检索结果-内蒙古大学图书馆

A deep learning-Based Hybrid Approach to Detect Fastener Defects in real-time

TEHNICKI VJESNIK-TECHNICAL GAZETTE 2023年第5期30卷 1461-1468页

作者： Aydin, Ilhan Sevi, Mehmet Akin, Erhan Guclu, Emre Karakose, Mehmet Aldarwich, Hssen Firat Univ Elazig Turkiye Mus Alparslan Univ Mus Turkiye

A fastener is an important component used to fix the rail in railways. Defects in this component cause the rail and ballast to remain unstable. If the defective fasteners are not replaced in time, it is inevitable that the train will derail, and serious accidents will occur. Therefore, this component should be inspected periodically. Conventional image processing-based control systems are affected by noise and different lighting conditions in the real environment. In this study, it is aimed to determine the defects of fasteners with a deep learning-based hybrid approach. The YOLOv4-Tiny method is used for fastener detection and localization. This method gives accurate results, especially for the detection of small objects. After the fastener position is determined, a new lightweight convolutional neural network model is used for defect classification. The proposed convolutional neural network for classification has a small network structure because it uses depth-wise and pointwise convolution layers. When the experimental results are compared with other known transfer learning methods, better results were obtained in terms of training/test time and accuracy.

关键词： defect detection deep learning fastener object detection railway system

来源：评论

学校读者我要写书评

暂无评论

Contraband detection of millimeter wave image for postal security checks using a spatial transformer-feature fusion network

引用

APPLIED OPTICS 2024年第18期63卷 4868-4873页

作者： Xu, Li -Min Pan, Zi-Xiang Wu, Heng Di, Jiang-Lei Qin, Yu-Wen Guangdong Univ Technol Adv Inst Photon Technol Sch Informat Engn Guangzhou 510006 Peoples R China Guangdong Prov Key Lab Informat Photon Technol Guangzhou 510006 Peoples R China Minist Educ Key Lab Photon Technol Integrated Sensing & Commun Guangzhou 510006 Peoples R China Huaxun Anjue Intelligent Mine Co Ltd Shenzhen Peoples R China Guangdong Univ Technol Sch Automat Guangdong Prov Key Lab Cyber Phys Syst Guangzhou 510006 Peoples R China

The image resolution and contraband object detection accuracy are the two key factors for security checks based on millimeter wave imaging techniques. In this paper, a homemade real-time millimeter imaging system for small package security inspection is used to obtain about 400 raw images of envelopes containing multi -contraband objects like guns and knives. After pre -processing, spatial transformer-feature fusion (ST-FF) adapted single -shot multi -box detector (SSD) networks are used to detect the contraband objects of postal packages. The experiments reveal that the spatial-transformed-feature fusion deep learning networks demonstrate better mean average precision (mAP) performance than traditional single networks in detecting contraband objects of different scales, orientations, and distortions, and prove the great potential for security checks based on millimeter wave imaging. (c) 2024 Optica Publishing Group

关键词： deep learning image resolution Imaging systems Imaging techniques Millimeter waves real time imaging

来源：评论

学校读者我要写书评

暂无评论

A Fast Robustness Quantification Method for Evaluating Typical deep learning Models by Generally image processing 18

A Fast Robustness Quantification Method for Evaluating Typic...

引用

18th IEEE Int Symp on Parallel and Distributed Proc with Applicat (ISPA) / 10th IEEE Int Conf on Big Data and Cloud Comp (BDCloud) / IEEE Int Symp on Social Comp and Networking (SocialCom) / IEEE Int Conf on Sustainable Comp and Commun (SustainCom)

作者： Li, Haocong Cheng, Yunjia Ren, Wei Zhu, Tianqing China Univ Geosci Sch Comp Sci Wuhan Peoples R China Guangxi Key Lab Cryptog & Informat Secur Guilin Peoples R China Chinese Acad Sci CAS Inst Informat Engn Key Lab Network Assessment Technol Beijing 100093 Peoples R China

ISBN: (纸本)9781665414852

deep learning especially image recognition techniques have been extensively used in various applications such as unmanned driving. The robustness of deep learning models is of critical importance since fault image recognition results may result in serious incidents. In this paper, we propose a fast quantifying method by general image processing to evaluate the robustness of five typical deep learning models under the Keras framework (i.e., VGG16, InceptionV3, ResNet50, DenseNet, and MobileNet). We analyze six metrics in terms of accuracy, precision, recall, F1, recognition time, and impact factor. The evaluation data is publicly accessible image data sets from Kaggle. In our evaluation, the adversary samples are generated by generally image processing methods such as gray-scaling, color-reversing, and image-flipping, which is ordinary operations and easily launched. The different models over various image processing methods are evaluated and compared comprehensively. The evaluation results show that DenseNet performs best over three conditions such as baseline, gray-scaling and horizontal flipping. MobileNet costs the shortest delay in decision over all image processing methods. F1 score varies with different attack intensity. InceptionV3 presents overall robustness in most conditions.

关键词： robustness model evaluation deep learning image recognition

来源：评论

学校读者我要写书评

暂无评论

A deep Face Antispoofing System with Hardware Implementation for real-time Applications 8th

A Deep Face Antispoofing System with Hardware Implementation...

引用

8th International Conference on Computer Vision and image processing (CVIP)

作者： Umer, Saiyed Singh, Shubham Sarvadeo Kangotra, Vikram Rout, Ranjeet Kumar Aliah Univ Comp Sci & Engn Kolkata India Natl Inst Technol Comp Sci & Engn Srinagar Jammu & Kashmir India

ISBN: (纸本)9783031581809;9783031581816

A deep learning-based face anti-spoofing system has been proposed here. This work has been implemented in four segments. Firstly, an image preprocessing task is performed to extract the facial region. Then, the texture analysis of the facial region is performed to compute discriminant features. For this, a robust approach to deep learning techniques is needed, starting with defining some convolutional neural network (CNN) architectures for feature computation, followed by the classification of genuine vs. imposter face liveliness. The motivation of this work is to find both software- and hardware-based solutions to access biometric-based real-time systems through robust and vigorous face-liveness detection techniques. The recognition system's performances are further improved by image acquisition-challenging issues, image augmentation, fine-tuning, transfer learning, and the fusion of various trained CNN models. Finally, the above steps have been embedded in Raspberry Pi devices to build the system for real-time applications. The experimentation with two benchmark databases, NUAA and CASIA Replay-Attack, and comparing the performance with some well-known methods relating to the proposed system area show the proposed system's superiority.

关键词： Face-liveliness Anti-spoofing CNN Fusion Raspberry-Pi

来源：评论

学校读者我要写书评

暂无评论

Non-invasive respiratory infection monitoring using AI-driven thermal imaging and signal classification

引用

SIGNAL image AND VIDEO processing 2025年第7期19卷 1-14页

作者： Abisha, D. Natl Engn Coll Dept Comp Sci & Engn Kovilpatti Tamil Nadu India

The COVID-19 pandemic has highlighted the need for efficient and non-contact health screening methods. Signal-based infrared imaging is an emerging field in biomedical engineering that enables remote monitoring of vital signs. While fever is a common symptom, respiratory abnormalities often appear earlier, necessitating advanced screening systems that monitor both body temperature and respiratory patterns. This research presents an artificial intelligence-based screening device for health that identifies human respiratory patterns based on a deep learning model. The device is built with a Convolutional Neural Network (CNN) to extract features and a Long Short-Term Memory (LSTM) network to classify time-series patterns. The Softmax classifier accurately classifies respiratory patterns. It is learned on a specialized dataset of six breathing signal patterns, making it an effective model for real-time public health surveillance. The experimental result demonstrates that the proposed CNN-LSTM model achieves 91% accuracy, 90% precision, 93% recall, and an F1-score of 91%. It can be scaled up even further for medical real-time applications, paves the way to even greater future advancements in automated health surveillance.

关键词： Respiratory signals Health screening Feature extraction Signal processing deep learning techniques Classification of patterns

来源：评论

学校读者我要写书评

暂无评论

Toward User-Guided Seismic Facies Interpretation With a Pre-Trained Large Vision Model

引用

IEEE ACCESS 2025年 13卷 42965-42976页

作者： Atolagbe, Joshua Koeshidayatullah, Ardiansyah King Fahd Univ Petr & Minerals Dept Geosci Dhahran 31261 Saudi Arabia King Fahd Univ Petr & Minerals Ctr Integrat Petr Res Dhahran 31261 Saudi Arabia

Recent advancements in computer vision and deep learning have made a paradigm shift in seismic facies interpretation. Various supervised and unsupervised deep learning-based seismic facies research using Convolutional Neural Network (CNN) as the baseline architecture have been proposed and achieved promising results. However, these approaches are often limited by the lack of available high-quality labelled dataset and minimum explainability of the model. This is further compounded by the fact that these models do not allow user-guided interaction, which limits the ability of seismic interpreters to perform localized seismic facies segmentation through prompts. To optimize the already existing approach, we present a time-efficient and high precision alternative by reformulating seismic facies segmentation as a Segment All or Segment One (SASO) task. In this paper, we propose FaciesSAM, based on Fast Segment Anything Model, for seismic facies segmentation. For the first time, our paper highlights that FaciesSAM can help to decouple seismic facies identification into all-instance segmentation (segment all) and prompt-guided selection (segment one) for broad and localized facies interpretation, respectively. The effectiveness of our proposed method was evaluated on the benchmark F3 geological dataset. Experimental results shows that our method is effective, even when trained on fewer seismic images, achieving a mAP0.5 of 83.3% with 3.1% increase in pixel accuracy and 4.6% increase in mean class accuracy when compared to the CNN benchmark results. Furthermore, our method meets real-time processing speed of 1.14ms per seismic section. These results underscore the capacity of prompt-based CNN detectors to solving specific geological challenges such as seismic interpretation accuracy and processing speed.

关键词： image segmentation Convolutional neural networks Computational modeling Training Computer vision Transformers Petroleum Head Feature extraction Data models Facies segmentation prompt-based FaciesSAM deep learning model explainability

来源：评论

学校读者我要写书评

暂无评论

Research on automatic classification and detection of chicken parts based on deep learning algorithm

引用

JOURNAL OF FOOD SCIENCE 2023年第10期88卷 4180-4193页

作者： Chen, Yan Peng, Xianhui Cai, Lu Jiao, Ming Fu, Dandan Xu, Chen Chen Zhang, Peng Wuhan Polytech Univ Sch Mech Engn Wuhan Peoples R China

Accurate classification and identification of chicken parts are critical to improve the productivity and processing speed in poultry processing plants. However, the overlapping of chicken parts has an impact on the effectiveness of the identification process. To solve this issue, this study proposed a real-time classification and detection method for chicken parts, utilizing YOLOV4 deep learning. The method can identify segmented chicken parts on the assembly line in real time and accurately, thus improving the efficiency of poultry processing. First, 600 images containing multiple chicken part samples were collected to build a chicken part dataset after using the image broadening technique, and then the dataset was divided according to the 6:2:2 division principle, with 1200 images as the training set, 400 images as the test set, and 400 images as the validation set. Second, we utilized the single-stage target detector YOLO to predict and calculate the chicken part images, obtaining the categories and positions of the chicken leg, chicken wing, and chicken breast in the image. This allowed us to achieve real-time classification and detection of chicken parts. This approach enabled real-time and efficient classification and detection of chicken parts. Finally, the mean average precision (mAP) and the processing time per image were utilized as key metrics to evaluate the effectiveness of the model. In addition, four other target detection algorithms were introduced for comparison with YOLOV4-CSPDarknet53 in this study, which include YOLOV3-Darknet53, YOLOV3-MobileNetv3, SSD-MobileNetv3, and SSD-VGG16. A comprehensive comparison test was conducted to assess the classification and detection performance of these models for chicken parts. Finally, for the chicken part dataset, the mAP of the YOLOV4-CSPDarknet53 model was 98.86% on a single image with an inference speed of 22.2 ms, which was higher than the other four models of YOLOV3-Darknet53, YOLOV3-MobileNetv3, SSD-Mo

关键词： chicken parts comparison test deep learning detection effect target detection

来源：评论

学校读者我要写书评

暂无评论

Automatic Vision-Based Dump Truck Productivity Measurement Based on deep-learning Illumination Enhancement for Low-Visibility Harsh Construction Environment

引用

JOURNAL OF CONSTRUCTION ENGINEERING AND MANAGEMENT 2024年第11期150卷 04024154-04024154页

作者： Deng, Tao Sharafat, Abubakar Lee, Soomin Seo, Jongwon Hanyang Univ Seoul 04763 South Korea Kyungpook Natl Univ Sch Architectural Civil Environm & Energy Engn Daegu 41566 South Korea

Productivity assessment plays a key role in successful earthwork projects and is primarily achieved by monitoring key construction equipment such as excavators and dump trucks. Vision-based methods are widely adopted to analyze the productivity of construction equipment in earthwork projects. These methods are inexpensive and easy to implement and maintain. However, previous studies on vision-based productivity analysis of earthmoving equipment have predominantly demonstrated its effectiveness under favorable conditions characterized by stable lighting, areas devoid of shadows, and high-visibility environments free from significant occlusion by other objects or terrain. There is a significant illumination difference and limited visibility under harsh low-visibility conditions at earthwork construction sites, which makes it difficult to achieve reliable identification accuracy using these already developed methods. To address this problem, this study proposes an automatic vision-based dump truck productivity measurement method based on a deep learning illumination enhancement algorithm combined with transfer learning for low-visibility, harsh conditions at earthwork construction sites. This method uses an internet of things (IoT) system equipped with a camera to capture the image and a deep learning illumination enhancement algorithm, trainable deep hybrid network (TDHN), to enhance the image quality under low-light conditions at earthwork sites. Then, a deep convolutional neural network image recognition algorithm, ResNet50, was combined with a transfer learning technique to extract information from the image. Through the IoT, this processed information is sent to the earthwork platform to perform productivity analysis and make timely decisions regarding equipment allocation schemes. To validate the effectiveness of the proposed methodology, it was implemented in a real-time earthwork project. This study results show that image recognition accuracy of 99.6%, 95.67%,

关键词： Earthwork Productivity Internet of things (IoT) Convolutional neural network Transfer learning image enhancement Low visibility

来源：评论

学校读者我要写书评

暂无评论

SP-CrackNet: serial-parallel network with boundary contrastive learning for real-time crack detection

引用

SIGNAL image AND VIDEO processing 2024年第4期18卷 3265-3274页

作者： Xie, Ying Yin, Hui Chong, Aixin Yang, Ying Beijing Jiaotong Univ Sch Comp & Informat Technol Beijing 100044 Peoples R China Beijing Jiaotong Univ Beijing Key Lab Traff Data Anal & Min Beijing 100044 Peoples R China Beijing Jiaotong Univ Frontiers Sci Ctr Smart High Speed Railway Syst Beijing 100044 Peoples R China Beijing Jiaotong Univ Key Lab Beijing Railway Engn Beijing 100044 Peoples R China

Crack detectors based on deep learning have made tremendous progress compared to inefficient traditional inspections. However, missing thin local structures, blurred boundary segmentation and slow inference speed restrict the performance improvement of existing crack detectors. To this end, we propose a serial-parallel network (SP-CrackNet) for pixel-level real-time crack detection. Specifically, a serial-parallel feature extractor with global bottleneck blocks (GB Block) is proposed. Based on the serial-parallel structure, SPFE can enlarge the receiving field and capture the local information of thin cracks effectively, and the GB Block designed by us can ensure the continuity of the slender cracks is sensed with a lower computational cost. Moreover, a boundary contrastive learning scheme (BCL scheme) is designed to enhance the learning ability of SP-CrackNet for crack boundary features, thereby improving the segmentation accuracy of crack boundary regions. Extensive experiments on CFD and deepCrack datasets show that SP-CrackNet outperforms the comparative methods while achieving real-time inference speed.

关键词： real-time crack detection Serial-parallel structure Boundary contrastive learning Global bottleneck block

来源：评论

学校读者我要写书评

暂无评论

An Adaptive learning Rate deep learning Optimizer Using Long and Short-Term Gradients Based on G-L Fractional-Order Derivative

引用

NEURAL processing LETTERS 2024年第2期56卷 106-106页

作者： Chen, Shuang Zhang, Changlun Mu, Haibing Beijing Univ Civil Engn & Architecture Sch Sci Beijing 100044 Peoples R China Beijing Jiaotong Univ Key Lab Commun & Informat Syst Beijing 100044 Peoples R China

deep learning model is a multi-layered network structure, and the network parameters that evaluate the final performance of the model must be trained by a deep learning optimizer. In comparison to the mainstream optimizers that utilize integer-order derivatives reflecting only local information, fractional-order derivatives optimizers, which can capture global information, are gradually gaining attention. However, relying solely on the long-term estimated gradients computed from fractional-order derivatives while disregarding the influence of recent gradients on the optimization process can sometimes lead to issues such as local optima and slower optimization speeds. In this paper, we design an adaptive learning rate optimizer called AdaGL based on the Grunwald-Letnikov (G-L) fractional-order derivative. It changes the direction and step size of parameter updating dynamically according to the long-term and short-term gradients information, addressing the problem of falling into local minima or saddle points. To be specific, by utilizing the global memory of fractional-order calculus, we replace the gradient of parameter update with G-L fractional-order approximated gradient, making better use of the long-term curvature information in the past. Furthermore, considering that the recent gradient information often impacts the optimization phase significantly, we propose a step size control coefficient to adjust the learning rate in real-time. To compare the performance of the proposed AdaGL with the current advanced optimizers, we conduct several different deep learning tasks, including image classification on CNNs, node classification and graph classification on GNNs, image generation on GANs, and language modeling on LSTM. Extensive experimental results demonstrate that AdaGL achieves stable and fast convergence, excellent accuracy, and good generalization performance.

关键词： deep learning Optimization algorithm Adaptive learning rate Fractional-order derivative

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：