检索结果-内蒙古大学图书馆

Designing deep Reinforcement learning enhanced edge-terminal collaborative AIoT for Intelligent Visitor Management System

引用

AD HOC NETWORKS 2025年 169卷

作者： Liao, Yong Zhu, Zhiyuan Tang, Tong Wu, Dapeng Wang, Ruyan Chongqing Univ Posts & Telecommun Sch Commun & Informat Engn Chongqing 400065 Peoples R China Key Lab Chongqing Educ Commiss China Adv Network & Intelligent Connect Technol Chongqing 400065 Peoples R China Chongqing Key Lab Ubiquitous Sensing & Networking Chongqing 400065 Peoples R China

Intelligent Visitor Management System (IVMS) is crucial for enhancing security and operational efficiency in smart factories and intelligent office buildings. Leveraging AIoT-driven image analysis will facilitate realtime visitor authentication and access control. However, the growing volume of interactions and the limited processing power of local terminals complicate the delivery of timely and accurate image analysis. To address these challenges, we propose an edge-terminal collaborative AIoT framework for real-time visitor management. The framework solves the limitations of traditional approaches, where local terminals are unable to handle the computational load and edge solutions experience high latency due to transmission delays. Specifically, it integrates three key components to improve system performance: a local analysis module for initial processing, an image communication module for efficient data transmission, and an edge analysis module for advanced processing. Moreover, the framework jointly optimizes image task offloading, wireless channel allocation, and image compression, all formulated as an optimization problem to ensure fast and accurate analysis. Additionally, a novel multi-level deep Reinforcement learning (DRL) method is further designed to dynamically refine the selection of compression and offloading strategies. By learning in real-time, the DRL model adapts to network variations, addressing the scalability and adaptability limitations of existing methods. Simulation results show that our proposed edge-terminal collaborative AIoT framework significantly outperforms both edge-only and terminal-only methods in terms of latency and accuracy.

关键词： Intelligent Visitor Management System (IVMS) Terminal-edge collaborative AIoT deep Reinforcement learning (DRL)

来源：评论

学校读者我要写书评

暂无评论

Research on online measurement method of fineness modulus of manufactured sand based on deep learning

引用

CONSTRUCTION AND BUILDING MATERIALS 2024年 414卷

作者： Huang, Feizhi Yang, Jianhong Fang, Huaiying Pan, Weijun Wei, Yixing Huaqiao Univ Coll Mech Engn & Automat Xiamen 361021 Fujian Peoples R China

The fineness modulus(FM) represents the level of particle size of manufactured sand. real-time feedback of FM of manufactured sand is important for industrial sand production, but extracting the particle profile from densely stacked images is a great challenge. In this study, a deep learning and regression analysis -based online measurement method for FM of manufactured sand is proposed. Firstly, the real fineness modulus of the sand produced by the sand -making machine in real time was obtained by the vibration -screening method(VSM). Then, the particle size fraction of larger particles (0.6-4.75 mm) was obtained based on machine vision combined with a convolutional neural network and image processing. Secondly, a multiple linear regression model was developed for the percentage of particle size and FM. Finally, the percentage of particle size was substituted into the regression model as the independent variable to achieve a fast prediction of the unknown FM. The experimental results show that the maximum repeatability errors for FM of different manufactured sands are 0.09 and 0.13 respectively, and the maximum absolute errors of the FM prediction results are 0.18 and 0.17 respectively. The calculation efficiency and error level of this research method can meet the online testing at sand making sites.

关键词： Manufactured sand Fineness modulus deep learning Online measurement image processing

来源：评论

学校读者我要写书评

暂无评论

real-time Classification of Chicken Parts in the Packaging Process Using Object Detection Models Based on deep learning

引用

PROCESSES 2025年第4期13卷 1005-1005页

作者： Sahin, Dilruba Torkul, Orhan Sisci, Merve Diren, Deniz Demircioglu Yilmaz, Recep Kibar, Alpaslan Sakarya Univ Ind Engn Dept TR-54050 Sakarya Turkiye Kutahya Dumlupinar Univ Ind Engn Dept TR-43300 Kutahya Turkiye Sakarya Univ Dept Informat Syst & Technol TR-54050 Sakarya Turkiye Sakarya Univ Business Sch TR-54050 Sakarya Turkiye Sakarya Univ Dept Management Informat Syst TR-54050 Sakarya Turkiye

Chicken meat plays an important role in the healthy diets of many people and has a large global trade volume. In the chicken meat sector, in some production processes, traditional methods are used. Traditional chicken part sorting methods are often manual and time-consuming, especially during the packaging process. This study aimed to identify and classify the chicken parts for their input during the packaging process with the highest possible accuracy and speed. For this purpose, deep-learning-based object detection models were used. An image dataset was developed for the classification models by collecting the image data of different chicken parts, such as legs, breasts, shanks, wings, and drumsticks. The models were trained by the You Only Look Once version 8 (YOLOv8) algorithm variants and the real-time Detection Transformer (RT-DETR) algorithm variants. Then, they were evaluated and compared based on precision, recall, F1-Score, mean average precision (mAP), and Mean Inference time per frame (MITF) metrics. Based on the obtained results, the YOLOv8s model outperformed the other models developed with other YOLOv8 versions and the RT-DETR algorithm versions by obtaining values of 0.9969, 0.9950, and 0.9807 for the F1-score, mAP@0.5, and mAP@0.5:0.95, respectively. It has been proven suitable for real-time applications with an MITF value of 10.3 ms/image.

关键词： chicken parts deep learning image processing object detection reducing waste and costs RT-DETR YOLOv8

来源：评论

学校读者我要写书评

暂无评论

DMC-Net: a lightweight network for real-time surface defect segmentation

引用

JOURNAL OF real-time image processing 2025年第2期22卷 1-11页

作者： Zuo, Haiqiang Zheng, Yubo Huang, Qizhou Du, Zehao Wang, Hao China Univ Petr East China Coll New Energy Qingdao 266580 Shandong Peoples R China

In industrial applications, surface defect segmentation is a critical task. However, facing challenges such as diverse defect scales, low contrast between defects and background, high interclass similarity and real-time detection in defect inspection, we propose an efficient lightweight network, named DMC-Net, for real-time surface defect segmentation. The structural optimization of DMC-Net includes the following components: (1) depthwise separable convolution attention module, a lightweight and efficient feature extraction module for extracting multi-scale defect features. (2) Multi-scale feature enhancement module, providing long-range information capture and local information focusing to enhance defect localization capability. (3) Channel shuffle group convolution, enhancing feature interaction and information propagation while reducing the parameter quantity. Based on the experimental results, DMC-Net achieved an mIoU of 73.74% on the NEU-SEG dataset, while achieving an FPS of 211.7. This indicates that we have successfully reduced the complexity and computational cost of the model while improving performance, providing a feasible solution for industrial applications. The relevant code can be obtained at https://***/Michaelzyb/***.

关键词： deep learning Surface defect detection Segmentation network Lightweight

来源：评论

学校读者我要写书评

暂无评论

Adversarial Attacks and Countermeasures on image Classification-based deep learning Models in Autonomous Driving Systems: A Systematic Review

引用

ACM COMPUTING SURVEYS 2025年第1期57卷 1-52页

作者： Badjie, Bakary Cecilio, Jose Casimiro, Antonio Univ Lisbon Comp Sci & Engn Res Ctr LASIGE Lisbon Portugal

The rapid development of artificial intelligence (AI) and breakthroughs in Internet of Things (IoT) technologies have driven the innovation of advanced autonomous driving systems (ADSs). image classification deep learning (DL) algorithms immensely contribute to the decision-making process in ADSs, showcasing their capabilities in handling complex real-world driving scenarios, surpassing human driving intelligence. However, these algorithms are vulnerable to adversarial attacks, which aim to fool them in real-time decision- making and compromise the reliability of the autonomous driving functions. This systematic review offers a comprehensive overview of the most recent literature on adversarial attacks and countermeasures on image classification DL models in ADSs. The review highlights the current challenges in applying successful countermeasures to mitigating these vulnerabilities. We also introduce taxonomies for categorizing adversarial attacks and countermeasures and provide recommendations and guidelines to help researchers design and evaluate countermeasures. We suggest interesting future research directions to improve the robustness of image classification DL models against adversarial attacks in autonomous driving scenarios.

关键词： Adversarial attacks defense and countermeasures autonomous driving systems deep learning image classification

来源：评论

学校读者我要写书评

暂无评论

A deep learning-based template matching through other field of view infrared image pair for real-time mixed reality

A deep learning-based template matching through other field ...

引用

Conference on real-time image processing and deep learning

作者： Lee, Seungeon Kim, Donyung Kim, Sungho Yeungnam Univ Dept Elect Engn Gyeongbuk 38541 South Korea

ISBN: (纸本)9781510673878;9781510673861

In this paper, we proposed a template matching technique using deep learning to match pairs of wide fields of view and narrow field of view infrared images. The deep learning network has a similar structure with the Atrous Spatial Pyramid Pooling (ASPP) module and both wide and narrow fields of view images are input to the same network, so the network weights are shared. Our experiments used the Galaxy S20 (Qualcomm Snapdragon 865) platform and show that the trained network has higher matching accuracy than other template matching techniques and is fast enough to be used in real time.

关键词： template matching infrared image deep-learning real-time CNN Snapdragon 865

来源：评论

学校读者我要写书评

暂无评论

real-time Motion Analysis With 4D deep learning for Ultrasound-Guided Radiotherapy

引用

IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING 2023年第9期70卷 2690-2699页

作者： Bengs, Marcel Sprenger, Johanna Gerlach, Stefan Neidhardt, Maximilian Schlaefer, Alexander Hamburg Univ Technol Inst Med Technol & Intelligent Syst D-21073 Hamburg Germany

Motion compensation in radiation therapy is a challenging scenario that requires estimating and forecasting motion of tissue structures to deliver the target dose. Ultrasound offers direct imaging of tissue in real-time and is considered for image guidance in radiation therapy. Recently, fast volumetric ultrasound has gained traction, but motion analysis with such high-dimensional data remains difficult. While deep learning could bring many advantages, such as fast data processing and high performance, it remains unclear how to process sequences of hundreds of image volumes efficiently and effectively. We present a 4D deep learning approach for real-time motion estimation and forecasting using long-term 4D ultrasound data. Using motion traces acquired during radiation therapy combined with various tissue types, our results demonstrate that long-term motion estimation can be performed markerless with a tracking error of 0.35 +/- 0.2 mm and with an inference time of less than 5 ms. Also, we demonstrate forecasting directly from the image data up to 900 ms into the future. Overall, our findings highlight that 4D deep learning is a promising approach for motion analysis during radiotherapy.

关键词： 4D deep learning sequence processing ultrasound motion analysis radiation therapy

来源：评论

学校读者我要写书评

暂无评论

Online Recognition of Manually Spray-Printed Ladle Numbers in Complex Dynamic Environments

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2024年 73卷 1页

作者： Meng, Hongji Ma, Hancong Yang, Jian Hu, Zhenwei Fan, Jia He, Qing Northeastern Univ Coll Informat Sci & Engn Dept Intelligent Detect Shenyang 110819 Peoples R China HBIS Grp HanSteel Co Handan Peoples R China

During the converter process, it is crucial to automatically identify and record ladle numbers to track steel product quality and enhance automation levels. However, the steelmaking environment presents several challenges, including intricate ladle scheduling, varying lighting conditions, severe background interference, and significant disparities between manually spray-printed ladle number characteristics and publicly available datasets. The combination of these problems makes it challenging to perform accurate and real-time ladle number identification. In response, this article suggests an automatic ladle number recognition approach based on deep learning and image processing. First, a double-region object detection model based on YOLOv5 is employed to capture keyframe images of the ladle to be identified from the video stream. Then, a method that can enable the acquisition of an accurate region of ladle numbers in sophisticated industrial settings is proposed to address the distortion of numerical features caused by lighting variations and background interference in industrial environments. Last, leveraging the proprietary dataset found and a ladle number recognition model integrating CNN and multiframe image fusion is designed, developing multithreading design and image queue management to ensure real-time and accurate ladle number recognition. In this study, the video data of a steel plant is used for testing. Through testing 176 steelmaking production cycles, all ladle numbers are accurately identified prior to finishing charging molten iron, indicating the high accuracy and real-time capability of the recognition system.

关键词： image recognition Feature extraction YOLO real-time systems Streaming media Iron image segmentation Complex dynamic environments deep learning image processing ladle number recognition online recognition

来源：评论

学校读者我要写书评

暂无评论

Enhanced image processing for Automobile Accident Detection Using deep learning

Enhanced Image Processing for Automobile Accident Detection ...

引用

Smart Technologies and Systems for Next Generation Computing (ICSTSN), International Conference on

作者： S. Usharani J. Dhanushkumar P. Manju Bala A. Balachandar Department of Artificial Intelligence and Machine Learning IFET College of Engineering (An Autonomous Institution) Villupuram India Department of Computer Science and Engineering IFET College of Engineering (An Autonomous Institution) Villupuram India

ISBN: (数字)9798350391565

ISBN: (纸本)9798350391572

Road safety can be creatively increased by utilizing systems for reporting and detecting accidents use the YOLO algorithm. Yolo, which stands for "You Only Look Once," is a sophisticated object recognition system that can identify and pinpoint objects in live video streams. By identifying accidents and notifying emergency services, the system lowers the reaction times and increases the possibility of saving lives by utilizing the YOLO algorithm. The object detection and alarm systems are the two primary parts of the proposed system. The YOLO method is employed by the object recognition module to look for accidents in live video broadcasts. A module of accident photos was used to teach the system to accurately identify incidents. When an accident is discovered, an alert system is activated. The location of the accident and a brief account of what transpired are communicated to the emergency services by the alert system. This information is communicated to emergency services through a wireless communication network, which expedites response times and increases the likelihood of saving lives. Positive results were obtained by testing the system using the images and an accident module. It was shown that the warning system could react in a couple of seconds and that the YOLO algorithm could identify accidents having a precision of around 94. Highways, busy intersections, and other high-risk areas may have systems in place to increase traffic safety and lower the number of accidents. Developing crash detection and warning systems using deep learning using the YOLO technique is one way to potentially increase road safety. With the use of technology, problems may be precisely identified in real-time video feeds, alerting emergency services and potentially increasing survival rates and reaction times.

关键词： YOLO deep learning Accuracy Alarm systems Streaming media Emergency services Road safety

来源：评论

学校读者我要写书评

暂无评论

Dynamic Tactical image Recognition and Analysis in Football Matches Using Convolutional Neural Networks

引用

TRAITEMENT DU SIGNAL 2025年第1期42卷 583-592页

作者： Xie, Qi Baoji Univ Arts & Sci Sch Phys Educ Baoji 721000 Peoples R China

With the increasing complexity of modern football tactics, how to intelligently and accurately analyze tactical changes in real-time during matches has become an important research direction. Traditional manual tactical analysis methods are inefficient and susceptible to subjective bias. Therefore, using computer vision and deep learning technologies for tactical image recognition and analysis in football matches has gradually become a research hotspot. Convolutional Neural Networks (CNNs), as a powerful image processing tool, have been widely applied in video analysis and player detection. However, multi-target motion prediction and tracking management in dynamic football match scenes still face significant challenges. Existing research mainly focuses on static image analysis or simple player tracking, but the high-frequency image updates, player interactions, and occlusion issues in football matches complicate multi-target tracking. While some deep learning-based methods for multi-target detection and tracking have made progress, challenges remain, such as handling high-density player targets and improving motion trajectory prediction accuracy. To address these shortcomings, this study proposes two core techniques based on CNNs: first, multi-target motion prediction, which accurately forecasts players' future positions based on historical motion data;second, multi-target tracking management, which uses deep learning to track and manage each player's movement trajectory in real-time. Through these two techniques, this research aims to improve the realtime and accuracy of tactical analysis in football matches, providing coaches and analysts with more scientific and efficient tactical decision-making support.

关键词： CNN football matches dynamic tactical image multi-target motion prediction multi-target tracking management computer vision

来源：评论

学校读者我要写书评

暂无评论

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：

请选择收藏分类：

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

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：