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

8,291 篇 会议
395 篇 期刊文献
17 篇 学位论文
11 册 图书
3 篇 资讯

馆藏范围

8,717 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

5,399 篇 工学
- 3,222 篇 计算机科学与技术...
- 1,815 篇 电气工程
- 1,716 篇 软件工程
- 1,350 篇 信息与通信工程
- 590 篇 机械工程
- 532 篇 控制科学与工程
- 467 篇 电子科学与技术（可...
- 453 篇 光学工程
- 348 篇 仪器科学与技术
- 208 篇 安全科学与工程
- 200 篇 生物医学工程（可授...
- 163 篇 交通运输工程
- 147 篇 材料科学与工程（可...
- 132 篇 生物工程
- 94 篇 航空宇航科学与技...
- 82 篇 测绘科学与技术
- 69 篇 化学工程与技术
- 64 篇 土木工程
1,968 篇 理学
- 1,384 篇 物理学
- 465 篇 数学
- 159 篇 系统科学
- 140 篇 生物学
- 111 篇 统计学（可授理学、...
- 75 篇 化学
1,375 篇 医学
- 1,301 篇 临床医学
- 114 篇 特种医学
378 篇 管理学
- 275 篇 管理科学与工程(可...
- 107 篇 图书情报与档案管...
- 78 篇 工商管理
54 篇 法学
- 49 篇 社会学
28 篇 经济学
28 篇 农学
24 篇 教育学
20 篇 艺术学
15 篇 文学
15 篇 军事学

主题

1,031 篇 image processing
709 篇 cameras
622 篇 streaming media
503 篇 real time system...
503 篇 real-time system...
444 篇 image segmentati...
384 篇 image coding
298 篇 object detection
298 篇 image edge detec...
270 篇 image color anal...
258 篇 video coding
257 篇 feature extracti...
253 篇 motion estimatio...
249 篇 hardware
218 篇 pixel
193 篇 computer archite...
181 篇 graphics process...
165 篇 video compressio...
162 篇 video
162 篇 field programmab...

机构

14 篇 school of commun...
12 篇 beijing key labo...
10 篇 institute of inf...
8 篇 univ chinese aca...
8 篇 center for signa...
7 篇 heinrich hertz i...
7 篇 tsinghua univ de...
7 篇 chinese acad sci...
7 篇 microsoft res as...
7 篇 department of co...
6 篇 univ pisa dept i...
6 篇 microsoft resear...
6 篇 eindhovan univer...
6 篇 imec leuven
6 篇 school of inform...
6 篇 hewlett packard ...
6 篇 electrical and c...
5 篇 tsinghua univers...
5 篇 beijing inst tec...
5 篇 tampere univ ult...

作者

17 篇 wang qi
13 篇 grecos christos
12 篇 li li
11 篇 saponara sergio
10 篇 nightingale jame...
9 篇 gohshi seiichi
9 篇 cheung gene
9 篇 ponomaryov volod...
9 篇 de with peter h....
8 篇 li ying
8 篇 zhang hong
8 篇 satoshi goto
8 篇 takaki takeshi
8 篇 van der schaar m
7 篇 amer aishy
7 篇 luciano agostini
7 篇 agostini luciano
7 篇 wang chunping
7 篇 chien shao-yi
7 篇 sarmiento r

语言

8,346 篇 英文
180 篇 其他
173 篇 中文
19 篇 土耳其文
3 篇 葡萄牙文
1 篇 西班牙文
1 篇 俄文

检索条件"任意字段=Conference on Real-Time Image and Video Processing 2011"

共 8717 条记录，以下是361-370 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：

2023 8th International conference on Signal and image processing, ICSIP 2023

2023 8th International Conference on Signal and Image Proces...

引用

8th International conference on Signal and image processing, ICSIP 2023

ISBN: (纸本)9798350397932

The proceedings contain 210 papers. The topics discussed include: facial expression recognition based on the combination of landmarks and texture features;review of quality assessment algorithms on the realistic blurred image database (BID2011);a hybrid approach for customized skull-stripping MR brain images;the development of a quick-look radar processor for detecting small sea vessels;RF fingerprint identification for 5G mobile device based on transient features;respiratory sound classification based on SWIN transformer;design of ess-based adaptive particle filter for real-time tracking;joint modeling and simulation of tropospheric scattering communication channel based on OPNET and MATLAB;lattice-based privacy enhanced identity protocol for SDO services;automatic detection of lunar rocks using single shot multibox detector;and scene cartoonization algorithm based on generative adversarial network.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Embedded Devices for real-time video Lane Detection 29

Evaluation of Embedded Devices for Real-Time Video Lane Dete...

引用

29th International conference on Mixed Design of Integrated Circuits and System (MIXDES)

作者： Podbucki, Kacper Suder, Jakub Marciniak, Tomasz Dabrowski, Adam Poznan Univ Tech Fac Automat Control Robot & Elect Engn Inst Automat Control & Robot Div Signal Proc & Elect Syst Jana Pawla II 24 PL-60965 Poznan Poland

ISBN: (数字)9788363578220

ISBN: (纸本)9781665461764

This paper presents a comparison of the performance of embedded systems processing video sequences in real time. As part of the work, practical programs for detecting lanes located on airport areas, which allow autonomous vehicles to move around the airport, were tested. The following modules were used during the tests: Raspberry Pi 4B, NVIDIA Jetson Nano, NVIDIA Jetson Xavier AGX. For modules from the NVIDIA Jetson family, the maximum performance of video stream processing depending on the resolution and the selected power mode has been checked. The results of the experiment show that NVIDIA Jetson modules have sufficient computing resources to effectively track lines based on the camera image, even in low power modes.

关键词： lane detection embedded systems video analysis microprocessor power modes NVIDIA Jetson Raspberry Pi

来源：评论

学校读者我要写书评

暂无评论

FrameFire: Enabling Efficient Spiking Neural Network Inference for video Segmentation 5

FrameFire: Enabling Efficient Spiking Neural Network Inferen...

引用

5th IEEE International conference on Artificial Intelligence Circuits and Systems, AICAS 2023

作者： Chen, Qinyu Sun, Congyi Gao, Chang Fang, Xinyuan Luan, Haitao

ISBN: (纸本)9798350332674

Fast video recognition is essential for real-time scenarios, e.g., autonomous driving. However, applying existing Deep Neural Networks (DNNs) to individual high-resolution images is expensive due to large model sizes. Spiking Neural Networks (SNNs) are developed as a promising alternative to DNNs due to their more realistic brain-inspired computing models. SNNs have sparse neuron firing over time, i.e., spatio-temporal sparsity;thus they are useful to enable energy-efficient computation. However, exploiting the spatio-temporal sparsity of SNNs in hardware leads to unpredictable and unbalanced workloads, degrading energy efficiency. In this work, we, therefore, propose an SNN accelerator called FrameFire for efficient video processing. We introduce a Keyframe-dominated Workload Balance Schedule (KWBS) method. It accelerates the image recognition network with sparse keyframes, then records and analyzes the current workload distribution on hardware to facilitate scheduling workloads in subsequent frames. FrameFire is implemented on a Xilinx XC7Z035 FPGA and verified by video segmentation tasks. The results show that the throughput is improved by 1.7× with the KWBS method. FrameFire achieved 1.04 KFPS throughput and 1.15 mJ/frame recognition energy. © 2023 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Underground target location method based on positive image-based camera position and pose estimate 23

Underground target location method based on positive image-b...

引用

6th International conference on Signal processing and Machine Learning, SPML 2023

作者： Liu, Yi Cai, Wen-Hao Wang, Wen-Ke Lyu, Zhi-Qin Min, Zhi-Peng Gao, Yu-Xiang China

ISBN: (纸本)9798400707575

At present, the traditional underground target positioning technology is passive positioning. It needs to rely on external equipment such as communication networks, hosts and reference base stations with known position coordinates to achieve target positioning. The location system is complex and the ability to resist disasters is weak. To get rid of the problems existing in the passive positioning system, this paper proposes an underground target location method based on a positive image-based camera position and pose estimate. The method consists of two stages: an offline stage and a real-time positioning stage. In the offline stage, a number of identification signboards are arranged at known positions in the tunnel, and the coordinate position information of each identification signboard is recorded, and it is built into the identification signboard-position information database. In the real-time positioning stage, the main body of this stage is the camera, and the camera, video analysis module, and storage module storing the signboard-position information database is embedded into the embedded system, and the embedded system is carried by the positioning target. The embedded system uses the camera and video analysis module to find one of the signboards, finds the coordinate position information of the signboard in the signboard-position information database, and establishes the signboard coordinate system with the coordinate position as the origin;according to the angle The coordinate value of the point in the pixel coordinate system and the signboard coordinate system, as well as the PnP algorithm, calculate the coordinate value of the corner point in the camera coordinate system. Through the different coordinate values of the same corner point in the camera coordinate system and the signboard coordinate system, the mutual relationship between the two coordinate systems is solved by inversion, that is, the camera extrinsic parameters. The relative pose of the ca

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Cascade Attentional Fusion for Unsupervised Domain Adaptation on Multi-Modal Egocentric video Analysis

Cascade Attentional Fusion for Unsupervised Domain Adaptatio...

引用

2023 International conference on image, Signal processing, and Pattern Recognition, ISPP 2023

作者： Liu, Xianyuan Zhang, Sanxing Lei, Tao Jiang, Ping Institute of Optical and Electronics Chinese Academy of Sciences Chengdu610209 China School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing101408 China University of Chinese Academy of Sciences Beijing100049 China

ISBN: (纸本)9781510666351

Supervised learning models require a large-scale dataset for more effective model training. However, a large-scale dataset requires time-consuming data collection and highly complicated preprocessing, posing a significant challenge for researchers. Therefore, creating a large-scale dataset for each practical application is unachievable in a real-world setting. In this case, unsupervised domain adaptation is crucial for practical applications, as it can enable models to enhance their performance on unlabeled data by training on labeled data. For multi-modal egocentric video analysis, some models have used unsupervised domain adaptation and achieved outstanding performance. However, they use either early or late fusion, ignoring the correlation in and between multi-modal inputs. Therefore, this paper investigates different fusion architecture and proposes a cascade attentional fusion to improve the feature representation for unsupervised domain adaptation on multi-modal egocentric video analysis. First, we propose a cascade fusion architecture for increased audio signal reuse. Then, we propose a temporal-spatial attention mechanism for highlighting spatio-temporal feature representations. Third, we propose a novel cascade attentional fusion method for multi-modal egocentric video data fusion by incorporating the architecture and attention model described previously. In addition, we study the ways for integrating different attentions. Finally, we propose an adversarial domain alignment model that incorporates the proposed fusion for unsupervised domain adaptation on multi-modal egocentric video analysis, reaching state-of-the-art performance on the public dataset. © 2023 SPIE.

关键词： Data fusion

来源：评论

学校读者我要写书评

暂无评论

real-ESRGAN in Neural Rendering Frameworks for High-Fidelity video Upscaling

Real-ESRGAN in Neural Rendering Frameworks for High-Fidelity...

引用

Advanced Computing Technologies (ICoACT), International conference on

作者： Sarthak Das Shivani Kamboj Department of Mathematics (of Aff.) Chandigarh University Chandigarh India

ISBN: (数字)9798331509859

ISBN: (纸本)9798331509866

As digital video content continues to grow, the need for enhanced visual quality has become increasingly important. However, utilizing the real-ESRGAN video module can often lead to issues such as frame skipping and inconsistent enhancement results. This paper tackles these issues by introducing a novel approach that enhances individual frames of a video separately. By converting the original video into distinct frames and applying real-ESRGAN for enhancement, we ensure that each frame is treated individually, thereby eliminating frame skips and achieving uniform enhancement across the video. After processing, the frames are reassembled into a cohesive video output. Our extensive evaluations reveal significant improvements in visual fidelity compared to conventional enhancement techniques. This research highlights the promise of integrating neural rendering methods in various fields, including film, gaming, and online streaming, and provides valuable contributions to the evolving landscape of video processing.

关键词： Measurement Visualization Laplace equations Streaming media Media Rendering (computer graphics) real-time systems Computational efficiency image restoration image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Based Low Light Enhancements for Advanced Driver-Assistance Systems at Night 17

Deep Learning Based Low Light Enhancements for Advanced Driv...

引用

17th IEEE International conference on Industrial and Information Systems, ICIIS 2023

作者： Ranasinghe, Pamudu Muthukuda, Dilshan Morapitiya, Primash Dissanayake, Maheshi B Lakmal, H.K.I.S. University of Peradeniya Dept. Electrical & Electronic Eng. Peradeniya Sri Lanka

ISBN: (纸本)9798350323634

In the modern automobile industry, full/partial autonomous driving has become a common phenomenon. These systems heavily rely on sensors, both visual and non-visual, such as cameras and LIDAR, to interpret their surroundings and aid the decision-making process. Recently, visual-only sensing devices, mainly cameras, have emerged as the primary sensor for obtaining an immersive feeling in autonomous driving. However, the performance of such systems is heavily constrained by fluctuating light intensity and shadows. The primary goal of the presented research is to develop an effective low-light image enhancement system that improves the perception and inter-pretability of images taken in low-light driving environments. The developed image enhancement architecture demonstrates remarkable capabilities, surpassing existing models in terms of real-time suitability, PSNR (Peak Signal-to-Noise Ratio), and SSIM (Structural Similarity Index) values. Additionally, the model has been specifically designed to have low resource usage, making it an ideal solution for deployment on low-end devices. With significantly lower inference time, the model is exceptionally well-suited for real-time operation in autonomous driving applications. Furthermore, this architecture provides an efficient and effective solution not only for autonomous driving but also for a range of applications in video/image processing and computer vision, such as surveillance systems, medical imaging, astronomy, underwater imaging, and the mining industry. Finally, the relatively short training time makes it an attractive option for researchers and developers. Overall, this architecture represents a significant advancement in low-light image enhancement and autonomous vehicles. A demo of the system and the source code of the proposed LLE_UNET can be found on https://***/pamudu123ILow_Light_image_Enhancement. © 2023 IEEE.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

VIhanceD: Efficient video Super Resolution for Edge Devices 2

VIhanceD: Efficient Video Super Resolution for Edge Devices

引用

2nd Edition of IEEE Delhi Section Owned conference, DELCON 2023

作者： Papanai, Ashish Babbar, Siddharth Pandey, Anshuman Kathuria, Harshit Sharma, Alok Kumar Gupta, Namita Maharaja Agrasen Institute of Technology Department of Computer Science and Engineering Delhi India

ISBN: (纸本)9798350322064

video Super Resolution (VSR) aims to generate high-resolution (HR) frames from corresponding low-resolution (LR) frames. It draws a stark contrast from single image super-resolution (SISR) because of its high temporal dependency on misaligned supporting frames. The existing methods involve using RNNs to learn the temporal dependency by using other networks (CNNs, GANs) for predicting neighboring pixels. Due to the memory and processing constraints and the inference time required for up-scaling LR frames, a wide variety of VSR techniques cannot be applied to mid-range and budget mobile devices. This paper presents VIhanceD, a real-time sliding window-based network that can operate on budget smartphones and laptops while producing cutting-edge results on various video datasets. Our approaches include both spatial and temporal dependencies to make the up-scaled HR frames coherent and free of motion distortions. We focus on enhancing the user experience in areas with internet restrictions due to social, political, and geographical limitations. The mobile app (and PC client) provides a continuous stream of HR frames without buffering. We obtained 33.9 PSNR on REDS Dataset with a single frame inference time of 23.6 ms demonstrating state-of-the-art performance. Our subsequent experiments on VIMEO-90K dataset demonstrates that the suggested method is generalizable and works on natural video frames and textual data, making it suitable for infotainment and multimedia. © 2023 IEEE.

关键词： Optical flows

来源：评论

学校读者我要写书评

暂无评论

EdgeRelight360: Text-Conditioned 360-Degree HDR image Generation for real-time On-Device video Portrait Relighting

EdgeRelight360: Text-Conditioned 360-Degree HDR Image Genera...

引用

IEEE Computer Society conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

作者： Min-Hui Lin Mahesh Reddy Guillaume Berger Michel Sarkis Fatih Porikli Ning Bi Qualcomm AI Research

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

In this paper, we present EdgeRelight360, an approach for real-time video portrait relighting on mobile devices, utilizing text-conditioned generation of 360-degree high dynamic range image (HDRI) maps. Our method proposes a diffusion-based text-to-360-degree image generation in the HDR domain, taking advantage of the HDR10 standard. This technique facilitates the generation of high-quality, realistic lighting conditions from textual descriptions, offering flexibility and control in portrait video relighting task. Unlike the previous relighting frameworks, our proposed system performs video relighting directly on-device, enabling real-time inference with real 360-degree HDRI maps. This on-device processing ensures both privacy and guarantees low runtime, providing an immediate response to changes in lighting conditions or user inputs. Our approach paves the way for new possibilities in real-time video applications, including video conferencing, gaming, and augmented reality, by allowing dynamic, text-based control of lighting conditions.

关键词： Privacy Runtime image synthesis image edge detection Lighting Streaming media real-time systems

来源：评论

学校读者我要写书评

暂无评论

real-time video Prediction With Fast video Interpolation Model and Prediction Training

Real-Time Video Prediction With Fast Video Interpolation Mod...

引用

IEEE International conference on image processing

作者： Shota Hirose Kazuki Kotoyori Kasidis Arunruangsirilert Fangzheng Lin Heming Sun Jiro Katto School of Fundamental Science and Engineering Waseda University Tokyo Japan School of Engineering Tokyo Institute of Technology Tokyo Japan Yokohama National University Kanagawa Japan

ISBN: (数字)9798350349399

ISBN: (纸本)9798350349405

Transmission latency significantly affects users’ quality of experience in real-time interaction and actuation. As latency is principally inevitable, video prediction can be utilized to mitigate the latency and ultimately enable zero-latency transmission. However, most of the existing video prediction methods are computationally expensive and impractical for real-time applications. In this work, we therefore propose real-time video prediction towards the zero-latency interaction over networks, called IFRVP (Intermediate Feature Refinement video Prediction). Firstly, we propose three training methods for video prediction that extend frame interpolation models, where we utilize a simple convolution-only frame interpolation network based on IFRNet. Secondly, we introduce ELAN-based residual blocks into the prediction models to improve both inference speed and accuracy. Our evaluations show that our proposed models perform efficiently and achieve the best trade-off between prediction accuracy and computational speed among the existing video prediction methods. A demonstration movie is also provided at http://***/IFRVPDemo.

关键词： Training Interpolation Accuracy Computational modeling Streaming media Predictive models real-time systems

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 << < 33 34 35 36 37 38 39 40 41 42 > >>

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：