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

128 篇 会议

馆藏范围

128 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

89 篇 工学
- 66 篇 计算机科学与技术...
- 35 篇 软件工程
- 25 篇 电气工程
- 22 篇 信息与通信工程
- 18 篇 电子科学与技术（可...
- 17 篇 光学工程
- 15 篇 控制科学与工程
- 11 篇 安全科学与工程
- 10 篇 材料科学与工程（可...
- 10 篇 交通运输工程
- 10 篇 生物工程
- 8 篇 机械工程
- 6 篇 仪器科学与技术
- 4 篇 动力工程及工程热...
- 4 篇 土木工程
- 4 篇 生物医学工程（可授...
- 3 篇 力学（可授工学、理...
- 3 篇 建筑学
- 3 篇 化学工程与技术
- 3 篇 航空宇航科学与技...
34 篇 理学
- 24 篇 物理学
- 15 篇 数学
- 10 篇 生物学
- 2 篇 统计学（可授理学、...
13 篇 管理学
- 11 篇 管理科学与工程(可...
- 5 篇 工商管理
6 篇 医学
- 6 篇 临床医学
2 篇 经济学
- 2 篇 应用经济学
1 篇 法学
1 篇 教育学
1 篇 农学

主题

24 篇 object detection
18 篇 accuracy
14 篇 deep learning
14 篇 yolo
11 篇 feature extracti...
8 篇 image segmentati...
8 篇 image processing
7 篇 visualization
6 篇 convolutional ne...
5 篇 target tracking
5 篇 media
5 篇 real-time system...
5 篇 computer vision
4 篇 neural networks
4 篇 convolution
4 篇 computational mo...
4 篇 target recogniti...
4 篇 training
3 篇 performance mode...
3 篇 roads

机构

2 篇 university of sc...
2 篇 business school ...
2 篇 school of mechat...
2 篇 hebei univ sci &...
2 篇 northwest univ s...
2 篇 school of electr...
2 篇 college of engin...
2 篇 ahsanullah unive...
2 篇 college of infor...
2 篇 dept. of compute...
2 篇 school of electr...
2 篇 faculty of curre...
2 篇 xinjiang univers...
2 篇 school of inform...
2 篇 school of electr...
2 篇 shijiazhuang uni...
2 篇 school of inform...
2 篇 college of futur...
2 篇 school of inform...
1 篇 xiangzhong norma...

作者

2 篇 he lifeng
2 篇 zhang mengying
2 篇 zhang xiaoran
2 篇 wanzhen zhou
2 篇 liu zhiguo
2 篇 song yufei
2 篇 zhou wanzhen
2 篇 zhiguo liu
2 篇 chao yuyan
2 篇 yufei song
2 篇 xiaoran zhang
1 篇 zhao chunhui
1 篇 zhao mingfu
1 篇 shi hongbo
1 篇 gurumoorthy sasi...
1 篇 ganesh kumar che...
1 篇 cheng huiyan
1 篇 gao fan
1 篇 lian-he shao
1 篇 xiangda wang

语言

118 篇 英文
10 篇 其他
1 篇 中文

检索条件"任意字段=2024 3rd International Conference on Image Processing, Object Detection, and Tracking, IPODT 2024"

共 128 条记录，以下是41-50 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：

Enhancing ORB-SLAM3 Pose Estimation in Dynamic Scenes with YOLOv5 object detection 3

Enhancing ORB-SLAM3 Pose Estimation in Dynamic Scenes with Y...

引用

3rd international conference on image processing and Media Computing (ICIPMC)

作者： Zhou, Wanzhen Zhang, Xiaoran Meng, Xi Wang, Shangyue Liu, Zhiguo Song, Yufei Hebei Univ Sci & Technol Sch Informat Sci & Engn Shijiazhuang Peoples R China Shijiazhuang Univ Coll Future Informat Technol Shijiazhuang Peoples R China

ISBN: (纸本)9798350386660;9798350386677

This research paper introduces an improved ORB-SLAM3, which is integrated with YOLO to achieve real-time dynamic feature point elimination and pose optimization. ORB-SLAM3 uses the ORB feature extractor to extract corner points, uses descriptors to match supporting points, and finally estimates the camera pose. However, in some dynamic scenes, the motion of dynamic objects will affect the pose estimation accuracy of SLAM, resulting in incorrect camera pose estimation. In order to solve this problem, it is proposed to add YOLO into ORB-SLAM3, and use YOLO's target detection to detect prior dynamic objects in image frames and eliminate feature points in dynamic objects, so as to reduce the impact of dynamic objects on camera pose estimation. The idea was evaluated on a publicly available dataset, which confirmed that pose estimation in dynamic scenarios was more accurate than the benchmark ORB-SLAM3.

关键词： ORB-SLAM3 ORB YOLO Dynamic Target detection

来源：评论

学校读者我要写书评

暂无评论

VGG-SSD Model for Weapon detection using image processing 3

VGG-SSD Model for Weapon Detection using Image Processing

引用

3rd international conference on Applied Artificial Intelligence and Computing, ICAAIC 2024

作者： Ravi Kiran Varma, P. Kishore Raju, K. Krishna Chaitanya, R. Sirisha, G.N.V.G. Varma, Dendukuri Narendra Sagi Rama Krishnam Raju Engineering College Dept. of Cse Bhimavaram India Sagi Rama Krishnam Raju Engineering College Dept. of It Bhimavaram India Sagi Rama Krishnam Raju Engineering College Dept. of Ece Bhimavaram India

ISBN: (纸本)9798350375190

Video surveillance demands application of technology like deep learning, image processing for automated detection of deadly weapons in the hands of anti-social elements. This work depicts the application of very deep convolutional neural network (CNN), Visual Geometry Group (VGG)-16, and popular object detection technique, Single Shot MultiBox Detector (SSD) for detecting a weapon in automated surveillance application. The model is trained and tested on benchmark data on normal, gun, and knife objects. Performance parameters are, Mean Average Precision (MAP), Recall, Intersection over Union (IoU), and classification loss. A MAP of 87%, a recall of 86.6%, and calculation loss of 0.07 and total loss of 0.35 are achieved and the model proves to be efficient. © 2024 IEEE.

关键词： object detection

来源：评论

学校读者我要写书评

暂无评论

Remote Sensing object detection Based on Improved detection Transformer 3

Remote Sensing Object Detection Based on Improved Detection ...

引用

3rd international conference on Cloud Computing, Big Data Application and Software Engineering, CBASE 2024

作者： Hu, Yuanzhong Hu, Po Wang, Haihui Wang, Yuzhuo School of Computer Science and Engineering School of Artificial Intelligence Wuhan Institute of Technology Wuhan China

ISBN: (纸本)9798331506582

Nowadays, the accuracy of remote sensing image target recognition has greatly improved. It enables humans to efficiently monitor crop growth, track climate changes and natural disasters, and even provide critical strategic intelligence for national defense. However, due to the challenges posed by the large number of objects and the immense size of remote sensing images, there is still considerable room for improvement in recognition accuracy and efficiency. detection Transformer (DETR) framework utilizes the Transformer architecture, change the object detection task to a set prediction problem, thus simplifying the traditional post-processing workflow. Through its attention mechanisms, DETR effectively captures object features in intricate scenes by modeling global contextual information. Nonetheless, there is still potential for improvement in extracting fine-grained details. In this study, three modifications are proposed to the DETR framework to boost remote sensing object detection accuracy. First, a multi-scale feature extraction approach is employed to capture deeper and more detailed image features. Second, a bidirectional learning path is introduced to enhance the contextual relationships between image features. Experimental results demonstrate that our proposed method has achieved strong competitiveness compared to other approaches © 2024 IEEE.

关键词： Optical remote sensing

来源：评论

学校读者我要写书评

暂无评论

Investigating U-Net's Reliability in Saliency detection with Salt and Pepper Noise 3

Investigating U-Net's Reliability in Saliency Detection with...

引用

3rd international conference on Power, Control and Computing Technologies, ICPC2T 2024

作者： Kumain, Sandeep Chand Singh, Maheep Awasthi, Lalit K. Srinagar India

ISBN: (纸本)9798350349207

In this digital age, images and videos are the main source of conveying information. People can concentrate very well on the most crucial areas of an image or video. Emulating the human visual system to determine the most noticeable object is a popular area of study in the field of computer vision and image processing. Salient objects are those that stand out the most in the image. Numerous applications, including automated cropping, video summarizing, compression, and others, are greatly impacted by salient object detection approaches. Recent rapid advancements in artificial intelligence have led to the proposal of multiple deep learning-based saliency detection models by researchers. Nevertheless, the majority of approaches concentrate on saliency detection in noise-free environments. Since noise can affect images or videos, it can be difficult to handle the noise and identify the important object in noisy conditions. The detection of the presence of noise in the image or frame is also a challenging task. Here in this work, the author(s) tried to analyze the effect of salt and pepper noise in the saliency detection process. In the proposed work first, the author(s) developed a noise classifier that identifies the presence of salt and pepper noise. Further, the existing noise reduction algorithms are used for denoising purposes, and finally for saliency detection lightweight U-Net model is utilized to identify the most prominent object. In a clean, noisy, and denoised environment, the lightweight U-Net model's performance is evaluated in this work. © 2024 IEEE.

关键词： Salt and pepper noise

来源：评论

学校读者我要写书评

暂无评论

Apple image recognition model based on optimized sYOLOv5 network with small object detection 24

Apple image recognition model based on optimized sYOLOv5 net...

引用

3rd international conference on Cryptography, Network Security and Communication Technology (CNSCT)

作者： Wei, Cunli Tan, Hao Zhang, Jie Feng, Mengdan Liu, Zirou Wang, Jianwei Zhang, Pan Tianjin Univ Technol Sch Comp Sci & Engn Tianjin 300382 Peoples R China Guangdong Univ Technol Sch Informat Engn Guangzhou 510006 Peoples R China Anhui Jianzhu Univ Sch Management & Econ Hefei 230000 Peoples R China Southwest Jiaotong Univ Sch Comp Sci & Artificial Intelligence Chengdu 611756 Peoples R China Sichuan Univ Jinjiang Coll Meishan 620860 Peoples R China

ISBN: (纸本)9798400716959

In this research, we employ a deep learning approach to extract features from an apple image dataset, enabling precise counting and localization of apples. We address challenges like low resolution and small targets by optimizing the network and implementing small target optimization. The focus in another task is on building a mathematical model using sYOLOv5 to assess apple ripeness based on color and texture features. Additionally, we compute the two-dimensional area and estimate mass by combining instance segmentation and traditional image processing techniques. Lastly, we train a fruit recognition model using sYOLOv5 on a harvested fruit dataset.

关键词： YOLOv5 network architecture small target detection optimization CBAM module instance segmentation Gurukin's theorem

来源：评论

学校读者我要写书评

暂无评论

MW-YOLO: Improved YOLOv8n for Lightweight Dense Vehicle object detection Algorithm 3

MW-YOLO: Improved YOLOv8n for Lightweight Dense Vehicle Obje...

引用

3rd international conference on image processing and Media Computing (ICIPMC)

作者： Zhou, Wanzhen Wang, Junjie Song, Yufei Zhang, Xiaoran Liu, Zhiguo Ma, Yupeng Hebei Univ Sci & Technol Sch Informat Sci & Engn Shijiazhuang Peoples R China Shijiazhuang Univ Coll Future Informat Technol Shijiazhuang Peoples R China Ningxia Med Univ Sch Med Informat & Engn Shijiazhuang Peoples R China

ISBN: (纸本)9798350386660;9798350386677

In recent years, the transportation field has focused on advanced object detection algorithms to develop autonomous vehicles. However, the prob- lem of misidentification and missed detection often occurs due to the high overlap of small size targets on the road. To solve this problem, this paper pro- poses a lightweight dense vehicle object detection al- gorithm MWYOLO(Multi-dimensional feature fusion and WIoU loss function YOLO) based on YOLOv8n model. Firstly, a small target detection layer is intro- duced in the neck network, along with the addition of a detection head, to enhance the network's feature extraction and detection capabilities for small targets. Subsequently, two multi-scale feature fusion modules, MSFB and HFF, are proposed to enhance the fusion effect of different scale features and reduce the input and output channels. Finally, the WIOU loss function is used to replace the original CIOU function used in YOLOv8n to address the issue of high overlap of road targets. Experimental results on the RAIR-V2X autonomous driving dataset demonstrate that the proposed MW-YOLO model outperforms the original model, with improvements of 5.9% in AP50 and 6% in AP, and the model memory is only 5.1MB, meeting the requirements for deploying models on edge devices.

关键词： Vehicle detection Multi scale Small object detection WIOU

来源：评论

学校读者我要写书评

暂无评论

CrackVision: A Fusion of Deep Learning and image processing for Comprehensive Wall Crack detection and Analysis 3

CrackVision: A Fusion of Deep Learning and Image Processing ...

引用

3rd international conference on Artificial Intelligence For Internet of Things, AIIoT 2024

作者： Yaythish Kannaa, K.G. Dennis Joshua, D. Chellamani, Ganesh Kumar Manoj Prabhakaran, K. Amrita School of Engineering Chennai Amrita Vishwa Vidyapeetham Department of Electronics and Communication Engineering India

ISBN: (纸本)9798350372120

Wall crack detection is an essential part of the maintenance of building and safety as it allows for identifying and assessing defects on the wall surface. This information is necessary for determining the extent of the crack and the correct repair or reinforcement measures to be taken. Early methods, such as visual inspection, have been used, but recent advances in technology, such as infrared thermography and acoustic emission testing, have proven the detection of the crack. But in recent days, machine learning and computer vision techniques have become potent tools for automating and enhancing wall crack detection *** paper presents wall crack detection, combining image processing and deep learning. The edge detection algorithms like canny edge detector and You Only Look Once (YOLO) object detection models are implemented on the high-performance Nvidia Jetson Nano platform. This combination achieved an impressive 97.3% accuracy, demonstrating the effectiveness of the implemented methodology. Not only does the YOLO model increase the efficiency of wall crack detection, but it also improves the overall reliability of inspection procedures. This research is a step forward in utilizing cutting-edge technologies to solve critical building maintenance and safety aspects of the building. © 2024 IEEE.

关键词： object detection

来源：评论

学校读者我要写书评

暂无评论

Pedestrian detection and tracking for Driver Assistance Systems 3

Pedestrian Detection and Tracking for Driver Assistance Syst...

引用

3rd international conference for Advancement in Technology, ICONAT 2024

作者： Muddebihal, Amaresh Chandru, P. Nisanth, V. Babu, Tina Alliance University Department of Information Technology ACED Bengaluru India Alliance University Bengaluru Department of Computer Science and Engineering ACED India Alliance University Dept of Electronics and Communication ACED Bengaluru India

ISBN: (纸本)9798350354171

Pedestrian detection and tracking, particularly in low-light conditions, is critical for ensuring road safety, especially for vulnerable populations like senior citizens. Traditional methods often struggle with multiple moving objects and poor visibility, leading to increased noise and false alarms. To address these challenges, this project proposes a novel approach combining a wavelet-based contrast change detector and locally adaptive thresholding for real-time detection and tracking of multiple moving objects during night-time driving scenarios. The initial phase utilizes a contrast change detector to identify potential moving objects by detecting local changes in contrast over time. False alarms are suppressed using motion prediction and spatial nearest neighbor data association. Furthermore, a sophisticated change detection algorithm is employed to segment video sequences effectively, minimizing noise and enhancing the quality of outputs. Incorporating the latest advancements, such as the YOLO V8 module, this project focuses on leveraging deep learning techniques for pedestrian detection. The YOLO V8 module, a state-of-the-art variant of the YOLO series, is utilized to enhance accuracy and runtime efficiency. By harnessing a Large-Field Of-View (LFOV) deep network approach, the project achieves high detection accuracy while processing larger image areas at faster speeds compared to traditional deep networks. © 2024 IEEE.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

Proceedings of 2024 3rd international conference on Frontiers of Artificial Intelligence and Machine Learning, FAIML 2024

Proceedings of 2024 3rd International Conference on Frontier...

引用

2024 3rd international conference on Frontiers of Artificial Intelligence and Machine Learning, FAIML 2024

ISBN: (纸本)9798400709777

The proceedings contain 71 papers. The topics discussed include: an innovative time domain graph convolutional network enables effective tracking of multiple objects;a spatiotemporal mask autoencoder for one-shot video object segmentation;real-time vehicle pedestrian detection and tracking algorithm based on computer vision;real-time license plate detection and recognition in unconstrained scenarios;research on the application of image element extraction technology based on improved faster R-CNN in the communication of Hubei traditional culture;direct position determination of quasi-stationary sources based on virtual array synthesis of distributed nested arrays;analysis of sea clutter characteristics of digital array multi-channel ubiquitous radar;characterization and extraction of sea and air maneuvering targets using passive radar;advancing multi-modal beam prediction with multipath-like data augmentation and efficient fusion mechanism;and an overview study of automated inland waterway topographic contour mapping.

关键词：

来源：评论

学校读者我要写书评

暂无评论

2024 3rd international conference for Advancement in Technology, ICONAT 2024

2024 3rd International Conference for Advancement in Technol...

引用

3rd international conference for Advancement in Technology, ICONAT 2024

ISBN: (纸本)9798350354171

The proceedings contain 326 papers. The topics discussed include: design of low current driver for digital attenuator;a comprehensive metric for evaluating object-oriented software complexity;examining the role of error control in ATM networks;an intelligent method for performance of air conditioning system and vehicle fuel economy trade-offs for a hybrid electric vehicle using SA-CNN-LSTM mode;AI-enhanced cloud security framework for IoT networks using a predictive analytics approach;design and analysis of 1710-1880 MHz power amplifier for n3-5G new radio frequency band;duplicate detection in Quora question pairs using machine learning;and advanced machine learning frameworks for multimodal image and speech signal processing.

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13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：