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111-120 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：

VGG-SSD Model for Weapon detection using image processing

VGG-SSD Model for Weapon Detection using Image Processing

引用

Applied Artificial Intelligence and Computing (ICAAIC), international conference on

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

ISBN: (数字)9798350375190

ISBN: (纸本)9798350375206

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.

关键词： Deep learning YOLO Visualization Accuracy Weapons image processing Video surveillance

来源：评论

学校读者我要写书评

暂无评论

Remote Sensing object detection Method Based on Three-Dimensional Weight-Guided Selection Kernel

Remote Sensing Object Detection Method Based on Three-Dimens...

引用

image processing and Media Computing (ICIPMC), international conference on

作者： Min Gong Kun Yan Shenglin Peng Shuyi Qu School of Information Science and Technology Northwest University Xi’an China China Academy of Space Technology(Xi’an) Xi’an China Shaanxi Key Laboratory of Higher Education Institution of Generative Artificial Intelligence and Mixed Reality Xi’an China

ISBN: (数字)9798350386660

ISBN: (纸本)9798350386677

In recent years, research on remote sensing object detection has primarily focused on oriented box representation and optimization, while overlooking the importance of studying feature extraction networks, leading to inaccurate identification of some targets. The conventional feature extraction networks employ fixed-size convolutional kernels, which fail to capture different levels of visual features for targets of varying sizes. In this paper, we propose a mechanism called the 3D-Weight Guide Selective Kernel (3D-WGSK) to jointly utilize spatial and channel information of input features to derive three-dimensional weights. These weights are then employed for convolutional kernel selection, enabling adaptive receptive field acquisition for capturing features of targets with different sizes. We devise a network architecture named the 3D-WGSK Net for feature extraction in remote sensing object detection. It possesses the capability of multi-scale information fusion and adaptive kernel adjustment, effectively extracting crucial features of targets with varying sizes. Experimental results on the publicly available DOTA-v1.5 dataset demonstrate the superior detection performance of our method.

关键词： Location awareness Visualization Target recognition object detection Feature extraction Reliability engineering Kernel

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

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

引用

Artificial Intelligence For Internet of Things (AIIoT), international conference on

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

ISBN: (数字)9798350372120

ISBN: (纸本)9798350372137

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.

关键词： YOLO Deep learning Accuracy Computational modeling image processing image edge detection Buildings

来源：评论

学校读者我要写书评

暂无评论

Investigating Salient object detection Methods Tailored for Edge Computing Infrastructure 3rd

Investigating Salient Object Detection Methods Tailored for...

引用

3rd international conference on Computing, Communication and Learning, CoCoLe 2024

作者： Sebastian, Elsa Martin, John Paul Department of Computer Science and Engineering Indian Institute of Information Technology Kottayam Kottayam686635 India

ISBN: (纸本)9783031790409

Salient object detection aims in identifying the most significant parts of a scene as viewed by the human eye and plays a vital role in a variety of applications, including object detection, video compression, and augmented reality. Saliency detection has emerged as a fundamental preprocessing step in many computer vision and image processing tasks. Implementing saliency detection in edge computing platforms is challenging, however it promises enhanced real-time responsiveness, reduced bandwidth usage, and improved privacy. This paper examines the most advanced techniques for adapting saliency detection techniques to edge computing and discusses encountered challenges. The paper also gives insights into the evaluation metrics that can be utilized for performance assessment, investigates primary application domain and proposes potential directions for future research. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

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

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

引用

image processing and Media Computing (ICIPMC), international conference on

作者： Wanzhen Zhou Xiaoran Zhang Xi Meng Shangyue Wang Zhiguo Liu Yufei Song School of Information Science and Engineering Hebei University of Science and Technology Shijiazhuang China College of Future Information Technology Shijiazhuang University Shijiazhuang China

ISBN: (数字)9798350386660

ISBN: (纸本)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： YOLO Accuracy Simultaneous localization and mapping Pose estimation Dynamics Media Feature extraction

来源：评论

学校读者我要写书评

暂无评论

The Application of Computer Vision Target Recognition Technology in Autonomous Driving

The Application of Computer Vision Target Recognition Techno...

引用

Artificial Intelligence and Autonomous Robot Systems (AIARS), international conference on

作者： Yaning Wang Xin Bi TongJi University Shanghai China

ISBN: (数字)9798350376173

ISBN: (纸本)9798350376180

In recent years, the rapid growth of Internet of Things (IoT) technology and computer vision (CV) technology has provided strong support for the application of deep learning (DL) in various fields. Among them, DL based object detection algorithms have attracted much attention due to their excellent performance. Vehicle target detection, as an important branch of object detection, is crucial for the construction of intelligent driving and intelligent transportation systems. In autonomous driving technology, using machines to detect and recognize traffic signs, vehicles, and pedestrians is of great significance for improving driving safety, reducing labor costs, and demonstrating broad application prospects. In this paper, a target recognition algorithm based on CV and DL is proposed to improve the target detection capability of auto drive system. This algorithm combines the image processing technology of CV and the feature extraction and classification ability of DL to achieve fast and accurate recognition of targets such as vehicles and pedestrians in road environments. Experimental results show that through training and optimizing the DL model, the algorithm can perform well in complex and changeable traffic scenes and provide reliable target detection support for the auto drive system.

关键词： Training Pedestrians Accuracy Target recognition Roads object detection Feature extraction Classification algorithms Safety Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

PhD Forum Abstract: Sensor Fusion for Vehicle-side and Roadside 3D object detection and tracking

PhD Forum Abstract: Sensor Fusion for Vehicle-side and Roads...

引用

international Symposium on Information processing in Sensor Networks (IPSN)

作者： Yao Li University of Science and Technology of China Hefei China

ISBN: (数字)9798350362015

ISBN: (纸本)9798350362022

We focus on the sensor fusion for vehicle-side and roadside 3D object detection and tracking. Although quite a few sensor fusion algorithms have been proposed, some of which are top-ranked on various leaderboards, a systematic study on how to integrate three crucial sensors (LiDAR, camera and millimeter-wave Radar sensors) to develop effective multi-modal 3D object detection and tracking for vehicle-side perception is still missing. Therefore, we first study the three sensors’ strengths and weaknesses carefully, then compare several different fusion strategies to maximize their utility. Finally, based on the lessons learnt, we propose a simple yet effective multi-modal 3D object detection and tracking framework (namely EZFusion). Without fancy network modules, our proposed EZFusion makes remarkable improvements over the LiDAR-only baseline, and achieves comparable performance. For intelligent transportation, far-range perception with roadside sensors is vital. The main challenge of far-range perception is performing accurate object detection and tracking under far distances (e.g., > 150m) at a low cost. To cope with such challenges, deploying both millimeter wave Radars and high-definition cameras, and fusing their data has become a common practice. Towards this goal, the first question is to conduct the association on the 2D image plane or the BEV plane. We argue that the former is more suitable because the magnitude of location errors in the perspective projection points is smaller at far distances on the 2D plane, leading to more accurate association. Thus, we first project the Radar points to the 2D plane and then associate them with the camera-based 2D object locations. Subsequently, we map the camera-based object locations to the BEV plane through inverse projection mapping (IPM) with the corresponding depth information from the Radar data. Finally, we engage a BEV tracking module to generate target trajectories. Our system is capable of achieving an average l

关键词： Three-dimensional displays Accuracy Target tracking Transportation object detection Sensor fusion Millimeter wave radar

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

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

引用

image processing and Media Computing (ICIPMC), international conference on

作者： Wanzhen Zhou Junjie Wang Yufei Song Xiaoran Zhang Zhiguo Liu Yupeng Ma School of Information Science and Engineering Hebei University of Science and Technology Shijiazhuang China College of Future Information Technology Shijiazhuang University Shijiazhuang China School of Medical Informatics and Engineering Ningxia Medical University

ISBN: (数字)9798350386660

ISBN: (纸本)9798350386677

In recent years, the transportation field has focused on advanced object detection algorithms to develop autonomous vehicles. However, the problem 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 algorithm MW-YOLO(Multi-dimensional feature fusion and WIoU loss function YOLO) based on YOLOv8n model. Firstly, a small target detection layer is introduced 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： YOLO Performance evaluation Accuracy Roads Transportation Random access memory Feature extraction

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

Pedestrian Detection and Tracking for Driver Assistance Syst...

引用

Advancement in Technology (ICONAT), international conference for

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

ISBN: (数字)9798350354171

ISBN: (纸本)9798350354188

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.

关键词： YOLO Pedestrians Accuracy Runtime Motion segmentation Noise Video sequences Detectors Road safety Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Lane detection via Sparse Instance Activation

Lane Detection via Sparse Instance Activation

引用

image processing and Media Computing (ICIPMC), international conference on

作者： Jun Yang Yanhong Gu Yuxia Hu Yuanyuan Li Fudong Nian School of Advanced Manufacturing Engineering Hefei University Hefei China Anhui International Joint Research Center for Ancient Architecture Intellisencing and Multi-Dimensional Modeling Anhui Jianzhu University Hefei China Information Materials and Intelligent Sensing Laboratory of Anhui Province AnHui University Hefei China Anhui Provincial Engineering Technology Research Center of Intelligent Vehicle Control and Integrated Design Technology Hefei China

ISBN: (数字)9798350386660

ISBN: (纸本)9798350386677

The most advanced lane detection methods typically rely on specific knowledge about lanes (such as straight lines and parametric curves) to detect lane lines. Although specific knowledge can simplify the modeling process, it does not work well in handling lane lines with complex topological structures (such as dense, forked, curved, etc.). Recently, methods based on dynamic convolution have shown promising performance by using features of some key positions of the lane lines (such as starting points) as convolutional kernels and convolving them with the entire feature map to detect lane lines. Although such methods reduce the reliance on specific knowledge, the kernels derived from key positions cannot capture the global structure of the lane lines due to their long and thin structure, leading to inaccurate detection of lane lines with complex topologies. In addition, the kernels derived from key positions are sensitive to occlusions and lane intersections. To overcome these limitations, in this paper, we propose to use multiple sets of sparse instance activation maps as the object representation of lane lines, highlighting the information regions of each foreground object. Then, based on the highlighted regions, instance-level features are aggregated. Furthermore, based on the Hungarian algorithm, the instance activation maps can predict lanes in one-to-one manner, avoiding non-maximum suppression (NMS) in post-processing. We evaluated our method on two lane detection benchmarks, and the results proved its advanced performance. Specifically, our method achieved F1 scores of 78.36 and 96.68 on CULane and Tuisimple, respectively.

关键词： Accuracy Lane detection Convolution Benchmark testing Media Feature extraction Prediction algorithms

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 << < 4 5 6 7 8 9 10 11 12 13 > >>

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：