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

795 篇 会议
12 册 图书
2 篇 期刊文献

馆藏范围

809 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

512 篇 工学
- 356 篇 计算机科学与技术...
- 235 篇 软件工程
- 148 篇 控制科学与工程
- 133 篇 电气工程
- 125 篇 信息与通信工程
- 71 篇 电子科学与技术（可...
- 68 篇 光学工程
- 61 篇 机械工程
- 40 篇 材料科学与工程（可...
- 38 篇 生物医学工程（可授...
- 37 篇 交通运输工程
- 34 篇 仪器科学与技术
- 33 篇 安全科学与工程
- 28 篇 生物工程
- 23 篇 化学工程与技术
- 22 篇 土木工程
- 21 篇 动力工程及工程热...
- 20 篇 网络空间安全
- 16 篇 建筑学
- 14 篇 石油与天然气工程
176 篇 理学
- 80 篇 物理学
- 71 篇 数学
- 33 篇 生物学
- 27 篇 化学
- 12 篇 系统科学
- 12 篇 统计学（可授理学、...
117 篇 管理学
- 92 篇 管理科学与工程(可...
- 34 篇 图书情报与档案管...
- 24 篇 工商管理
44 篇 医学
- 40 篇 临床医学
9 篇 教育学
8 篇 农学
6 篇 法学
5 篇 经济学
2 篇 文学
2 篇 军事学

主题

77 篇 accuracy
54 篇 image processing
49 篇 feature extracti...
41 篇 real-time system...
40 篇 deep learning
38 篇 convolutional ne...
32 篇 training
31 篇 image segmentati...
31 篇 image recognitio...
30 篇 computational mo...
25 篇 image enhancemen...
25 篇 object detection
23 篇 visualization
20 篇 computer vision
17 篇 cameras
16 篇 optimization
16 篇 artificial intel...
15 篇 image classifica...
15 篇 data models
15 篇 robustness

机构

6 篇 fujian provincia...
6 篇 university of ch...
6 篇 college of compu...
5 篇 fujian provincia...
4 篇 guangdong univer...
4 篇 huzhou key labor...
4 篇 harbin institute...
4 篇 institutes for r...
4 篇 school of intell...
3 篇 hohai university
3 篇 shandong institu...
3 篇 school of comput...
3 篇 school of inform...
3 篇 shenyang institu...
3 篇 guangzhou mariti...
3 篇 nanjing universi...
3 篇 xi'an shiyou uni...
3 篇 school of electr...
3 篇 school of engine...
3 篇 north china univ...

作者

9 篇 li zuoyong
5 篇 wang tao
3 篇 li yang
3 篇 sabina jeschke
3 篇 wang dan
3 篇 liang lingyu
3 篇 honghai liu
3 篇 daniel schilberg
3 篇 wang bo
3 篇 putz barbara
3 篇 guo bao-long
3 篇 ching fum yew
3 篇 keikhosrokiani p...
3 篇 chen jian
2 篇 yufeng hu
2 篇 zhang tao
2 篇 niu zhenhua
2 篇 xiaona kang
2 篇 haijun zhang
2 篇 erdal erdal

语言

758 篇 英文
42 篇 其他
16 篇 中文

检索条件"任意字段=4th International Conference on Image Processing and Intelligent Control, IPIC 2024"

共 809 条记录，以下是1-10 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：

Feature Extraction and three-dimensional Reconstruction based Power Tower Tilt Measurement 24

Feature Extraction and Three-dimensional Reconstruction base...

引用

4th international Joint conference on Robotics and Artificial Intelligence, JCRAI 2024

作者： Ge, Mengying Yu, Jirong Zhu, Chenyi Wu, Shuang Jinken College of Technology Nanjing China

ISBN: (纸本)9798400710100

To prevent power accidents caused by the tilt of power towers and improve the efficiency of daily maintenance and inspection of power towers, an efficient and convenient power tower tilt measurement method based on feature extraction and three-dimensional reconstruction is proposed. First, a stereo camera is used to collect images of power towers, and distortion and stereo correction are performed on the images according to the principle of stereo vision calibration. Second, the pre-processed images are sent to the first detection module, which is power tower side edge feature extraction. third, the images are sent to the three-dimensional reconstruction module, and a stereo matching algorithm suitable for the side edge image of the power tower is proposed using the principle of parallax, and a three-dimensional reconstruction of the side edge of the power tower is performed. Finally, the inclination algorithm of the power tower is deduced based on the geometric principle, and the maintenance inspection of the power tower is obtained suggestion. the system was applied for experiments, and the results showed that this method can accurately and conveniently calculate the inclination of the power tower. © 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Stereo image processing

来源：评论

学校读者我要写书评

暂无评论

Research on Multi-class Fine Motor Intention Recognition of Hands 24

Research on Multi-class Fine Motor Intention Recognition of ...

引用

4th international conference on Signal processing and Communication Technology, SPCT 2024

作者： Yang, Yang Yan, Bian Miao, Sun Tianjin Key Laboratory of Information Sensing and Intelligent Control Tianjin Vocational and Technical Normal University Tianjin China

ISBN: (纸本)9798400710636

To address the problem of poor precision of fine motor intention recognition, which is difficult to apply to the field of neural rehabilitation, this paper designed a bilateral motor imagery (MI) paradigm using dynamic visual imagery: there were four kinds of motor intentions: left hand to finger, left hand to grip, right hand to finger, right hand to grip. Time-frequency map, brain topographic map and R2 coefficient were used to analyze the divisibility features among different categories. FBCSP (filter bank - common space model) and SVM (support vector machine) models were used to classify the fine motor intentions among various categories. the research results prove that the event-related desynchronization (ERD) features of multiple types of fine motor intentions in the same part are separable under the dynamic visual auxiliary stimulus paradigm. the average recognition accuracy of 4 types of fine motor intentions of 12 subjects can reach 63.7±3.67%, which is significantly higher than the random probability of 4 types. the experimental results show that the proposed method can effectively distinguish multiple types of fine motor intentions in the same part, and provide a new way for its application in the field of neurological rehabilitation. © 2024 Copyright held by the owner/author(s).

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

Machine vision and image processing for intelligent online monitoring and control of pharmaceutical fluidized bed granulation processes 4

Machine vision and image processing for intelligent online m...

引用

4th international conference on Computer Vision, Application, and Algorithm, CVAA 2024

作者： Liu, Yan Wu, Tao Wang, Xue Zhong Beijing Key Laboratory of Enze Biomass Fine Chemicals College of New Materials and Chemical Engineering Beijing Institute of Petrochemical Technology Beijing102617 China

ISBN: (数字)9781510687622

ISBN: (纸本)9781510687615

Fluidized bed granulation is a unit operation widely used in the pharmaceutical, chemical and food processing industries. It is a manufacturing technology that by suspending lose powders using hot air and transforms the powders into granules of uniform sizes to improve compaction and flow characteristics. the granule size distribution and moisture content are important quality indicators that are currently characterized by sampling and offline analysis in the laboratory, leading to time delay in measurement. this work reports an investigation of machine vision combined with deep learning image segmentation for on-line real-time monitoring. A non-invasive microscopic imaging probe with an integrated light source is designed and mounted on the granulator’s sight glass to monitoring the granule dynamic changes in particle morphology and size. In addition, a near-infrared spectrometer combined with chemometric modeling is used for real-time monitoring of moisture content. © 2025 SPIE.

关键词： Near infrared spectroscopy

来源：评论

学校读者我要写书评

暂无评论

Enhancing pedestrian re-identification in low-light environments with multi-scale feature attention extraction network 4

Enhancing pedestrian re-identification in low-light environm...

引用

4th international conference on Computer Vision, Application, and Algorithm, CVAA 2024

作者： Li, Zhenghao Xiong, Jiping Li, Jiake College of Physics and Electronic Information Engineering Zhejiang Normal University Zhejiang Hangzhou China

ISBN: (数字)9781510687622

ISBN: (纸本)9781510687615

Pedestrian re-identification has witnessed rapid development in recent years, with particular attention given to the challenges posed by complex conditions, including pedestrian re-identification in low-light environments, such as nighttime scenarios. through our experiments, it was discovered that even with image enhancement in low-light conditions, satisfactory results were not achieved. To address this challenge, this paper introduces a Multi-scale Feature Attention Extraction (MFAE) network. © 2025 SPIE.

关键词： Feature extraction image enhancement Network architectures image segmentation Education and training image processing Data modeling image restoration Lithium Pollution control

来源：评论

学校读者我要写书评

暂无评论

An improved asymptotic denoising algorithm for infrared images of electrical equipment based on Non-Local means 4

An improved asymptotic denoising algorithm for infrared imag...

引用

4th international conference on Network Communication and Information Security, ICNCIS 2024

作者： Zhou, Yunlei Dong, Xiaojie Liu, Chengyi Pi, Minghuan Le, Yanbo College of Intelligent Systems Science and Engineering Hubei Minzu University Enshi445000 China

ISBN: (数字)9781510688261

ISBN: (纸本)9781510688254

Infrared images are susceptible to Gaussian noise during acquisition and transmission. To meet the quality requirements for infrared image data in image processing, an asymptotic Non-Local Means (NLM) algorithm based on an improved Scharr operator was proposed for denoising infrared images of electrical equipment. Firstly, the RGB infrared images were converted to the Y channel. Secondly, the improved Scharr operator was used to adjust the computation weights of the NLM algorithm, better preserving the edge details of the images. To optimize the denoising effect, a multi-layer pyramid was constructed, and a layer-by-layer denoising fusion method was adopted to obtain the initially denoised images. Finally, for the residual noise in the initially denoised images, asymptotic denoising was employed, adjusting the filter parameters based on the image characteristics for secondary denoising, followed by image reconstruction to obtain the denoised images. Experimental results showed that the proposed algorithm achieved clear and complete denoised images, with Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity (SSIM) improved by 0.78 to 4.95 and 0.01 to 0.08, respectively, compared to other methods. this indicated that the method is effective for high-efficiency denoising of infrared images of electrical equipment. © 2025 SPIE.

关键词： Infrared imaging

来源：评论

学校读者我要写书评

暂无评论

Phase Retrieval System Based on Refractive Index Change 4

Phase Retrieval System Based on Refractive Index Change

引用

4th international Computational Imaging conference, CITA 2024

作者： Cheng, Hong Zhang, Hongyi Wang, Li Fenzhang Li, Shuhan Key Laboratory of Intelligent Computing & Signal Processing Anhui University Anhui Province Hefei230601 China

ISBN: (纸本)9781510688834

the phase recovery method based on the Transport of Intensity Equation is widely used in the field of microscopic imaging of biological cells. When using this method for phase recovery, the CCD is always moved to acquire intensity images at different out-of-focus positions, which introduces mechanical errors, it also causes errors when using the traditional FFT method. Based on this, this paper proposes a phase recovery system based on refractive index change: firstly, an image acquisition system with a refractive index medium is built, and two intensity images with different refractive index are acquired;the intensity-phase equation based on refractive index change is established, and the "maximum intensity" assumption method is introduced to solve this equation. then, we can obtain high-precision phase results without moving the CCD. In this paper, the feasibility and accuracy of this technique are confirmed by numerical simulation and optical experiment respectively. © 2025 SPIE.

关键词： Refractive index

来源：评论

学校读者我要写书评

暂无评论

An Improved Residual Network image Enhancement Method for Surface Defect Reconstruction 4

An Improved Residual Network Image Enhancement Method for Su...

引用

4th international Computational Imaging conference, CITA 2024

作者： Sun, Shangrongxi Peng, Xing Shi, Feng College of Intelligent Science and Technology National University of Defense Technology Hunan Changsha410073 China Hunan Provincial Key Laboratory of Ultra-Precision Machining Technology Hunan Changsha410073 China

ISBN: (纸本)9781510688834

Laser additive manufacturing (LAM) technology is widely used in the industrial field because of its convenience and precision. With the influence of the processing environment and parameter setting, the AM process often produces scratches, cracks, holes, and other defects. Further analysis of these defects is essential. However, improving defect detection technology only from optical devices is costly and ineffective. therefore, this paper performs super-resolution reconstruction of PBF part defect pictures, which provides ideas for further analysis of part defects. Starting from the algorithm level, this paper first uses the image fusion method to fuse the part defect images and then uses the improved ResNet model to perform super-resolution reconstruction of the fused image. For improved ResNet, this paper accelerates training by replacing the RELU activation function with the Hardswish function and enhances training stability by adding a tanh function at the output layer to normalize the output to the [-1,1] range. this paper compares the improved ResNet model with Nearest, Bicubic, and CNN, which shows the effectiveness of the improved ResNet algorithm in PBF part defect image reconstruction from evaluation indicators such as PSNR, SIMM, and MSE. For the scratching-fusion, crack-fusion, and hole-fusion test images selected in the experiment, the PSNR index of the improved ResNet model is increased by about 11.2463%, 26.1737%/, 3.8462% respectively compared with the CNN, Bicubic, Nearest algorithm. Its SSIM index is increased by about 1.9580%, 2.0765%, and 10.6688% respectively. For scratch-fusion and crack-fusion images, the MSE index of the improved ResNet model is reduced by more than 60%. For hole-fused images, compared with CNN, Bicubic, and Nearest algorithms, the MSE index decreases by about 6.7772%, 5.3827%, and 38.4451% respectively. this proves that the SR image of the improved ResNet algorithm is more informative, the contour is clearer, and the recons

关键词： image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Target recognition technology for unmanned ships based on improved YOLOv5 4

Target recognition technology for unmanned ships based on im...

引用

2024 4th international conference on intelligent Traffic Systems and Smart City, ITSSC 2024

作者： Yuan, Mingkai Liang, Bingnan Wang, Haoliang Dong, Yixuan School of Marine Engineering Dalian Maritime University Dalian116026 China Department of Automation Shanghai Jiaotong University Shanghai200240 China Dalian Key Laboratory of Swarm Control and Electrical Technology for Intelligent Ships Dalian116026 China State Key Laboratory of Maritime Technology and Safety Dalian116026 China

ISBN: (纸本)9781510686304

To enable safe and efficient autonomous navigation of unmanned ships in complex marine environments, particularly when encountering overtaking, head-on, or crossing scenarios, it is crucial to accurately identify and detect unknown unmanned vessels. this paper proposes a lightweight object detection algorithm tailored to these challenges. the lightweight network Ghostnet is used to improve the backbone network of the YOLOv5s algorithm, achieving lightweight target detection. By introducing the ECA attention mechanism, the model can better focus on important information in the image, enhancing the ability of feature representation, and improving the model's capability for complex scene understanding and target recognition and localization. Finally, the MPDIoU is used as the bounding box loss function for the YOLOv5s algorithm, which not only improves convergence speed but also obtains more accurate regression results. Comparative experiments show that the proposed improved algorithm outperforms models such as YOLOv5-BiFPN, YOLOv5-CBAM, and YOLOv5-SE in terms of model size, computational complexity, parameter count, detection speed, and average precision. © 2025 SPIE.

关键词： Marine navigation

来源：评论

学校读者我要写书评

暂无评论

Cycle-GAN-based holographic reconstruction for 3D particle fields 4

Cycle-GAN-based holographic reconstruction for 3D particle f...

引用

4th international Computational Imaging conference, CITA 2024

作者： Deng, Dingnan Fu, Xin Wang, Chengguo Zhang, Shuiyin School of Physics and Electronic Engineering Jiaying University Meizhou514015 China Meizhou Intelligent Photoelectric Detection Application Engineering Technology Research Center Meizhou514015 China

ISBN: (纸本)9781510688834

A self-supervised model based on CycleGAN is proposed to reconstruct the 3D particle fields from the unpaired data sets. the ground truth can be obtained by converting the 3D information of the particle field into a 2D grayscale image. the hologram of particles is the input of network model. A training model based on CycleGAN is designed. the unpaired data not only alleviates the pressure of data demand but also simplifies the design of the holographic device. thus, the model training can proceed with incomplete data. With the cycle consistency of the mode, the particle characterization is more accurate. In order to assess the viability of the proposed scheme, the structural similarity (SSIM) between the reconstructed result and the ground truth is calculated. © 2025 SPIE.

关键词： 3D reconstruction

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of intelligent Coupled Rearview Mirror Variable Position Structure 4th

Design and Implementation of Intelligent Coupled Rearview Mi...

引用

4th international conference on Mechanical Design and Simulation, MDS 2024

作者： Liu, Jinghui Xu, Tongqiang Du, Guangfu Wu, Liying School of Mechanical and Vehicle Engineering Linyi University Linyi276000 China Information Department Linyi University Linyi276000 China

ISBN: (纸本)9789819778867

In view of the shortcomings of the traditional optical rearview mirror, such as the existence of blind zone, rain weather, snow weather and night vision observation are not effective and the wind resistance coefficient of automobile at high speed is large, which affects fuel economy and other problems. Because the reliability of electronic rearview mirrors is lower than that of traditional rearview mirrors. therefore, a coupled variable position intelligent rearview mirror is designed. It has both the structure of traditional optical rearview mirror and the image processing ability of electronic rearview mirror. Under the condition of satisfying the driver's visual habits, it can effectively improve the visual effects of different scenes, and improve the reliability and driving safety of the car. By designing the displacement mechanism, the information display mechanism can be folded into the cab. It can effectively reduce the air resistance and wind noise when the car is driving at high speed. It can improve the fuel economy and NVH performance of automobiles. By using SolidWorks to carry out three-dimensional design and motion simulation, it is proved that there is no interference in the motion process of the displacement mechanism. It can realize automatic displacement according to different situations, and it has human-computer interaction ability and a higher degree of intelligence. © the Author(s) 2025.

关键词： Fuel economy

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81页 << < 1 2 3 4 5 6 7 8 9 10 > >>

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：