检索结果-内蒙古大学图书馆

deep learning assisted characterization of bubble behavior in a gas-solid fluidized bed with binary particle mixtures

引用

POWDER TECHNOLOGY 2024年 448卷

作者： Yang, Peng Guo, Qiankun Chen, Hongsheng Chongqing Univ Coll Mat Sci & Engn Dept Met Engn Chongqing 400044 Peoples R China

Gas-solid fluidized beds are widely applied as chemical reactors, and the fluidization quality in the bed is closely related to bubble behavior. Digital image processing is a commonly used non-invasive method for bubble behavior analysis, but it is usually constrained by experimental conditions such as lighting, making identification of bubble and emulsion phases still challenging. Herein, deep learning is applied in this study to optimize traditional digital image processing techniques. By evaluating different deep learning models (FCN, deepLab V3, U-Net), rapid and accurate identification and segmentation of bubble images can be achieved, and the U-Net model performs best, achieving an identification accuracy of 99.05 %. Further application of U-Net to analyze bubble behavior demonstrates that deep learning methods enable efficient and accurate identification of bubbles and real-time analysis of bubble behavior, highlighting the significant potential application of deep learning in the field of complex hydrodynamics in fluidized beds.

关键词： Bubbling fluidized bed deep learning U-Net model Bubble recognition Bubble behavior

来源：评论

学校读者我要写书评

暂无评论

The analysis of Iris image acquisition and real-time detection system using convolutional neural network

引用

JOURNAL OF SUPERCOMPUTING 2024年第4期80卷 4500-4532页

作者： Liu, Yanru Xu, Jiali Yee, Austin Lin Inner Mongolia Univ Sci & Technol Baotou Med Coll Baotou 014040 Peoples R China Shanghai Univ Finance & Econ Sch Math Shanghai 200433 Peoples R China Med & Technol Co Ltd Chengdu 613000 Peoples R China

The purpose is to explore the effect of iris image acquisition and real-time detection systems based on Convolutional Neural Network (CNN) and improve the efficiency of iris real-time detection. Based on existing iris data acquisition and detection systems, this study uses the light field focusing algorithm to collect iris data in live, introduces CNN in deep learning (DL) algorithm, and designs an iris image acquisition and live detection system based on CNN. Afterward, Radial Basis Function (RBF)-Support Vector Machines (SVM) algorithm is used to classify iris feature information. Based on Field Programmable Gate Array (FPGA), a system for iris image acquisition, processing, and display is constructed. Finally, the performance of the constructed system and algorithm are analyzed through simulation experiments. The research results show that the proposed algorithm can automatically select the qualified iris images in live, significantly improve the recognition accuracy of the whole iris recognition system, and the average time of live quality evaluation for each frame image is less than 0.05 s. The focal point of the investigation involves the exploration of a CNN-based iris image acquisition and real-time detection system, with an emphasis on enhancing the efficiency of real-time iris detection. The innovation of this research lies in the integration of deep learning algorithms and light-field focusing techniques, applied to the reconstruction of a FPGA system. Further, the proposed algorithm is compared with Super-Resolution Using Very deep Convolutional Networks (VDSR), deeply Recursive Convolutional Network (DRCN), Residual Dense Network (RDN), and Bicubic. The comparison analysis suggests that the recognition accuracy of the proposed algorithm is the highest, close to 100%. Additionally, the proposed algorithm is compared with the image Quality Evaluation-based Algorithm (IQA) and the Feature Extraction-based Algorithm (FEA), showing that the proposed RBF-SVM

关键词： deep learning Convolutional neural network Iris image acquisition real-time detection Recurrent neural network Smart city

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

High Precision Robust real-time Lightweight Approach for Railway Pantograph Slider Wear Estimation

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2024年第5期25卷 3973-3985页

作者： Tang, Qingfeng Wei, Xiukun Wei, Dehua Shen, Xing Yin, Xinqiang Wang, Diqing Jia, Limin Zhong, Qitian Beijing Jiaotong Univ State Key Lab Adv Rail Autonomous Operat Beijing 100044 Peoples R China Beijing Jiaotong Univ Sch Traff & Transportat Beijing 100044 Peoples R China

The pantograph slider is a key component of the pantograph-catenary system. It is important to monitor the wear of sliders for rail transit safety. In this paper, an innovative real-time high-precision lightweight approach is proposed to estimate the wear of the slider. It allows complete monitoring of all sliders of the pantograph. In the first stage, a method based on image processing and object detection by deep learning is proposed to locate the region of the slider. It takes into account the large aspect ratio on the pantograph slider and the inclined angle. In the second stage, the neural network for wear estimation of pantograph slider (WEPSNet) is proposed. It realizes end-to-end contour extraction of the slider. The residual thickness of the slider is calculated by counting the number of pixels and the error is analyzed. Furthermore, the error arising from the perspective projection transformation in the monocular image is discussed. The experimental results demonstrate that, with the similar model size, the proposed WEPSNet outperforms the state-of-the-art method by 1.08% mIoU and 4.63% IMP. Moreover, the accuracy of residual thickness is tested on 120 pantograph slider images, achieving up to 95.91% within the allowable 1mm error, which is 6.68% higher than the state-of-the-art method.

关键词： image processing real-time systems Monitoring image edge detection deep learning Head Rails Pantograph slider thickness estimation WEPSNet contour extraction deep learning

来源：评论

学校读者我要写书评

暂无评论

Application of Convolutional Neural Networks for Parallel Multi-Scale Feature Extraction in Noise image Denoising

引用

IEEE ACCESS 2024年 12卷 98599-98610页

作者： Li, Yiming Xie, Tao Mei, Dongdong Ningxia Inst Sci & Technol Coll Comp Sci & Engn Shizuishan 753000 Peoples R China

Although deep learning techniques have made significant advances in the field of images, existing methods still face challenges in processing complex, noisy images. In view of the limitation that most denoising models only focus on extracting single scale features, a new denoising network structure is proposed in this paper. Firstly, the channel attention mechanism and convolutional neural network are combined to construct a real image denoising model, and then the parallel multi-scale convolutional neural network is constructed by combining the adaptive dense connected residual block and parallel multi-scale feature extraction module. The results showed that the designed model can reach the stable state only after 121 and 86 iterations on the training set and the test set, and the denoising accuracy of the model is as high as 0.96. In addition, the research model has high computational efficiency and short denoising time when processing noisy images, and the processing time of an image is as low as 0.09s. Therefore, the proposed denoising structure has good denoising performance under different noise levels and types, and this study also provides a new idea for the application of deep learning in image denoising and other image processing tasks.

关键词： Noise measurement Noise reduction image denoising Mathematical models Convolutional neural networks Multi-scale CNN attention mechanism feature extraction noise image residual residual

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

Integrating YOLOv8 and CSPBottleneck based CNN for enhanced license plate character recognition

引用

JOURNAL OF real-time image processing 2024年第5期21卷 168页

作者： Khokhar, Sahil Kedia, deepak GJUS&T Dept ECE Hisar India

The paper introduces an integrated methodology for license plate character recognition, combining YOLOv8 for segmentation and a CSPBottleneck-based CNN classifier for character recognition. The proposed approach incorporates pre-processing techniques to enhance the recognition of partial plates and augmentation methods to address challenges arising from colour diversity. Performance analysis demonstrates YOLOv8's high segmentation accuracy and fast processing time, complemented by precise character recognition and efficient processing by the CNN classifier. The integrated system achieves an overall accuracy of 99.02% with a total processing time of 9.9 ms, offering a robust solution for automated license plate recognition (ALPR) systems. The integrated approach presented in the paper holds promise for the practical implementation of ALPR technology and further development in the field of license plate recognition systems.

关键词： Computer vision Optical character recognition deep learning Artificial intelligence ALPR

来源：评论

学校读者我要写书评

暂无评论

A deep learning enhanced inverse scattering framework for microwave imaging of piece-wise homogeneous targets

引用

INVERSE PROBLEMS 2024年第4期40卷 045001-045001页

作者： Ruiz, Alvaro Yago Stevanovic, Maria Nikolic Cavagnaro, Marta Crocco, Lorenzo Inst Electromagnet Sensing Environm Natl Res Council Italy CNR IREA Naples Italy Singidunum Univ Belgrade Serbia Sapienza Univ Rome DIET Rome Italy

In this paper, we present a framework for the solution of inverse scattering problems that integrates traditional imaging methods and deep learning. The goal is to image piece-wise homogeneous targets and it is pursued in three steps. First, raw-data are processed via orthogonality sampling method to obtain a qualitative image of the targets. Then, such an image is fed into a U-Net. In order to take advantage of the implicitly sparse nature of the information to be retrieved, the network is trained to retrieve a map of the spatial gradient of the unknown contrast. Finally, such an augmented shape is turned into a map of the unknown permittivity by means of a simple post-processing. The framework is computationally effective, since all processing steps are performed in real-time. To provide an example of the achievable performance, Fresnel experimental data have been used as a validation.

关键词： inverse scattering microwave imaging deep learning qualitative methods orthogonality sampling method

来源：评论

学校读者我要写书评

暂无评论

A two-stage deep transfer learning model and its application for medical image processing in Traditional Chinese Medicine

引用

KNOWLEDGE-BASED SYSTEMS 2022年 239卷 108060-108060页

作者： Zhang, Xu Chen, Zhikui Gao, Jing Huang, Wei Li, Peng Zhang, Jianing Dalian Univ Technol Sch Software Technol Dalian Peoples R China Key Lab Ubiquitous Network & Serv Software Liaoni Dalian Peoples R China Dalian Med Univ Dept Crit Care Med Affiliated Hosp 1 Dalian Peoples R China

People are deepening the study on model explainability as well as performance to better understand models' decisions from the human perspective. However, the lack of rare clinical diagnosis data always limits the power of the emerging data-driven deep diagnosis methods, and the traditional deep transfer learning (DTL) applicable for the case is often insufficient to learn specific features in medical image processing, leading to poor explainability. To address those challenges, a two-stage deep transfer learning model is proposed and applied to assist in the Traditional Chinese Medicine (TCM) tongue diagnosis. Especially, a two-stage transfer learning training strategy is designed to loose the data dependence of deep learning on the domain data, which is composed of the imitate stage that discovers shared basic source features and the transfer stage to relearn target patterns, with good explainability. The corresponding deep squeeze-and-excitation convolutional network is proposed to learn the clinical patterns of tongue symptoms, in which a three-layer feature pyramid network fuses the multi-scale tongue features. Extensive experiments are conducted on the real clinical dataset in terms of classification accuracy and learning efficiency. The resulting accuracy of the proposed model proves its performance advantage with the recognition time achieving real-time performance. (c) 2021 Elsevier B.V. All rights reserved.

关键词： deep transfer learning deep neural networks Medical image processing Traditional Chinese Medicine Tongue diagnosis

来源：评论

学校读者我要写书评

暂无评论

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

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：