检索结果-内蒙古大学图书馆

A deep Convolutional Encoder-Decoder-Restorer Architecture for image Deblurring

NEURAL processing LETTERS 2024年第1期56卷 27-27页

作者： Fan, Yiqing Hong, Chaoqun Zeng, Guanghui Liu, Lijuan Xiamen Univ Technol Key Lab Fujian Univ Virtual Real & 3D Visualizat Xiamen 361024 Fujian Peoples R China

The accuracy of many computer vision tasks is reduced by blurred images, so deblur is important. More details of the image can be captured by a common multi-stage network, but the computational complexity of this method is higher compared with a single-stage network. However, a single-stage network cannot capture multi-scale information well. To tackle the problem, a novel convolutional encoder-decoder-restorer architecture is proposed. In this architecture, a multi-scale input structure is used in the encoder. Improved supervised attention module is inserted into the encoder for enhanced feature acquisition. In decoder, information supplement block is proposed to fuse multi-scale features. Finally, the fused features are used for image recovery in the restorer. In order to optimise the model in multiple domains, the loss function is calculated separately in the spatial and frequency domains. Our method is compared with existing methods on the GOPRO dataset. In addition, to verify the applications of our proposed method, we conduct experiments on the real image dataset, the VOC2007 dataset and the LFW dataset. Experimental results show that our proposed method outperforms state-of-the-art deblurring methods and improves the accuracy of different vision tasks.

关键词： image deblurring Encoder-decoder-restorer architecture Multi-Scale deep learning

来源：评论

学校读者我要写书评

暂无评论

Application of intelligent real-time image processing in fitness motion detection under internet of things

引用

JOURNAL OF SUPERCOMPUTING 2022年第6期78卷 7788-7804页

作者： Cai, Hang Nanjing Normal Univ Sch Sports Sci & Phys Educ Nanjing 210000 Jiangsu Peoples R China

The purpose is to study the applicability of digital and intelligent real-time image processing (IP) in fitness motion detection under the environment of the Internet of Things (IoT). Given the absence of real-time training standards and possible workout injury problems during fitness activities, an intelligent fitness real-time IP system based on deep learning (DL) is implemented. Specifically, the keyframes of the real-time images are collected from the fitness monitoring video, and the DL algorithm is introduced to analyze the fitness motions. Afterward, the performance of the proposed system is evaluated through simulation. Subsequently, the Noise Reduction (NR) performance of the proposed algorithm is evaluated from the Peak Signal-to-Noise Ratio (PSNR), which remains above 20 dB for seriously noisy images (with a noise density reaching up to 90%). By comparison, the PSNR of the Standard Median Filter (SMF) and Ranked-order Based Adaptive Median Filter (RAMF) algorithms are not higher than 10 dB. Meanwhile, the proposed algorithm outperforms other DL algorithms by over 2.24% with a detection accuracy of 97.80%;the proposed system can adaptively detect the fitness motion, with a transmission delay no larger than 1 s given a maximum of 750 keyframes. Therefore, the proposed DL-based intelligent fitness real-time IP algorithm has strong robustness, high detection accuracy, and excellent real-time image diagnosis and processing effect, thus providing an experimental reference for sports digitalization and intellectualization.

关键词： deep learning real-time image processing Internet of Things Fitness motion Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

A Generative Neighborhood-Based deep Autoencoder for Robust Imbalanced Classification

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第1期5卷 80-91页

作者： Troullinou, Eirini Tsagkatakis, Grigorios Losonczy, Attila Poirazi, Panayiota Tsakalides, Panagiotis University of Crete Department of Computer Science HeraklionGR 70013 Greece Institute of Computer Science - FORTH HeraklionGR 70013 Greece Columbia University Department of Neuroscience New YorkNY10027 United States Mortimer B. Zuckerman Mind Brain Behavior Institute New YorkNY10027 United States Foundation for Research and Technology Hellas Institute of Molecular Biology and Biotechnology Heraklion70013 Greece

deep learning models perform remarkably well on many classification tasks recently. The superior performance of deep neural networks relies on the large number of training data, which at the same time must have an equal class distribution in order to be efficient. However, in most real-world applications, the labeled data may be limited with high imbalance ratios among the classes, and thus, the learning process of most classification algorithms is adversely affected resulting in unstable predictions and low performance. Three main categories of approaches address the problem of imbalanced learning, i.e., data-level, algorithmic level, and hybrid methods, which combine the two aforementioned approaches. Data generative methods are typically based on generative adversarial networks, which require significant amounts of data, while model-level methods entail extensive domain expert knowledge to craft the learning objectives, thereby being less accessible for users without such knowledge. Moreover, the vast majority of these approaches are designed and applied to imaging applications, less to time series, and extremely rare to both of them. To address the above issues, we introduce GENDA, a generative neighborhood-based deep autoencoder, which is simple yet effective in its design and can be successfully applied to both image and time-series data. GENDA is based on learning latent representations that rely on the neighboring embedding space of the samples. Extensive experiments, conducted on a variety of widely-used real datasets demonstrate the efficacy of the proposed method. © 2020 IEEE.

关键词： time series analysis

来源：评论

学校读者我要写书评

暂无评论

Condition Monitoring of Railway Pantograph Using R-CNN and image processing

引用

JOURNAL OF ELECTRICAL ENGINEERING & TECHNOLOGY 2023年第3期18卷 2407-2416页

作者： Na, Kyung-Min Lee, Kiwon Kim, Hyungchul Railway Components Evaluat Ctr Korea Testing Lab Seoul South Korea Korea Railrd Res Inst Smart Elect & Signaling Div Uiwang South Korea

A railway pantograph supplies a vehicle with the electric power from the OCL (Overhead Contact Line). The contact strip, which directly contacts the OCL, is vulnerable to wear and should be periodically replaced to prevent accidents from power outages. To that end, the pantograph is regularly checked visually during routine maintenance, along with the panhead which includes the horn and the contact strip. However, real-time monitoring is still difficult, and a reliable method needs to be developed. The existing methods use image processing to detect the actual condition of the contact strip. In this paper, we suggest a method for detecting the wear size of the contact strip using image processing and deep learning. In addition, we demonstrate how to assess the condition of the panhead and the horn in the contact. The monitoring equipment is built on the test bed and is automatically configured to acquire images of the moving pantograph. The tilt of the panhead is estimated from image recognition and the condition of the horn is assessed with deep learning. In the future, this method can be used not only for efficient pantograph maintenance but also for determining the performance according to the contact condition.

关键词： Electric railway Pantograph Contact strip Maintenance

来源：评论

学校读者我要写书评

暂无评论

real-time pose estimation and motion tracking for motion performance using deep learning models

引用

JOURNAL OF INTELLIGENT SYSTEMS 2024年第1期33卷

作者： Liu, Long Dai, Yuxin Liu, Zhihao Chongqing Presch Educ Coll Sch Hlth Care Chongqing 404047 Peoples R China Chongqing Presch Educ Coll Sch Phys Educ Chongqing 404047 Peoples R China

With the refinement and scientificization of sports training, the demand for sports performance analysis in the field of sports has gradually become prominent. In response to the problem of low accuracy and poor real-time performance in human pose estimation during sports, this article focused on volleyball sports and used a combination model of OpenPose and deepSORT to perform real-time pose estimation and tracking on volleyball videos. First, the OpenPose algorithm was adopted to estimate the posture of the human body region, accurately estimating the coordinates of key points, and assisting the model in understanding the posture. Then, the deepSORT model target tracking algorithm was utilized to track the detected human pose information in real-time, ensuring consistency of identification and continuity of position between different frames. Finally, using unmanned aerial vehicles as carriers, the YOLOv4 object detection model was used to perform real-time human pose detection on standardized images. The experimental results on the Volleyball Activity Dataset showed that the OpenPose model had a pose estimation accuracy of 98.23%, which was 6.17% higher than the PoseNet model. The overall processing speed reached 16.7 frames/s. It has good pose recognition accuracy and real-time performance and can adapt to various volleyball match scenes.

关键词： motion performance pose estimation motion tracking deep learning models real-time performance

来源：评论

学校读者我要写书评

暂无评论

Phase unwrapping using deep learning in holographic tomography

引用

OPTICS EXPRESS 2023年第12期31卷 18964-18992页

作者： Gontarz, Michal Dutta, Vibekananda Kujawinska, Malgorzata Krauze, Wojciech Warsaw Univ Technol Inst Micromech & Photon 8 Boboli St PL-02525 Warsaw Poland

Holographic tomography (HT) is a measurement technique that generates phase images, often containing high noise levels and irregularities. Due to the nature of phase retrieval algorithms within the HT data processing, the phase has to be unwrapped before tomographic reconstruction. Conventional algorithms lack noise robustness, reliability, speed, and possible automation. In order to address these problems, this work proposes a convolutional neural network based pipeline consisting of two steps: denoising and unwrapping. Both steps are carried out under the umbrella of a U-Net architecture;however, unwrapping is aided by introducing Attention Gates (AG) and Residual Blocks (RB) to the architecture. Through the experiments, the proposed pipeline makes possible the phase unwrapping of highly irregular, noisy, and complex experimental phase images captured in HT. This work proposes phase unwrapping carried out by segmentation with a U-Net network, that is aided by a pre-processing denoising step. It also discusses the implementation of the AGs and RBs in an ablation study. What is more, this is the first deep learning based solution that is trained solely on real images acquired with HT.

关键词： image processing Medical image processing Phase imaging Phase measurement Phase retrieval Phase unwrapping

来源：评论

学校读者我要写书评

暂无评论

Estimating Water Levels through Smartphone-imaged Gauges: A Comparative Analysis of ANN, DL, and CNN Models

引用

WATER RESOURCES MANAGEMENT 2025年第4期39卷 1639-1654页

作者： Santos, Celso Augusto Guimaraes Ghorbani, Mohammad Ali Abdi, Erfan Patel, Utkarsh Sadeddin, Siria Univ Fed Paraiba Dept Civil & Environm Engn BR-58051900 Joao Pessoa PB Brazil Univ Tabriz Dept Water Engn Tabriz Iran Indian Inst Technol IIT Bhilai Main Campus Durg 491001 Chhattisgarh India Univ Nacl Colombia Math Dept Bogota Colombia

Understanding and monitoring water levels are essential for various applications, including environmental protection, public safety, and resource management. Water level estimation, a critical aspect of hydrological monitoring, is often constrained by challenges such as resource scarcity, high costs, and time-intensive processes. This research addresses these limitations by developing a machine learning-based system for automatic and real-time water level control. Specifically, it investigates the effectiveness of a non-contact, image-based water level measurement approach, leveraging recent advancements in mobile imaging technology. images were captured using a standard smartphone equipped with an RGB camera for water level analysis. Through precise image alignment processing under both clear and turbid conditions, the water's edge on a gauge was accurately detected. The study centers on the development and comparison of three computational models: Artificial Neural Networks (ANN), deep learning (DL), and Convolutional Neural Networks (CNN). These models were trained to estimate water levels from processed image data. Results demonstrated varying levels of accuracy across models, with the CNN model outperforming others, achieving the lowest error rate of 24.36 mm and the highest correlation of 0.986. In contrast, the ANN model yielded the highest error rate at 30.76 mm and the lowest correlation of 0.968, highlighting the relative effectiveness of CNN in this application. Given the high accuracy (92.6%) of the image processing method and CNN model in detecting water surface edges and determining water levels, this system has substantial potential to enhance water resource management and control efficiency.

关键词： Computational Hydrology Convolutional Neural Networks Hydrological Monitoring image Analysis Non-contact Measurement

来源：评论

学校读者我要写书评

暂无评论

real-time deep learning-Based Object Recognition in Augmented reality

Real-Time Deep Learning-Based Object Recognition in Augmente...

引用

Conference on real-time processing of image, Depth, and Video Information

作者： Egipko, V Zhdanova, M. Gapon, N. Voronin, V. Semenishchev, E. Moscow State Univ Technol STANKIN Ctr Cognit Technol & Machine Vis Moscow Russia Don State Tech Univ Rostov Na Donu Russia

ISBN: (纸本)9781510673199;9781510673182

Augmented reality is a visualization technology that displays information by adding virtual images to the real world. Effective implementation of augmented reality requires recognition of the current scene. Identifying objects in real-time video on computationally limited hardware requires significant effort. One way to solve this problem is to create a hybrid system that, based on machine learning and computer vision technology, processes and analyzes visual data to identify and classify real-world objects. The proposed architecture is based on a combination of the Vuforia augmented system, which provides good performance by balancing prediction accuracy and efficiency. First, the Vuforia neural network architecture allows convenient interaction with AR in Unity and provides initial conditions for detecting 3D objects. The augmented reality construction algorithm is based on the ARCore framework and the OpenGL interface for embedded systems. The system integrates recognition data with an AR platform to display corresponding 3D models, allowing users to interact with them through the functionality of the AR application. This method also involves the development of an enhanced user interface for AR, making the augmented environment more accessible for navigation and control. Experimental research has shown that the proposed method significantly improves the accuracy of object recognition and the ease of working with 3D models in AR.

关键词： deep learning augmented reality computer vision object recognition robotic systems real-time processing

来源：评论

学校读者我要写书评

暂无评论

Artifact reduction in photoacoustic images by generating virtual dense array sensor from hemispheric sparse array sensor using deep learning

引用

JOURNAL OF MEDICAL ULTRASONICS 2024年第2期51卷 169-183页

作者： Yamakawa, Makoto Shiina, Tsuyoshi Shibaura Inst Technol SIT Res Labs 3-7-5 ToyosuKoto Ku Tokyo 1358548 Japan

PurposeVascular distribution is important information for diagnosing diseases and supporting surgery. Photoacoustic imaging is a technology that can image blood vessels noninvasively and with high resolution. In photoacoustic imaging, a hemispherical array sensor is especially suitable for measuring blood vessels running in various directions. However, as a hemispherical array sensor, a sparse array sensor is often used due to technical and cost issues, which causes artifacts in photoacoustic images. Therefore, in this study, we reduce these artifacts using deep learning technology to generate signals of virtual dense array *** 2D virtual array sensor signals using a 3D convolutional neural network (CNN) requires huge computational costs and is impractical. Therefore, we installed virtual sensors between the real sensors along the spiral pattern in three different directions and used a 2D CNN to generate signals of the virtual sensors in each direction. Then we reconstructed a photoacoustic image using the signals from both the real sensors and the virtual *** evaluated the proposed method using simulation data and human palm measurement data. We found that these artifacts were significantly reduced in the images reconstructed using the proposed method, while the artifacts were strong in the images obtained only from the real sensor *** the proposed method, we were able to significantly reduce artifacts, and as a result, it became possible to recognize deep blood vessels. In addition, the processing time of the proposed method was sufficiently applicable to clinical measurement.

关键词： Photoacoustic imaging Sparse array sensor Hemispherical array sensor deep learning Artifact reduction

来源：评论

学校读者我要写书评

暂无评论

Yield prediction, pest and disease diagnosis, soil fertility mapping, precision irrigation scheduling, and food quality assessment using machine learning and deep learning algorithms

引用

DISCOVER FOOD 2025年第1期5卷 1-23页

作者： Ajith, S. Vijayakumar, S. Elakkiya, N. Int Rice Res Inst New Delhi 110012 India ICAR Indian Inst Rice Res Hyderabad 500030 India ICAR Cent Inst Brackishwater Aquaculture Chennai 600028 Tamil Nadu India

The growing demand for food grains amidst resource constraints necessitates advancements in crop management. Artificial intelligence, particularly machine learning and deep learning, is revolutionizing agricultural practices by enabling data-driven, precise, and sustainable solutions. This review synthesizes advancements in artificial intelligence applications across key domains, including crop yield prediction, precision irrigation, soil fertility mapping, insect pest and disease forecasting, and foodgrain quality assessment. Artificial intelligence algorithms efficiently process vast datasets from unmanned aerial vehicles, ground vehicles, and satellites, enabling precise and timely interventions. Artificial intelligence-driven tools automate pest detection and classification, optimize irrigation with minimal human input, generate high-resolution soil fertility maps, and enhance foodgrain quality assessment through rapid defect and contaminant detection. Artificial intelligence-powered precision irrigation integrates real-time soil moisture data and weather predictions for optimized water usage. Similarly, artificial intelligence-driven soil fertility mapping not only enables high-resolution assessments but also facilitates real-time monitoring of nutrient dynamics, supporting sustainable land management. In pest and disease detection, artificial intelligence systems combining image processing and real-time analytics demonstrate promise for early intervention. Artificial intelligence integration into foodgrain quality assessment leverages hyperspectral imaging and predictive models to enhance grading, adulteration detection, and contaminant screening, contributing to food safety and market competitiveness. Furthermore, advancements in transfer learning and data augmentation have improved artificial intelligence adoption in regions with limited datasets. While artificial intelligence technologies promise to boost agricultural productivity and sustainability, their

关键词： Artificial intelligence Nutrient management Soil moisture Crop protection Yield forecasting

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：