检索结果-内蒙古大学图书馆

Detection Model for Automatic Defect Quantification and Segmentation for Stepped Eddy Current Thermography

IEEE SENSORS JOURNAL 2025年第7期25卷 10784-10799页

作者： Gao, Yuan Zhang, Liang Liang, Zheng Zheng, Ting Deng, Xiong Chen, Xin Southwest Petr Univ Sch Mech Engn Chengdu 610500 Peoples R China Luzhou Vocat & Tech Coll Sch Intelligent Mfg & Automot Engn Luzhou 646000 Sichuan Peoples R China Southwest Petr Univ Petr Engn Sch Chengdu 610500 Sichuan Peoples R China

The stepped eddy current thermography (SECT) nondestructive testing (NDT) technique is characterized by long heating time and nonuniform temperature rise. This causes it to remain challenging to quantify the geometrical features of defects on the inner wall of the tank roof and the outer wall of the tank bottom in oil and gas storage tanks. This article proposes a combined model for compressing and reconstructing thermal image sequences: the skewness model combined with the improved Gaussian adaptive background estimation algorithm (SM-IGABEA) for quantifying the defect morphology. The combined model is coupled with the first-order differential max-min method to quantify the width and height of defects accurately. The combined model combined with the first-order differential mean method can accurately segment defects. A mathematical model for predicting the residual depth (RD) of steel plates is developed to describe the relationship between the geometric characteristics of defects and the mean value of skewness. Finally, the generalization of SM-IGABEA is verified by elliptical defects. The results show that various combinatorial models and quantization methods are proposed for the defect measurement task. The measurement accuracy and stability of SM-IGABEA significantly outperform the mainstream compressive reconstruction algorithms.

关键词： Steel Eddy currents Sensors Infrared imaging Heating systems Temperature sensors Time series analysis Surface morphology reconstruction algorithms Oils Defect quantification study defect segmentation nondestructive testing (NDT) skewness model stepped eddy current thermography (SECT)

来源：评论

学校读者我要写书评

暂无评论

A Novel Compressive Sensing Method for Secure and Energy Efficient ECG Signal Transmission Applications

引用

IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS 2025年第5期29卷 3439-3450页

作者： Spagnolo, Fanny Lal, Bharat Corsonello, Pasquale Gravina, Raffaele Univ Calabria Dept Informat Modeling Elect & Syst Engn I-87036 Arcavacata Di Rende CS Italy SenSysCal SRL I-87036 Arcavacata Di Rende CS Italy

This paper introduces a novel Compressive Sensing (CS)-based cryptosystem tailored for the secure and efficient transmission of Electrocardiogram (ECG) signals in Internet of Medical Things (IoMT) environments. It leverages the inherent sparsity of ECG signals in the wavelet domain and ensures both data privacy and integrity during transmission through a simple but effective additional encryption stage. We have evaluated the performance of four distinct sensing matrices and three reconstruction algorithms across multiple wavelet families. Through extensive simulations using the MIT-BIH Arrhythmia Database we demonstrate that the Low-Density Parity-Check matrix combined with the L1 optimization algorithm achieves the highest Quality Score, with Compression Ratio up 50%. The proposed approach also shows an excellent ability in preserving important pathological features in presence of abnormal beats. The proposed CS encoder has been hardware implemented on low-resource microcontroller and FPGA devices. When realized on a Xilinx Artix 7 XC7A12 T FPGA, such a prototype allows real-time operations to be sustained running at 1 MHz clock frequency and dissipating only 0.8nJ per sample.

关键词： Sparse matrices Electrocardiography Sensors Vectors Compressed sensing Security reconstruction algorithms Hardware Europe Bioinformatics Compressive sensing cryptosystem healthcare security IoMT physiological signals

来源：评论

学校读者我要写书评

暂无评论

Morphological and Topological Analysis of the Human Renal Arterial Tree Using μ-CT Scans of Corrosion Cast Specimens

引用

IEEE ACCESS 2025年 13卷 38014-38034页

作者： Heryan, Katarzyna Skrzat, Janusz AGH Univ Krakow Inst Comp Sci PL-30059 Krakow Poland Jagiellonian Univ Med Coll Dept Anat PL-31008 Krakow Poland

This study addresses the analysis of morphological and topological relationships within the human renal arterial tree, which have significant implications for improving clinical practices, particularly in minimally invasive renal surgeries, where detailed information on vascular supply is necessary to preserve healthy parenchyma. Recent advances in imaging technologies, coupled with increased computational power, provide unprecedented detail in anatomical assessment and enable a comprehensive analysis. The presented investigation employed mu -CT scans of corrosion cast speciments of renal arterial trees, which underwent systematic processing, including binary reconstruction, artifact removal, cavity filling, skeletonization, and conversion into directed graph representations. This approach facilitated the computation of geometrical parameters and enabled morphological and topological analyses. The results confirm the feasibility of using mu -CT imaging to investigate both global population-level trends and intra-renal tree variations. Key findings reveal no strong individual predisposition for specific branching degrees, with trifurcations and quadfurcations being notable exceptions. Additionally, a significant inverse correlation between vessel length and diameter across generations was observed. The analysis of subtrees indicated which vessels supply specific renal segments, offering valuable information for preoperative planning, particularly in tumor surgeries. Key insights into vessel branching patterns highlight their relevance for renal surgeries. These findings have direct applications in enhancing algorithms for the reconstruction, segmentation, and visualization of preoperative CT scans by leveraging insights from mu -CT based vascular analysis. Despite limitations such as datasize constraints and artifacts inherent to historical corrosion cast specimens, this study provides a proof-of-concept framework. The proposed methodology lays the foundation for lar

关键词： Data visualization Surgery Corrosion Topology Planning Image reconstruction Computed tomography Kidney Filling Injuries Renal arterial tree vascular anatomy mu-CT computed tomography (CT) renal surgeries tumor resections branching patterns vascular morphology vessel length vessel diameter directed graph representation preoperative planning segmentation reconstruction algorithms anatomical assessment renal vascular supply corrosion cast specimens

来源：评论

学校读者我要写书评

暂无评论

Iterative Approach to Reconstructing Neural Disparity Fields From Light-Field Data

IEEE TRANSACTIONS ON COMPUTATIONAL IMAGING

引用

IEEE TRANSACTIONS ON COMPUTATIONAL IMAGING 2025年 11卷 410-420页

作者： Shi, Ligen Liu, Chang Zhao, Xing Qiu, Jun Capital Normal Univ Sch Math Sci Beijing 100048 Peoples R China Beijing Informat Sci & Technol Univ Coll Comp Sci Beijing 100101 Peoples R China

This study proposes a neural disparity field (NDF) that establishes an implicit, continuous representation of scene disparity based on a neural field and an iterative approach to address the inverse problem of NDF reconstruction from light-field (LF) data. NDF enables seamless and precise characterization of disparity variations in three-dimensional scenes and can discretize disparity at any arbitrary resolution, overcoming the limitations of traditional disparity maps that are prone to sampling errors and interpolation inaccuracies. The proposed NDF network architecture utilizes hash encoding combined with multilayer perceptrons (MLPs) to capture detailed disparities in texture levels, thereby enhancing its ability to represent the geometric information of complex scenes. By leveraging the spatial-angular consistency inherent in the LF data, a differentiable forward model to generate a central view image from the LF data is developed. Based on the forward model, an optimization scheme for the inverse problem of NDF reconstruction using differentiable propagation operators is established. Furthermore, an iterative solution method is adopted to reconstruct the NDF in the optimization scheme, which does not require training datasets and applies to LF data captured by various acquisition methods. Experimental results demonstrate that the proposed method can reconstruct high-quality NDF from LF data. The high-resolution disparity can be effectively recovered by NDF, demonstrating its capability for the implicit, continuous representation of scene disparities.

关键词： Image reconstruction Imaging Depth measurement Estimation Iterative methods Inverse problems Cameras Training reconstruction algorithms Image resolution Neural disparity field disparity estimation light-field

来源：评论

学校读者我要写书评

暂无评论

Computationally Efficient Implicit Training Strategy for Unrolled Networks (IMUNNE): A Preliminary Analysis Using Accelerated Real-Time Cardiac Cine MRI

引用

IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING 2025年第1期72卷 187-197页

作者： Iakovlev, Nikolay Schiffers, Florian A. Tapia, Santiago L. Shen, Daming Hong, Kyungpyo Markl, Michael Lee, Daniel C. Katsaggelos, Aggelos K. Kim, Daniel Northwestern Univ Feinberg Sch Med Dept Radiol Chicago IL 60611 USA Northwestern Univ Dept Comp Sci Chicago IL USA Northwestern Univ Dept Elect & Comp Engn Chicago IL USA GE Healthcare Inc Chicago IL USA Northwestern Univ Feinberg Sch Med Dept Med Chicago IL USA

Objective: Highly-undersampled, dynamic MRI reconstruction, particularly in multi-coil scenarios, is a challenging inverse problem. Unrolled networks achieve state-of-the-art performance in MRI reconstruction but suffer from long training times and extensive GPU memory cost. Methods: In this work, we propose a novel training strategy for IMplicit UNrolled NEtworks (IMUNNE) for highly-undersampled, multi-coil dynamic MRI reconstruction. It formulates the MRI reconstruction problem as an implicit fixed-point equation and leverages gradient approximation for backpropagation, enabling training of deep architectures with fixed memory cost. This study represents the first application of implicit network theory in the context of real-time cine MRI. The proposed method is evaluated using a prospectively undersampled, real-time cine dataset using radial k-space sampling, comprising balanced steady-state free precession (b-SSFP) readouts. Experiments include a hyperparameter search, head-to-head comparisons with a complex U-Net (CU-Net) and an alternating unrolled network (Alt-UN), and an analysis of robustness under noise perturbations;peak signal-to-noise ratio, structural similarity index, normalized root mean-square error, spatio-temporal entropic difference, and a blur metric were used. Results: IMUNNE produced significantly and slightly better image quality compared to CU-Net and Alt-UN, respectively. Compared with Alt-UN, IMUNNE significantly reduced training and inference times, making it a promising approach for highly-accelerated, multi-coil real-time cine MRI reconstruction. Conclusion: IMUNNE strategy successfully applies unrolled networks to image reconstruction of highly-accelerated, real-time radial cine MRI. Significance: Implicit training enables rapid, high-quality, and cost-effective CMR exams by reducing training and inference times and lowering memory cost associated with advanced reconstruction methods.

关键词： Magnetic resonance imaging Image reconstruction Real-time systems Training Iterative methods Biomedical imaging reconstruction algorithms Compressed sensing deep learning image reconstruction implicit network unrolled network

来源：评论

学校读者我要写书评

暂无评论

PACformer: A Multi-Stage Heterogeneous Convolutional-Vision Transformer for Sparse-View Photoacoustic Tomography Restoration

IEEE TRANSACTIONS ON COMPUTATIONAL IMAGING

引用

IEEE TRANSACTIONS ON COMPUTATIONAL IMAGING 2025年 11卷 377-388页

作者： He, Li Chen, Ruitao Liu, Xiangyu Cao, Xu Zhu, Shouping Wang, Yihan Xidian Univ Sch Life Sci & Technol Engn Res Ctr Mol & NeuroImaging Minist Educ Xian 710126 Peoples R China Xidian Univ Xian Key Lab Intelligent Sensing & Regulat Transsc Guangzhou 510555 Peoples R China Xidian Univ Int Joint Res Ctr Adv Med Imaging & Intelligent Di Guangzhou 510555 Peoples R China Xidian Univ Guangzhou Inst Technol Innovat Ctr Adv Med Imaging & Intelligent Med Guangzhou 510555 Peoples R China

Sparse sampling of photoacoustic (PA) signals is a crucial strategy for enhancing the feasibility of photoacoustic tomography (PAT) in clinical settings by reducing system complexity and costs. However, this approach often faces significant artifacts resulting from traditional reconstruction algorithms, underscoring the urgent need for effective solutions. To address the critical challenge of balancing computational efficiency with imaging quality, we introduce PACformer-a novel hybrid model that integrates convolutional neural networks (CNNs) with multi-head self-attentions (MSAs) to improve the reconstruction of sparse-view PAT images. While conventional CNNs excel at local feature extraction, they often struggle to capture long-range dependencies inherent in continuous structures and the diverse artifact patterns present in PAT images. PACformer tackles these limitations through a dual architecture that seamlessly combines MSAs with heterogeneous convolutional layers. Since feature representations differ in size and semantics at various stages of the deep model, PACformer employs specialized blocks for shallow and deep stages. Specifically, it utilizes efficient local convolutions and windowed MSAs for high-resolution feature maps, conditional convolutions (CondConv) integrated with MSAs for advanced feature representation in deeper stages, and Scale-Modulated Convolution combined with CondConv for the bottleneck stage. Experimental results on open-source datasets demonstrate PACformer's superior performance compared to traditional and state-of-the-art networks, validated through ablation studies and attention map visualizations. By effectively modeling both local and global artifacts, PACformer establishes itself as a robust solution for sparse-view PAT reconstruction.

关键词： Visualization Convolution Computational modeling Semantics reconstruction algorithms Transformers Feature extraction Image restoration Image reconstruction Faces Deep learning image restoration photoacoustic tomography reconstruction algorithms sparse-view

来源：评论

学校读者我要写书评

暂无评论

Recognition of UAVs in Infrared Images Based on YOLOv8

引用

IEEE ACCESS 2025年 13卷 1534-1545页

作者： Zhou, Gang Liu, Xiuqi Bi, Hongliang Naval Univ Engn Sch Elect Engn Wuhan 430033 Hubei Peoples R China Wuhan Univ Sch Elect Engn Wuhan 430072 Hubei Peoples R China Wuhan Univ Sch Comp Sci Wuhan 430072 Hubei Peoples R China China Univ Min & Technol Sch Informat & Control Engn Xuzhou 221008 Jiangsu Peoples R China

With the advancement of Unmanned Aerial Vehicle (UAV) technology, there has been a notable increase in the utilization of UAVs by criminals for engaging in illegal activities, which poses significant threats to critical infrastructure and national security. Previous studies have predominantly relied on visible image recognition, which is vulnerable to variations in lighting conditions. Additionally, the performance of detection models is often hindered by the poor quality of images capturing UAV small targets. In contrast to visible light images, infrared images can capture the heat emitted by UAVs, rendering them less susceptible to fluctuations in lighting. To address the necessity for micro UAV detection in complex environments, this paper proposes an infrared image UAV detection method that employs super-resolution reconstruction through the Super-Resolution Convolutional Neural Network (SRCNN) and YOLOv8. Initially, a convolutional neural network is utilized to enhance the resolution and clarity of the infrared images. Subsequently, the YOLOv8 target detection model is applied to identify and detect UAVs. The results indicate that the average accuracy in detecting UAVs is 93.1%, which proves that it has excellent detection performance.

关键词： Autonomous aerial vehicles Accuracy Superresolution Feature extraction YOLO Image reconstruction Convolution Signal resolution reconstruction algorithms Data models UAV infrared image SRCNN YOLOv8 object detection super-resolution image recognition

来源：评论

学校读者我要写书评

暂无评论

A Physics-Assisted Deep-Learning Scheme Based on Globally Perceptive Modules for Electromagnetic Inverse Scattering Problems

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2025年 63卷

作者： Du, Changlin Pan, Jin Yang, Deqiang Hu, Jun Nie, Zaiping Chen, Yongpin Univ Elect Sci & Technol China Sch Elect Sci & Engn Chengdu 611731 Peoples R China

The multiple scattering effect is commonly present in electromagnetic (EM) scattering and can serve as a priori information to guide the solution of inverse scattering problems (ISPs). As depicted by the Green's function, the multiple scattering effect exhibits both global and local features, i.e., the interaction between subscatterers is in principle global but the coupling strength is usually large in the neighboring region and decays with distance. For solving ISPs, the convolutional layer (CL) has been proven to be highly effective as a fundamental building block in learning-based solvers. Through supervised learning, CL-based networks can predict the refined result from the pre-solution of EM parameters. However, due to the limitation of local perception capability, CL can only model the local feature of the multiple scattering effect. To remedy this, this article proposes a globally perceptive (GP) module that cascades a global self-attention layer (GSAL) and a CL to capture both global interaction and local emphasis. To show the effectiveness of the GP module, a deep-learning scheme with global perception (DLSGP) is constructed using a U-shape structure, where the pre-solution is provided by the backpropagation (BP) or domain current (DC) method. Validation results using cross-set data, noisy data, and measured data demonstrate the high accuracy, strong generalization ability, and robustness of the proposed module. The study on the global perception ability further confirms that the proposed module contains more information on the multiple scattering effect. Since this effect is common in ISPs, this fundamental module can be applied to other learning-based solvers.

关键词： Scattering Neural networks Learning systems Accuracy Vectors Iterative methods Inverse problems Electromagnetic scattering Robustness reconstruction algorithms Deep learning global self-attention globally perceptive (GP) module inverse scattering problems (ISPs) multiple scattering effect

来源：评论

学校读者我要写书评

暂无评论

Hybrid Domain Enhancement Network for Ultraclean Pure Shift Spectroscopy With Fast Acquisition

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2025年 74卷

作者： Shen, Jia Huang, Mingkai Chen, Yida Wu, Liubin Li, Hong Yang, Yu Chen, Zhong Xiamen Univ Dept Elect Sci Xiamen 361005 Peoples R China Univ Hong Kong Dept Elect & Elect Engn Hong Kong Peoples R China Jimei Univ Sch Ocean Informat Engn Xiamen 361021 Peoples R China

Pure shift technique can greatly improve the resolution of proton spectra compared to conventional nuclear magnetic resonance (NMR) spectroscopy but at the cost of longer acquisition time. To accelerate data acquisition in pure shift experiments, nonuniform sampling (NUS) is usually incorporated along with advanced data processing methods to reconstruct the spectrum. While some deep learning (DL) approaches have been proposed for this purpose, their performance declines when dealing with data under varying experimental conditions, primarily because they solely rely on frequency-domain information. To overcome this limitation, we develop a novel hybrid domain enhancement (HDE) network that combines time- and frequency-domain signals as input. We introduced an adaptive-domain transform unit (ADTU) to extract time-domain features that capture segmental correlations while retaining some temporal sequential information. Our experiments demonstrate that the proposed network effectively suppresses chunking sidebands and undersampling artifacts, showing exceptional robustness in complex scenarios, particularly under phase distortion. On real experimental data, it achieves a 5%-33% higher precision than state-of-the-art (SOTA) methods, indicating fewer artifacts in the reconstructed spectrum. This approach holds great potential for broader application in NMR spectroscopy, offering clearer and more accurate spectral interpretation.

关键词： Nuclear magnetic resonance Time-domain analysis Image reconstruction Couplings Amplitude modulation Spectroscopy Phase distortion Discrete Fourier transforms Time-frequency analysis reconstruction algorithms Chunking sideband neural network nonuniform sampling (NUS) pure shift signal reconstruction

来源：评论

学校读者我要写书评

暂无评论

Multi-Scale Channel Distillation Network for Image Compressive Sensing

引用

IEEE ACCESS 2025年 13卷 9524-9537页

作者： Zhang, Tianyu Ye, Kuntao Zhang, Yue Lu, Rui Jiangxi Univ Sci & Technol Sch Sci Ganzhou 341000 Peoples R China State Grid Xinyu Power Supply Co Elect Power Commun Dept Xinyu 338000 Peoples R China

Recently, convolutional neural networks (CNNs) have demonstrated striking success in computer vision tasks. Methods based on CNNs for image compressive sensing (CS) have also gained prominence. However, existing methods tend to increase the depth of the network in feature space for better reconstruction quality, neglecting the hierarchical representation of intermediate features in pixel space. In order to coordinate the feature space and pixel space to complete the deep reconstruction of images, and further improve the reconstruction performance of current CS methods, we propose a multi-scale channel distillation network (MSCDN). This network first obtains images of multiple scales using a scale-space image decomposition method at the sampling stage, followed by sampling these decomposed images through a convolutional operation. In this way, multi-scale information in the compressed domain is aggregated. During the reconstruction phase, a low-frequency information recovery network generates a preliminary image, whereas a high-frequency feature aggregation network refines the image further. Specifically, we design a dual-branch deep reconstruction architecture with channel distillation residual block (CDRB) as the core component. One branch extracts features gradually by cascading multiple CDRB modules, thereby supplementing the initial reconstructed image with a large amount of high-frequency content in feature space. The other branch takes the initial reconstructed image as input and sequentially fuses the intermediate feature outputs by CDRBs to increase the local details of the image in pixel space. Combining outputs from both branches, we achieve an optimal reconstructed image. Extensive experimental results on four benchmark datasets demonstrate that MSCDN surpasses state-of-the-art CS methods not only in reconstruction accuracy but also in perceptual visual quality.

关键词： Image reconstruction Feature extraction Convolution reconstruction algorithms Image coding Computational complexity Compressed sensing Training Optimization Matched filters Convolutional neural networks compressive sensing intermediate feature multi-scale image reconstruction

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：