检索结果-内蒙古大学图书馆

Flame lift-off detector based on deep learning neural networks

COMBUSTION AND FLAME 2024年 260卷

作者： Gharib, Mohsen Tischer, Paul Schulze, Olaf Graebner, Martin Richter, Andreas Fraunhofer Inst Ceram Technol & Syst Winterbergstr 28 D-01277 Dresden Germany TU Bergakad Freiberg Inst Energy Proc Engn & Chem Engn Fuechsmuehlenweg 9 D-09599 Freiberg Germany

This study evaluates the application of deep learning techniques in real-time flame lift-off detection and lift -off length prediction from flame images. A multi-feed test facility equipped with an optical diagnostic system was used to investigate the flame stability of both liquid and solid fuels. A high-speed camera was used to capture flame images, and image processing techniques were employed to extract the data. In the case of flame detection from images captured by high-speed cameras, the temporal resolution of the images is very high, which is beneficial for detecting rapid changes in the flame dynamics. In the current study, the analysis of 10,000 images by images processing methods takes approximately 60 min. Therefore, traditional methods may not be suitable for real-time monitoring, as they may not be able to capture the detailed variations in the flame appearance and intensity. The objective of this study was to find a fast and computationally efficient way to detect flame lift-off in high-speed online flame monitoring system. Two models were used in this study: a convolutional autoencoder and a regression neural network. The results demonstrate the potential of deep learning techniques in online flame diagnostics. The proposed approach provides a fast and efficient way to process 10,000 images in only 3.5 s, making it suitable for implementation in real-time flame monitoring *** and significancePrevious studies in the field of real-time flame diagnostics have predominantly used low sampling rates to capture flame images. However, when high-speed cameras are used, conventional image processing techniques prove inadequate to provide instant results for real-time monitoring systems. This study presents a novel deep learning approach capable of directly detecting flame lift-off from high-speed images without the need for separate segmentation, thereby significantly enhancing the analysis speed. The results obtained in this paper emphasize the ad

关键词： Flame detection Flame lift-off Neural networks Flame stability Gasification Partial oxidation

来源：评论

学校读者我要写书评

暂无评论

real-time diabetic foot ulcer classification based on deep learning & parallel hardware computational tools

引用

MULtimeDIA TOOLS AND APPLICATIONS 2024年第27期83卷 70369-70394页

作者： Fadhel, Mohammed A. Alzubaidi, Laith Gu, Yuantong Santamaria, Jose Duan, Ye Univ Sumer Coll Comp Sci & Informat Technol Thi Qar 64005 Iraq Queensland Univ Technol Sch Mech Med & Proc Engn Brisbane Qld 4000 Australia Queensland Univ Technol ARC Ind Transformat Training Ctr Joint Biomech Brisbane Qld 4000 Australia Akunah Med Technol Pty Ltd Co Brisbane Qld 4120 Australia Univ Jaen Dept Comp Sci Jaen 23071 Spain Clemson Univ Sch Comp Clemson SC 29631 USA

Meeting the rising global demand for healthcare diagnostic tools is crucial, especially with a shortage of medical professionals. This issue has increased interest in utilizing deep learning (DL) and telemedicine technologies. DL, a branch of artificial intelligence, has progressed due to advancements in digital technology and data availability and has proven to be effective in solving previously challenging learning problems. Convolutional neural networks (CNNs) show potential in image detection and recognition, particularly in healthcare applications. However, due to their resource-intensiveness, they surpass the capabilities of general-purpose CPUs. Therefore, hardware accelerators such as application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), and graphics processing units (GPUs) have been developed. With their parallelism efficiency and energy-saving capabilities, FPGAs have gained popularity for DL networks. This research aims to automate the classification of normal and abnormal (specifically Diabetic Foot Ulcer-DFU) classes using various parallel hardware accelerators. The study introduces two CNN models, namely DFU_FNet and DFU_TFNet. DFU_FNet is a simple model that extracts features used to train classifiers like SVM and KNN. On the other hand, DFU_TFNet is a deeper model that employs transfer learning to test hardware efficiency on both shallow and deep models. DFU_TFNet has outperformed AlexNet, VGG16, and GoogleNet benchmarks with an accuracy 99.81%, precision 99.38% and F1-Score 99.25%. In addition, the study evaluated two high-performance computing platforms, GPUs and FPGAs, for real-time system requirements. The comparison of processing time and power consumption revealed that while GPUs outpace FPGAs in processing speed, FPGAs exhibit significantly lower power consumption than GPUs.

关键词： deep learning Double transfer learning FPGA GPU DFU real-time Parallel hardware Medical imaging

来源：评论

学校读者我要写书评

暂无评论

real-time Load Monitoring of Logistics Delivery Vehicles Using deep learning-Based image Analysis

引用

TRAITEMENT DU SIGNAL 2024年第4期41卷 1741-1748页

作者： Chen, Ying Chengdu Polytech Sch Int Business & Trade Chengdu 610041 Peoples R China

In the modern logistics industry, the rapid growth of e-commerce has made real-time load monitoring of delivery vehicles a critical factor in ensuring transportation efficiency and safety. However, traditional load monitoring methods are often hindered by delayed data acquisition and insufficient accuracy, making them inadequate for the high demands of efficient and precise logistics operations. Recently, with advancements in deep learning- based image analysis, image-based load monitoring methods have gained attention. However, existing studies face challenges in robustness and real-time performance, particularly in dynamic and complex environments. To address these issues, this paper proposes a real-time load monitoring method for logistics delivery vehicles based on deep learning techniques, focusing on three core technologies: subpixel edge detection in 2D images, interpolation between consecutive image frames, and real-time load volume calculation. This research aims to enhance the accuracy and real-time capabilities of load monitoring, thereby advancing the intelligent development of the logistics industry.

关键词： logistics delivery vehicles real-time load monitoring deep learning subpixel edge detection interpolation load volume calculation

来源：评论

学校读者我要写书评

暂无评论

Understanding Vector-Valued Neural Networks and Their Relationship With real and Hypercomplex-Valued Neural Networks: Incorporating intercorrelation between features into neural networks

引用

IEEE SIGNAL processing MAGAZINE 2024年第3期41卷 49-58页

作者： Valle, Marcos Eduardo Univ Estadual Campinas Dept Appl Math BR-13083859 Campinas Brazil

Despite the many successful applications of deep learning models for multidimensional signal and image processing, most traditional neural networks process data represented by (multidimensional) arrays of real numbers. The intercorrelation between feature channels is usually expected to be learned from the training data, requiring numerous parameters and careful training. In contrast, vector-valued neural networks (referred to as V-nets) are conceived to process arrays of vectors and naturally consider the intercorrelation between feature channels. Consequently, they usually have fewer parameters and often undergo more robust training than traditional neural networks. This article aims to present a broad framework for V-nets. In this context, hypercomplex-valued neural networks are regarded as vector-valued models with additional algebraic properties. Furthermore, this article explains the relationship between vector-valued and traditional neural networks. To be precise, a V-net can be obtained by placing restrictions on a real-valued model to consider the intercorrelation between feature channels. Finally, I show how V-nets, including hypercomplex-valued neural networks, can be implemented in current deep learning libraries as real-valued networks.

关键词： Training data deep learning image processing Neural networks Parallel processing Vectors Hypercomplex Multidimensional signal processing

来源：评论

学校读者我要写书评

暂无评论

Bubble evolution identification method based on U-Net deep learning

引用

SHIPS AND OFFSHORE STRUCTURES 2025年

作者： Gou, Yuxin Shi, Dongyan Wang, Jiuqiang Zhang, Haifeng Cui, Xiongwei Harbin Engn Univ Coll Mech & Elect Engn Harbin Peoples R China Harbin Engn Univ Coll Shipbldg Engn 145 Nantong St Harbin 150001 Heilongjiang Peoples R China

This study addresses the challenge of automated analysis of underwater bubble dynamics, as traditional methods for bubble detection often struggle with precision and real-time processing, requiring labour-intensive manual analysis or inefficient image processing techniques. To overcome these limitations, we propose a U-Net deep learning-based method for bubble segmentation and dynamic analysis, utilising high-speed photography (62420 fps) to capture bubble formation and dissipation. The proposed method achieves accurate bubble segmentation through deep feature extraction and upsampling using the U-Net model, with a proportional estimation method applied to calculate bubble size, expansion rate, and movement rate. Validation through manual measurements and CFD simulations confirms the method's reliability. The results demonstrate that the U-Net model enhances the efficiency and accuracy of bubble identification, providing a robust tool for studying underwater bubble dynamics in real-time.

关键词： U-net deep learning bubble evolution identification underwater electric spark experiment expansion and movement rates automated image segmentation

来源：评论

学校读者我要写书评

暂无评论

A novel hybrid Bayesian-optimized CNN-SVM deep learning model for real-time surface roughness classification and prediction based on in-process machined surface image analysis

引用

INTERNATIONAL JOURNAL OF INTERACTIVE DESIGN AND MANUFACTURING - IJIDEM 2025年 1-18页

作者： Arif, Abdul Rao, Ponugoti Gangadhara Prasad, Kalapala JNTUK Univ Coll Engn A Kakinada 533003 India Aditya Univ Dept Mech Engn Surampalem 533437 AP India JNTUK Dept Mech Engn Univ Coll Engn A Kakinada 533003 India

This study presents a novel hybrid Bayesian-optimized CNN-SVM deep learning model for real-time surface roughness classification and prediction based on in-process machined surface image analysis. The hybrid deep learning model, achieves unprecedented accuracy in real-time surface roughness classification and prediction from image data of Inconel 716 superalloy machined surface, eliminating human intervention for feature extraction and selection procedures. The Bayesian optimization algorithm (BOA) was employed to fine-tune the CNN model's hyperparameters. The derived optimal hyperparameters were used to train the CNN model, which achieved a 92.37% classification accuracy on a test dataset. The classification performance was further enhanced by integrating an SVM classifier achieving an accuracy of 98.21%. Additionally, the model's performance was compared with five state-of-the-art deep learning architectures (AlexNet, ResNet50, VGGNet, Faster R-CNN ResNet50, and CNN), with the proposed model showing superior performance in terms of precision (98.02%), sensitivity (98.40%), and F1-score (98.20%). For surface roughness estimation, the hybrid model demonstrated a 96.89% accuracy in predicting roughness values, highlighting its potential for real-time in-process quality monitoring in industrial applications. These results indicate the proposed hybrid approach demonstrated substantially better performance than other popular object detection models. Hence, the presented work demonstrates an efficient end-to-end approach based on the in-process acquired machined surface image analysis by eliminating human intervention in the process of image processing, feature extraction, and feature selection for the real-time classification and prediction of the surface roughness process.

关键词： Surface roughness prediction image-based classification Regression deep learning Convolutional neural networks Hyperparameters Bayesian optimization Support vector machine

来源：评论

学校读者我要写书评

暂无评论

Detection of weeds in vegetables using image classification neural networks and image processing

引用

FRONTIERS IN PHYSICS 2025年 13卷

作者： Jin, Huiping Han, Kang Xia, Hongting Xu, Bo Jin, Xiaojun Nanjing Forestry Univ Engn Training Ctr Nanjing Jiangsu Peoples R China Peking Univ Shandong Lab Adv Agr Sci Weifang Inst Adv Agr Sci Weifang Shandong Peoples R China Jurong Inst Smart Agr Zhenjiang Jiangsu Peoples R China

Weed management presents a major challenge to vegetable growth. Accurate identification of weeds is essential for automated weeding. However, the wide variety of weed types and their complex distribution creates difficulties in rapid and accurate weed detection. In this study, instead of directly applying deep learning to identify weeds, we first created grid cells on the input images. image classification neural networks were utilized to identify the grid cells containing vegetables and exclude them from further analysis. Finally, image processing technology was employed to segment the non-vegetable grid images based on their color features. The background grid cells, which contained no green pixels, were identified, while the remaining cells were labeled as weed cells. EfficientNet, GoogLeNet, and ResNet models achieved overall accuracies of over 0.956 in identifying vegetables in the testing dataset, demonstrating exceptional identification performance. Among these models, the ResNet model exhibited the highest computational efficiency, with a classification time of 12.76 ms per image and a corresponding frame rate of 80.31 fps, satisfying the requirement for real-time weed detection. Effectively identifying vegetables and differentiating weeds from soil significantly reduces the complexity of weed detection and improves its accuracy.

关键词： weed detection deep learning image classification neural networks image processing weed management

来源：评论

学校读者我要写书评

暂无评论

image processing framework for in-process shaft diameter measurement on legacy manual machines

引用

INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY 2024年第9-10期135卷 4323-4338页

作者： Choudhari, Sahil J. Singh, Swarit Anand Kumar, Aitha Sudheer Desai, Kaushal A. Indian Inst Technol Jodhpur Dept Mech Engn Jodhpur 342030 Rajasthan India

In-process dimension measurement is critical to achieving higher productivity and realizing smart manufacturing goals during machining operations. Vision-based systems have significant potential to serve for in-process dimensions measurements, reduce human interventions, and achieve manufacturing-inspection integration. This paper presents early research on developing a vision-based system for in-process dimension measurement of machined cylindrical components utilizing image-processing techniques. The challenges with in-process dimension measurement are addressed by combining a deep learning-based object detection model, You Only Look Once version 2 (YOLOv2), and image processing algorithms for object localization, segmentation, and spatial pixel estimation. An automated image pixel calibration approach is incorporated to improve algorithm robustness. The image acquisition hardware and the real-time image processing framework are integrated to demonstrate the working of the proposed system by considering a case study of in-process stepped shaft diameter measurement. The system implementation on a manual lathe demonstrated robust utilities, eliminating the need for manual intermittent measurements, digitized in-process component dimensions, and improved machining productivity.

关键词： Dimension measurement In-process inspection Machine vision image processing Object segmentation deep learning

来源：评论

学校读者我要写书评

暂无评论

Global-local coupled learning method for autonomous underwater vehicle side-scan sonar image recognition

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2025年 153卷

作者： Yu, Fei Liu, Xiaodong Liu, Wei Liu, Jixin Shandong Univ Sci & Technol Coll Ocean Sci & Engn Qingdao 266590 Peoples R China Minist Nat Resources Key Lab Marine Environm Survey Technol & Applicat Guangzhou 510300 Peoples R China Ocean Univ China Fac Informat Sci & Engn Qingdao 266404 Peoples R China

Independent real-time recognition of deep-sea targets is still challenging for autonomous underwater vehicles. The side-scan sonar plays an essential role in the fields of marine bottom topographic survey and resource exploration. For the deep and distant seas that are inaccessible to humankind, the traditional methods mainly collect information first and then manually recognize it offline, which has the shortcomings of weak recognition robustness and insufficient real-time. Unlike the previous methods, a global-local coupled learning method based on side-scan sonar image recognition is proposed, which can assist in independently exploring deepsea targets. Firstly, global recognition is performed to extract the image texture information using the deep learning-based segmentation network module and initially recognize the marine target species. Secondly, local recognition is performed, and the deep learning-based local attention module is used to optimize global recognition and refine image types. Finally, the results of the previous two steps are fused using the confidence screening strategy to output the final recognition results. The coupled learning method is compared with other classical and lightweight methods based on the side-scan sonar datasets. Simulation experiments demonstrate that the proposed method is robust and real-time, which can be widely used in marine target recognition.

关键词： Autonomous underwater vehicle Side-scan sonar Marine target recognition real-time capability Lightweight network Global-local coupled

来源：评论

学校读者我要写书评

暂无评论

Fast no-reference deep image dehazing

引用

MACHINE VISION AND APPLICATIONS 2024年第5期35卷 122页

作者： Qin, Hongyi Belyaev, Alexander G. Imperial Coll London Dept Elect & Elect Engn London England Heriot Watt Univ Sch Engn & Phys Sci Inst Sensors Signals & Syst Edinburgh Scotland

This paper presents a deep learning method for image dehazing and clarification. The main advantages of the method are high computational speed and using unpaired image data for training. The method adapts the Zero-DCE approach (Li et al. in IEEE Trans Pattern Anal Mach Intell 44(8):4225-4238, 2021) for the image dehazing problem and uses high-order curves to adjust the dynamic range of images and achieve dehazing. Training the proposed dehazing neural network does not require paired hazy and clear datasets but instead utilizes a set of loss functions, assessing the quality of dehazed images to drive the training process. Experiments on a large number of real-world hazy images demonstrate that our proposed network effectively removes haze while preserving details and enhancing brightness. Furthermore, on an affordable GPU-equipped laptop, the processing speed can reach 1000 FPS for images with 2K resolution, making it highly suitable for real-time dehazing applications.

关键词： image dehazing and clarification No-reference neural network training real-time dehazing Zero-DCE

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：