SCI image using neural radiance fields (NeRF), yet the training time, rendering computation cost, and reconstruction quality limitations are general issues that have limited wider adoption. This paper introduces SCI-Gaussian, the first 3D-aware SCI reconstruction based on 3D Gaussian splatting (3D-GS). This method utilizes an explicit 3D representation to achieve efficient and high-quality scene reconstruction. The motivation stems from the highly efficient representation and surprising quality of 3D-GS, despite when applied to SCI system, it encounters difficulties in generating point initialization for explicit Gaussians and accurate pose recovery from a single SCI measured image. Specifically, we effectively initialize these Gaussians through sampling a coarsely trained NeRF at various hash structures, then model the physical formation of the SCI measurement and jointly optimize Gaussians and camera trajectories with a bundle adjustment formulation during exposure time. Extensive experiments on synthetic and real-world datasets demonstrate that SCI-Gaussian outperforms the state-of-the-art (SOTA) methods, achieving comparable or better results with significantly 10× faster training and 1000× faster rendering speed than the most recent NeRF-based method.

关键词： Training image coding Costs Rendering (computer graphics) Neural radiance field real-time systems time measurement Trajectory Speech processing image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Approaches for Feature Extraction in Big Data Analytics 10

Deep Learning Approaches for Feature Extraction in Big Data ...

引用

10th IEEE Uttar Pradesh Section International conference on Electrical, Electronics and Computer Engineering, UPCON 2023

作者： Dhaygude, Amol Dattatray Varma, Raj A. Yerpude, Poonam Swarnkar, Suman Kumar Kumar Jindal, Rupesh Rabbi, Fazle University of Washington Department of Data Science Seattle United States Maharashtra Pune India Indian Institute of Technology Dept of Computer Science & Engineering Bhilai India Shri Shankaracharya Institute of Professional Management and Technology Dept of Computer Science and Engineering Raipur India National Institute of Design Dept of Computer Science & Engineering Ahmedabad India Australian Computer Society Australia

ISBN: (纸本)9798350382471

In the context of big data analytics, this study examines the use of algorithms based on deep learning for feature extraction. Traditional methods usually have trouble sifting through the complexity and volume of data to find the important elements. We investigate the application of auto encoders, transformer-based models, convolutional neural networks (CNNs), and recurrent neural networks (RNNs) to address this problem. Our comprehensive review of existing literature compares these deep learning techniques with traditional methods and highlights their adaptability to large-scale datasets. The efficacy and precision of these methodologies are demonstrated by empirical investigations conducted on authentic datasets across a range of disciplines, including but not limited to time-series analysis, picture identification, and natural language processing. Despite challenges like computational requirements and model interpretability, our findings indicate that deep learning-based feature extraction holds significant promise for enhancing big data analytics, leading to valuable insights and discoveries in various fields. © 2023 IEEE.

关键词： Autoencoders Big Data Analytics CNN) Deep Learning Efficiency Feature Extraction image Recognition Natural Language processing RNNs Scalability time-Series Analysis real-World Datasets Transformer Models

来源：评论

学校读者我要写书评

暂无评论

InvGS: a Novel real-time Inverse Rendering Framework Utilizing 3D Gaussian Splatting

InvGS: a Novel Real-Time Inverse Rendering Framework Utilizi...

引用

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

作者： Yang Pu Qingfeng Wu School of Film Xiamen University Xiamen China Xiamen University Xiamen China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

In this paper, we address the problem of reconstructing geometry, material and illumination from multi-view images of a scene captured in an unknown environment. Compared to prevalent NeRF-based methods, which are typically hindered by slow training and time-intensive evaluating, our approach capitalizes on recent advancements in Volume Rendering: point-based 3D Gaussian Splatting (3DGS) techniques. However, the inherent lack of geometric priors in this point-based representation and the material-lighting ambiguity of the radiance field make it intractable for inverse rendering tasks. To overcome this challenge, our method adopt a two-step approach which we call InvGS. First, our method optimize the original parameters of the initial 3DGS point cloud using flattening and alignment regularization to make the Gaussians closer to the object surfaces for reconstructing a more compact geometry. In the second stage, our method jointly optimize lighting and material parameters of 3DGS point cloud through the differentiable rendering process, thereby following the physically-based rendering equation. Benefiting from the fast rasterization of 3DGS and real-time rendering techniques in physically-based rendering, InvGS can reasonably shade each Gaussian under image-based HDR illumination without compromising real-time performance. We demonstrate that our method is comparable to the state of the arts, and even outperform classic and deep learning-based approaches.

关键词： Point cloud compression Geometry Training Three-dimensional displays Lighting Rendering (computer graphics) real-time systems Vectors image reconstruction Surface treatment

来源：评论

学校读者我要写书评

暂无评论

Moving Object Detection in HEVC video

Moving Object Detection in HEVC Video

引用

Asia-Pacific-Signal-and-Information-processing-Association Annual Summit and conference (APSIPA ASC)

作者： Pang, LieLin Wong, KokSheik Univ Malaya Fac Comp Sci & Informat Technol Kuala Lumpur Malaysia Monash Univ Malaysia Sch Informat Technol Subang Jaya Malaysia

ISBN: (纸本)9789881476890

video surveillance has drawn much interest in monitoring physical assets, spaces and events over time for detection of threats as well as business and process monitoring purposes. However, the rising number of recorded videos has significantly increased the time and effort in manual event analysis and video content management. Therefore, automatic moving object detection is of great importance. Nowadays, for storage and transmission purposes, video usually appears in the compressed form. Therefore, in this paper, an automatic moving object detection method is proposed for HEVC video. Specifically, the number of bits spent on coding a frame, which can be extracted during encoding or retrieved from an encoded video bit stream, is exploited as the key feature for moving object detection. In addition, temporal sub-layering feature of HEVC is utilized to reduce the number of frame to be processed, which in turn magnifies the energy of the coded video frames without losing most of the predicted information. A coarse background / foreground mask is then formed based on bit consumption, and it is further refined via post processing to remove noise and to smooth the mask image. The proposed method achieves encouraging results in detecting slow moving objects, even with dynamic background.

关键词： Process monitoring

来源：评论

学校读者我要写书评

暂无评论

Survey of Approaches to Non-realistic Neural Style Transfer 31

Survey of Approaches to Non-Realistic Neural Style Transfer

引用

31st conference of Open Innovations Association FRUCT, FRUCT 2022

作者： Varlamova, Arina Kitov, Victor Lomonosov Moscow State University Moscow Russia

ISBN: (纸本)9789526924472

Despite researchers interest toward style transfer problem, there is still no foremost method available. Difficulties in problem formalization make a comparison of methods especially complicated. This paper covers twelve widely used algorithms in order to provide their comprehensive description and advantages one over another. © 2022 FRUCT Oy.

关键词： Technological innovation image processing real-time systems Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Open-source platform for automated collection of training data to support video-based feedback in surgical simulators

Open-source platform for automated collection of training da...

引用

Medical Imaging conference - image-Guided Procedures, Robotic Interventions, and Modeling

作者： Laframboise, Jacob Ungi, Tamas Sunderland, Kyle Zevin, Boris Fichtinger, Gabor Queens Univ Sch Comp Lab Percutaneous Surg Kingston ON Canada Queens Univ Dept Surg Kingston ON Canada

ISBN: (纸本)9781510633988

Purpose: Surgical training could be improved by automatic detection of workflow steps, and similar applications of image processing. A platform to collect and organize tracking and video data would enable rapid development of image processing solutions for surgical training. The purpose of this research is to demonstrate 3D Slicer / PLUS Toolkit as a platform for automatic labelled data collection and model deployment. Methods: We use PLUS and 3D Slicer to collect a labelled dataset of tools interacting with tissues in simulated hernia repair, comprised of optical tracking data and video data from a camera. To demonstrate the platform, we train a neural network on this data to automatically identify tissues, and the tracking data is used to identify what tool is in use. The solution is deployed with a custom Slicer module. Results: This platform allowed the collection of 128,548 labelled frames, with 98.5% correctly labelled. A CNN was trained on this data and applied to new data with an accuracy of 98%. With minimal code, this model was deployed in 3D Slicer on real-time data at 30fps. Conclusion: We found the 3D Slicer and PLUS Toolkit platform to be a viable platform for collecting labelled training data and deploying a solution that combines automatic video processing and optical tool tracking. We designed an accurate proof-of-concept system to identify tissue-tool interactions with a trained CNN and optical tracking.

关键词： Data collection annotation open source surgical training deep learning image processing hernia 3D Slicer PLUS Toolkit

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of real time image Retrieval System for De-Noising Space images in Chandrayaan 3 Lunar Mission Using Autoencoders

Design and Implementation of Real Time Image Retrieval Syste...

引用

International conference on Contemporary Computing and Informatics (IC3I)

作者： Prince Shubham Pallab Banerjee Kanika Thakur Biresh Kumar Dipta Mitra Kumar Gaurav Department of Computer Science Engineering Amity University Ranchi Jharkhand India Amity School of Information Technology Amity University Ranchi Jharkhand India

ISBN: (数字)9798350350067

ISBN: (纸本)9798350350074

In the context of the Chandrayaan 3 Lunar Mission, this research paper introduces a real-time image retrieval and denoising system powered by autoencoders, designed to tackle the challenge of noisy space imagery. Leveraging advanced deep learning techniques, our system employs autoencoders to extract essential features from the noisy lunar images and subsequently retrieves and integrates similar, noise-free reference images from a comprehensive database. By doing so, it achieves real-time denoising, ensuring that the mission’s acquired lunar images are of high quality, thus facilitating more accurate scientific analysis. The paper details the architecture of the autoencoder-based denoising system, its training process using a meticulously curated lunar image dataset, and its seamless integration into the mission’s image processing pipeline. Experimental results underscore the system’s remarkable noise reduction capabilities, thereby playing a pivotal role in enhancing the Chandrayaan 3 mission’s scientific contributions, ultimately advancing our understanding of the lunar environment and bolstering the success of lunar exploration endeavours.

关键词： Deep learning Training Space missions Moon Noise reduction Autoencoders image retrieval Feature extraction real-time systems Noise measurement

来源：评论

学校读者我要写书评

暂无评论

Investigation of Band Selection Techniques to Enable Classification of Hyperspectral imagery at the Edge

Investigation of Band Selection Techniques to Enable Classif...

引用

conference on real-time image processing and Deep Learning

作者： Butler, Samantha Price, Stanton R. Gurbuz, Ali Price, Stephanie J. Fairley, Joshua R. Mississippi State Univ Dept Elect & Comp Engn Mississippi State MS 39762 USA US Army Engineer Res & Dev Ctr Vicksburg MS 39180 USA

ISBN: (数字)9781510643109

ISBN: (纸本)9781510643109

processing hyperspectral image data can be computationally expensive and difficult to employ for real-time applications due to its extensive spatial and spectral information. Further, applications in which computational resources may be limited, such as those requiring artificial intelligence at the edge, can be hindered by the volume of data that is common with airborne hyperspectral image data. This paper proposes utilizing band selection to down-select the number of spectral bands considering a given classification task so that classification can be done at the edge with lower computational complexity. Specifically, we consider popular techniques for band selection and investigate their feasibility to identify discriminative bands such that classification performance is not drastically hindered. This would greatly benefit applications where time-sensitive solutions are needed to ensure optimal outcomes (this could be related to defense, natural disaster relief/response, agriculture, etc.). Performance of the proposed approach is measured in terms of classification accuracy and run time.

关键词： real-time processing hyperspectral imaging band selection processing on the edge clustering

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 << < 491 492 493 494 495 496 497 498 499 500 > >>

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：