检索结果-内蒙古大学图书馆

Optimal matching measurement of AI based field surveys using deep learning network and smart monitoring

SMART STRUCTURES AND SYSTEMS 2025年第1期35卷 39-51页

作者： Cho, Ying-Chiang Hung, C. C. Minnan Normal Univ Sch Phys & Informat Engn Zhangzhou Fujan Peoples R China Fuzhou Univ Int Studies & Trade Sch Big Data Fuzhou Fujan Peoples R China

This research introduces an innovative method for targetless displacement measurement of reinforced soil retaining walls, employing an optimal AI deep learning network in conjunction with advanced smart monitoring technologies. Conventional displacement measurement techniques often rely on physical targets, which can introduce inaccuracies and complicate real-time internet big data collection. Our approach eliminates the need for these targets by utilizing a AI deep learning framework that processes high-dimensional sensor data to accurately detect and quantify displacements by digital platform. By optimizing the AI deep learning network architecture, we enhance the model's ability to learn complex patterns associated with soil-structure interactions with AI knowledge management. Field experiments validate the efficacy of our method, demonstrating significant improvements in measurement precision and responsiveness. The findings indicate that this targetless technique not only streamlines the monitoring process but also provides critical insights into the dynamic behavior of AI based field surveys under varying environmental and load conditions. This advancement has substantial implications for the design, safety, and maintenance based on geotechnical infrastructures.

关键词： AI knowledge management computer-aided internet big data simulation convolutional neural networks deep learning neural network digital image processing image matching remote sensing and monitoring vision technology

来源：评论

学校读者我要写书评

暂无评论

Coarse-to-fine blind image deblurring based on K-means clustering

引用

VISUAL COMPUTER 2024年第1期40卷 333-344页

作者： Eqtedaei, Amir Ahmadyfard, Alireza Shahrood Univ Technol Fac Elect Engn Shahrud Iran

Blind image deblurring is a challenging image processing problem, and a proper solution for this problem has many applications in the real world. This is an ill-posed problem, as both the sharp image and blur kernel are unknown. The traditional methods based on maximum a posterior (MAP) apply heavy constraints on the latent image or blur kernel to find the solution. However, these constraints are not always effective;meanwhile, they are very time-consuming. Recently, new approaches based on deep learning have emerged. The methods based on this approach suffer from two problems: the need for a large number of images and kernels for training and also the dependency of the result on the training data. In this paper, we propose a multiscale method based on MAP framework for image motion deblurring. In this method, we represent the blurry image in different scales. We suggest segmenting the image of each scale using kappa-means clustering. Using the image information at dominant edges guided by the segmented images, the blur kernel is estimated at each scale. The blur kernel at the finest level of the pyramid is estimated from the coarser levels in a coarse-to-fine manner. Unlike the existing MAP-based methods, the proposed method does not need mathematically complicated assumptions to estimate the intermediate latent image. So the proposed image deblurring is run fast. We evaluated the proposed method and compared it to the existing methods. The experimental results on real and synthetic blurry images demonstrate that the proposed scheme has promising results. The proposed method competes with the existing MAP-based methods for reconstructing qualitative sharp images, while the execution time for our method is considerably less.

关键词： Blind image deblurring ?-means clustering Kernel estimation

来源：评论

学校读者我要写书评

暂无评论

SPF-Net: Solar panel fault detection using U-Net based deep learning image classification

引用

ENERGY REPORTS 2024年 12卷 1580-1594页

作者： Rudro, Rifat Al Mamun Nur, Kamruddin Al Sohan, Md. Faruk Abdullah Mridha, M. F. Alfarhood, Sultan Safran, Mejdl Kanagarathinam, Karthick Amer Int Univ Bangladesh Dept Comp Sci Dhaka Bangladesh King Saud Univ Coll Comp & Informat Sci Dept Comp Sci Riyadh 11543 Saudi Arabia GMR Inst Technol Dept Elect & Elect Engn Rajam India

The detection of faults in solar panels is essential for generating increased amounts of renewable green energy. Solar panels degrade over time due to physical damage, dust, or other faults. Numerous studies have been conducted to detect and monitor solar panel faults in real-time. This research examines the deployment of deep learning models for identifying these faults. In this research, we propose a novel deep learning model combining the InceptionV3-Net with U-Net architecture. The proposed architecture applies the InceptionV3 base with imageNet weights, enhanced by convolutional layers, squeeze-and-excitation (SE) blocks, residual connections, and global average pooling. The model includes two dense layers with LeakyReLU and batch normalization, ending with a Soft-Max output layer. Incorporating image segmentation into deep learning models significantly improves the precision and test accuracy of identifying issues in solar panels. The proposed model achieves exceptional performance, having a validation accuracy of 98.34%, a test accuracy of 94.35% with an F1 score of 0.94, a precision of 0.94, and a Recall of 0.94.

关键词： Fault detection Inceptionv3 VGG16 Segmentation U-Net Solar panel

来源：评论

学校读者我要写书评

暂无评论

Thai Food Recognition Using deep learning With Cyclical learning Rates

引用

IEEE ACCESS 2024年 12卷 174204-174221页

作者： Theera-Ampornpunt, Nawanol Treepong, Panisa Prince Songkla Univ Coll Comp Phuket 83120 Thailand

Automated food recognition is essential in order to streamline dietary monitoring. To build and evaluate complex food recognition models, large datasets of annotated food images are crucial. In this paper, we introduce a new dataset called THFOOD-100, which is specifically designed for this purpose. This dataset consists of 53,459 high-quality images of popular Thai dishes categorized into 100 classes. We conducted a comprehensive comparison of 23 deep convolutional neural network and vision transformer architectures to establish a strong baseline for classification performance on the THFOOD-100 dataset. Additionally, we proposed training the models using cyclical learning rates, which has been shown to improve model generalization and significantly reduce training time. We demonstrated the effectiveness of cyclical learning rates with three standard optimizers on THFOOD-100, ETHZ Food-101, and UEC-Food256. The top-performing model achieved a 96% classification accuracy on THFOOD-100, showing great promise for real-world applications. Our new dataset is specifically aimed at better representing Thai cuisine in food recognition research, and our analyses offer valuable insights into the shortcomings of current models.

关键词： deep learning deep learning food dataset food dataset food recognition food recognition image classification image classification learning rate learning rate

来源：评论

学校读者我要写书评

暂无评论

Live imaging of laser machining via plasma deep learning

引用

OPTICS EXPRESS 2023年第25期31卷 42581-42594页

作者： Grant-Jacob, James A. Mills, Ben Zervas, Michalis N. Univ Southampton Optoelect Res Ctr Southampton SO17 1BJ England

real-time imaging of laser materials processing can be challenging as the laser generated plasma can prevent direct observation of the sample. However, the spatial structure of the generated plasma is strongly dependent on the surface profile of the sample, and therefore can be interrogated to indirectly provide an image of the sample. In this study, we demonstrate that deep learning can be used to predict the appearance of the surface of silicon before and after the laser pulse, in real-time, when being machined by single femtosecond pulses, directly from camera images of the generated plasma. This demonstration has immediate impact for real-time feedback and monitoring of laser materials processing where direct observation of the sample is not possible.

关键词： deep learning Femtosecond pulses Fiber lasers Laser imaging Laser materials Laser plasmas

来源：评论

学校读者我要写书评

暂无评论

Autonomous Traffic Sign Detection for Self-Driving Car System Using Convolutional Neural Network Algorithm

引用

JOURNAL OF OPTICS-INDIA 2024年第4期53卷 3359-3369页

作者： Yu, Zhao Ye, Ting Shanghai Inst Technol Sch Art & Design Shanghai 200235 Peoples R China Shanghai Normal Univ Res Adm Shanghai 200233 Peoples R China

The accurate detection of traffic signs is a critical component of self-driving systems, enabling safe and efficient navigation. In the literature, various methods have been investigated for traffic sign detection, among which deep learning-based approaches have demonstrated superior performance compared to other techniques. This paper justifies the widespread adoption of deep learning due to its ability to provide highly accurate results. However, the current research challenge lies in addressing the need for high accuracy rates and real-time processing requirements. In this study, we propose a convolutional neural network based on the YOLOv8 algorithm to overcome the aforementioned research challenge. The paper introduces an innovative solution in the form of a convolutional neural network based on the YOLOv8 architecture, underpinned by a custom dataset representing real-world traffic sign images and rigorous training. Through extensive experimentation, the proposed model not only proves highly effective but consistently achieves remarkable accuracy rates, successfully meeting the stringent real-time processing requirements crucial for self-driving systems, thus advancing the safety and efficiency of autonomous vehicles and shaping the future of transportation.

关键词： Traffic sign detection deep learning YOLOv8 model Self-driving cars real-time processing

来源：评论

学校读者我要写书评

暂无评论

A deep learning based Scalable and Adaptive Feature Extraction Framework for Medical images

引用

INFORMATION SYSTEMS FRONTIERS 2024年第4期26卷 1279-1305页

作者： Loukil, Zainab Mirza, Qublai Khan Ali Sayers, Will Awan, Irfan Univ Gloucestershire Cyber & Appl Comp Pk Cheltenham GL50 2RH Gloucestershire England Univ Gloucestershire Games Technol Pk Cheltenham GL50 2RH Gloucestershire England Univ Bradford Fac Engn & Informat Comp Sci Richmond Rd Bradford BD7 1DP West Yorkshire England

Features extraction has a fundamental value in enhancing the scalability and adaptability n of medical image processing framework. The outcome of this stage has a tremendous effect on the reliability of the medical application being developed, particularly disease classification and prediction. The challenging side of features extraction frameworks, in relation to medical images, is influenced by the anatomical and morphological structure of the image which requires a powerful extraction system that highlights high- and low- level features. The complementary of both feature types reinforces the medical image content-based retrieval and allows to access visible structures as well as an in-depth understanding of related deep hidden components. Several existing techniques have been used towards extracting high- and low-level features separately, including deep learning based approaches. However, the fusion of these features remains a challenging task. Towards tackling the drawback caused by the lack of features combination and enhancing the reliability of features extraction methods, this paper proposes a new hybrid features extraction framework that focuses on the fusion and optimal selection of high- and low-level features. The scalability and reliability of the proposed method is achieved by the automated adjustment of the final optimal features based on real-time scenarios resulting an accurate and efficient medical images disease classification. The proposed framework has been tested on two different datasets to include BraTS and Retinal sets achieving an accuracy rate of 97% and 98.9%, respectively.

关键词： Features extraction deep learning High-level features Low-level features Optimal features fusion

来源：评论

学校读者我要写书评

暂无评论

Leveraging Map Retrieval and Alignment for Robust UAV Visual Geo-Localization

引用

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

作者： He, Mengfan Liu, Jiacheng Gu, Pengfei Meng, Ziyang Tsinghua Univ Dept Precis Instrument Beijing 100084 Peoples R China Unmanned Aerial Vehicle Lab Beijing 100012 Peoples R China

The autonomous flight of unmanned aerial vehicles (UAVs) relies on a precise and robust geo-localization system. A visual geo-localization system registers the aerial captured image to a geo-referenced satellite map, which enables UAVs to determine their global position without a global navigation satellite system (GNSS). However, it is challenging to achieve precise and robust geo-localization in a large-scale environment due to the notable texture difference between the satellite map and the UAV-captured image. In this article, we design a robust visual geo-localization pipeline that integrates a proposed deep learning-based imagery feature. This pipeline starts with the image retrieval based on the deep feature encoding, to initialize the localization process over large-scale maps without any location prior. With the reuse of the same deep imagery feature, an image registration process enables real-time sequential localization. Besides, the proposed system has the re-localization ability to eliminate the localization drift caused by possible registration failure, especially during long-time flights. Evaluations of datasets and real-world experiments demonstrate that the proposed system is more robust and accurate than other state-of-the-art methods. To encourage further progress on the visual geo-localization problem, our code and materials are publicly available at https://***/hmf21/UAVLocalization.

关键词： Location awareness Visualization Autonomous aerial vehicles Feature extraction Accuracy image retrieval Satellites deep learning for visual perception hierarchical localization map-based navigation shared encoder visual geo-localization

来源：评论

学校读者我要写书评

暂无评论

Port obstacle detection algorithm based on image adaptive enhancement

引用

SIGNAL image AND VIDEO processing 2025年第6期19卷 1-18页

作者： Jiang, Hao Guo, Zijian Xu, Xinglu Zhang, Zhongyi Dalian Univ Technol State Key Lab Coastal & Offshore Engn Dalian 116024 Liaoning Peoples R China

When port robots perform inspection tasks, due to the diversity of shapes and categories of road obstacles, missed detections and false detections are prone to occur. At the same time, to meet the needs of robots for safe and normal operation in complex environments, an image-adaptive enhancement-based algorithm for port area environment target obstacle detection and avoidance is proposed. Firstly, in the preprocessing stage, hyperparameter optimization is introduced for the brightness, contrast, and edge clarity of the image to be detected for adaptive enhancement;secondly, a multi-scale detail enhancement module is introduced in yolov8 to enable the network to focus on high-frequency detail information of different scales to solve the problem of unclear image reconstruction edges;then, for the problem of insufficient utilization of scale information, a more efficient and lightweight multi-dimensional collaborative attention mechanism deep convolution module is used to learn the relationship between each channel and spatial position information in the image, and at the same time fuse these information to improve the reconstruction ability of the image;finally, a Transformer module is connected at the head to alleviate the interference of image noise and light pollution on target detection, enhancing the accuracy and robustness of the algorithm. Experiments are carried out by selecting some images from the public dataset and the self-built dataset. The proposed algorithm improves the detection accuracy of the port area environment by 2.1% compared with YOLOv8, reaching 90.1%;the recall rate is improved by 2.7%, reaching 91.2%, and the speed is improved by 6.1%, reaching 70.1FPS;it meets the actual requirements of real-time detection and avoidance of inspection robots

关键词： Adaptive enhancement real-time detection Inspection robots Machine vision deep learning

来源：评论

学校读者我要写书评

暂无评论

Speech enhancement using deep complex convolutional neural network (DCCNN) model

引用

SIGNAL image AND VIDEO processing 2024年第12期18卷 8675-8692页

作者： Iqbal, Yasir Zhang, Tao Fahad, Muhammad Rahman, Sadiq ur Iqbal, Anjum Geng, Yanzhang Zhao, Xin Tianjin Univ Sch Elect & Informat Engn 92 Weijin Rd Tianjin 300072 Peoples R China Dalian Univ Technol Sch Software Technol Dalian 116024 Peoples R China

In cases with highly non-stationary noise, single-channel speech enhancement is quite challenging, mainly when the noise includes interfering speech. In this situation, deep learning's success has contributed to speech enhancement to boost intelligibility and perceptual quality. Existing speech enhancement (SE) works in time-frequency domains only aim to improve the magnitude spectrum via neural network learnings;the latest research highlights the significance of phase in perceptual speech quality. Motivated by multi-task machines and deep learning this paper, proposes an effective and novel approach to the task of speech enhancement using an encoder-decoder architecture based on deep Complex Convolutional Neural Networks. The proposed model takes input from the spectrograms of the noisy speech signals, consisting of real and imaginary components for complex spectral mapping, and it simultaneously enhances the magnitude and phase responses of speech. Considering unseen non-stationary noise categories, which interfere with speech, the proposed model enhances speech quality by approximately, 0.44 MOS points compared to state-of-the-art single-stage techniques. Moreover, it outperforms all reference techniques constantly and improves intelligibility under low-SNR settings. In contrast, against the baselines, we find an incredible enhancement of over 3 dB in SNR, and 0.2 in STOI. In addition, our method outperforms baseline SE techniques in low-SNR conditions in terms of STOI.

关键词： Background noise Speech signals Speech enhancement Noise suppression deep learning deep complex convolutional neural networks

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：