检索结果-内蒙古大学图书馆

Defect super-resolution algorithm based on infrared thermal imaging physical kernel

NDT & E INTERNATIONAL 2025年 154卷

作者： Wu, Shunyao Gao, Bin Woo, Wai Lok Yu, Yongjie Yang, Yang Univ Elect Sci & Technol China Sch Automat Engn Chengdu Peoples R China Northumbria Univ Dept Comp & Informat Sci Newcastle Upon Tyne England Chengdu Aircraft Ind Grp Co Ltd Chengdu Peoples R China

Infrared thermal imaging technology has been adopted for its advantages such as fast detection response, noncontact testing, and applicability to various objects. When testing a target object, this technology presents temperature distribution information of the target object's surface in the form of an image, achieving visualization. However, due to limitations in the hardware system of the thermal imager and the noise generated during the detection process, the resolution of infrared images is relatively low, and the details of the image are not rich enough, leading to limitations in specific defect detection. In this study, a defect super-resolution algorithm based on infrared thermal imaging physical kernel is proposed. The imaging degradation factors of the infrared images are analyzed, and the modulation transfer function of the infrared thermal imaging system is used as the physical prior to generate the underlying blur kernel of the infrared images. The infrared images are then reconstructed using a super-resolution algorithm based on the blur kernel. Obtained experimental results have demonstrated that the proposed method significantly improves the defect detection rate and the overall image quality. The demo code will be updated soon in https://***/gaobin/zh_CN/lwcg/153392/list/***.

关键词： Infrared thermal imaging Defect detection super-resolution algorithm Physical kernel

来源：评论

学校读者我要写书评

暂无评论

A super-resolution algorithm Based on Beam Improvement for Angle Estimation in Multipath Environments 11

A Super-resolution Algorithm Based on Beam Improvement for A...

引用

11th IEEE Asia-Pacific Conference on Antennas and Propagation, APCAP 2023 - Proceedings

作者： Tian, Zengshan Li, Junjie Huang, Chenglin Liu, Kaikai Gui, Shuliang Chongqing University of Posts and Telecommunications School of Communications and Information Engineering Chongqing400065 China

ISBN: (纸本)9798350326277

With the integrated sensing and communications (ISAC) proposed and the development of the internet of things (IoT), indoor localization and sensing have become a hot spot of current research. Most of these researches directly use super-resolution algorithms to extract signal parameters to accomplish localization and sensing. Although high accuracy can be achieved, the real-time performance of these algorithms may have some problems due to the high computational complexity. Therefore, this paper proposes a super-resolution algorithm based on beam improvement (SRBI) for angle estimation in multipath environments, which first utilizes beams based methods for coarse angle estimates, and then the coarse estimates as an initialization is used to maximize the convergence rate of the super-resolution algorithm. The experimental results show that the accuracy after using beam improvement is comparable to the original accuracy, but it runs almost 119% faster than the latter. © 2023 IEEE.

关键词： Angle estimation Multipath super-resolution algorithm

来源：评论

学校读者我要写书评

暂无评论

Constructing Large Transmission Matrix of Scattering Sample Based on super-resolution algorithm

引用

IEEE ACCESS 2021年 9卷 55497-55505页

作者： Zhou, Shenghang Sui, Xiubao Xie, Hao Chen, Qian Gu, Guohua Nanjing Univ Sci & Technol Jiangsu Lab Spectral Imaging & Intelligence Sense Nanjing 210094 Peoples R China

A method to construct a large transmission matrix (TM) of highly scattering media based on an algorithm is presented. For imaging through scattering media, measuring a large TM enables image reconstruction with high spatial resolution;however, it is difficult to operate in practice because the time required for the calibration of the TM is proportional to the number of calibrated input modes. Instead of directly achieving calibration using advanced hardware, a large TM is defined and constructed based on a multiframe image super-resolution algorithm, which traditionally aims to recover a high-resolution (HR) image of the original object from several low-resolution images. With sufficient size improvement, the defined large TM is constructed from several naturally measured complementary small TMs, each of them is measured using a subpixel-shifted projector phase mask. The realized large TM, which is constructed through subpixel registration and interpolation operations at the help of a hypothetical HR mask, enables HR image reconstruction from the original object's speckle signal. The feasibility of the proposed method is proven via optical experiments involving statistical analysis and image reconstruction. The proposed method benefits existing TM-based image reconstruction applications and offers a new perspective on the size of TM measurements and the imaging resolution.

关键词： Scattering Image reconstruction Image resolution Speckle Optical imaging Charge coupled devices Phase measurement Scattering media transmission matrix image reconstruction super-resolution algorithm

来源：评论

学校读者我要写书评

暂无评论

RETRACTED: Application of single frame image super-resolution algorithm based on generative adversarial network in tennis motion image resolution (Retracted Article)

引用

JOURNAL OF AMBIENT INTELLIGENCE AND HUMANIZED COMPUTING 2021年第1-Sup期13卷 131-131页

作者： Hu, Ruizhe Cui, Xiaocan Zhengzhou Univ Sch Phys Educ Main Campus Zhengzhou 450001 Henan Peoples R China

Researchers who have successfully applied convolutional neural networks in the field of computer vision have developed a series of image super-resolution algorithms based on convolutional neural networks. In this way, the effect of image reconstruction is greatly improved. The existing image super-resolution algorithm realizes the ideal mathematical modeling of the image degradation process, and obtains a low-resolution image through a properly modeled degradation process. Then, a pair of high-resolution images and low-resolution images is used for surveillance-related training. As an effective software processing technology, image super-resolution reconstruction can break the physical boundaries of image equipment and improve the spatial resolution of the acquired image. This thesis focuses on the research of image emphasis and super-resolution reconstruction based on space animation, especially the image processing of the position and docking of spacecraft. Aiming at the characteristics of spatial moving images and the problems of application programs such as edge patterns, noise effects, and real-time processing, the algorithm is studied. We propose an image enhancement and super-resolution reconstruction algorithm based on multi-scale conversion. This research and design method once again realizes the image design and reconstruction.

关键词： Confrontation network Single frame image super-resolution algorithm Tennis

来源：评论

学校读者我要写书评

暂无评论

Terahertz super-resolution Nondestructive Detection algorithm Based on Edge Feature Convolution Network

引用

IEEE ACCESS 2023年 11卷 2721-2728页

作者： Hu, Cong Quan, Hui Wu, Xiangdong Li, Ting Zhou, Tian Guilin Univ Elect Technol Sch Elect Engn & Automat Guilin 541004 Peoples R China Chinese Acad Sci Shenzhen Inst Adv Technol Shenzhen 518055 Peoples R China Guilin Univ Aerosp Technol Sch Elect Informat & Automat Guilin 541004 Guangxi Peoples R China Shenzhen Engn Lab Single Mol Detect & Instrument D Shenzhen 518055 Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China

Much research has been conducted to improve the defect-detection rate and detection accuracy of the imaging technology used in terahertz nondestructive testing. Due to the power limit of light sources and noise interference in terahertz equipment, images have low resolution and fuzzy defect edges. Hence, improving the resolution is crucial for detecting defects. We designed an edge detection network structure based on a traditional deep neural network. Besides, we devised a node-fusing strategy to train the network. It demonstrates significant improvement of the resolution of the terahertz defect contour. A quartz fiber composites with embedded defects was tested with our network. The results showed that the proposed super-resolution reconstruction algorithm improves resolution, particularly on the edges of defect contours.

关键词： Terahertz wave imaging Feature extraction Convolution Image edge detection Training Circuit breakers superresolution Composite materials deep neural network nondestructive testing super-resolution algorithm terahertz imaging

来源：评论

学校读者我要写书评

暂无评论

A multi-antenna super-resolution passive Wi-Fi radar algorithm: Combined model order selection and parameter estimation

引用

IET RADAR SONAR AND NAVIGATION 2022年第8期16卷 1376-1387页

作者： Yildirim, Hasan Can Storrer, Laurent De Doncker, Philippe Louveaux, Jerome Horlin, Francois Univ Libre Bruxelles OPERA WCG Brussels Belgium Catholic Univ Louvain ICTM ELEN Louvain La Neuve Belgium

In recent years, Wi-Fi has become the main gateway that connects users to the Internet. Considering the availability of Wi-Fi signals, and their suitability for channel estimation, IEEE established the Wi-Fi Sensing (WS) Task Group whose purpose is to study the feasibility of Wi-Fi-based environment sensing. However, Wi-Fi signals are transmitted over limited bandwidths with a relatively small number of antennas in bursts, fundamentally limiting the range, Angle-of-Arrival and speed resolutions. This paper presents a super-resolution algorithm to perform the parameter estimation in a quasi-monostatic WS scenario. The proposed algorithm, RIVES, estimates the range, Angle-of-Arrival and speed parameters with Vandermonde decomposition of Hankel matrices. To estimate the size of the signal subspace, RIVES uses a novel Model Order Selection method which eliminates spurious noise targets based on their distance to the noise and signal subspaces. Various scenarios with multiple targets are simulated to show the robustness of RIVES. In order to prove its accuracy, real-life indoor experiments are conducted with human targets by using Software Defined Radios.

关键词： speed resolutions Wi-Fi signals Model Order Selection method signal subspaces RIVES parameter estimation speed parameters quasimonostatic WS scenario Hankel matrices passive radar multiantenna super-resolution passive Wi-Fi radar algorithm radar antennas software radio Wi-Fi-based environment sensing radar resolution signal subspace super-resolution algorithm channel estimation wireless LAN direction-of-arrival estimation

来源：评论

学校读者我要写书评

暂无评论

Geometric Reliability of super-resolution Reconstructed Images from Clinical Fetal MRI in the Second Trimester

引用

NEUROINFORMATICS 2023年第3期21卷 549-563页

作者： Ciceri, Tommaso Squarcina, Letizia Pigoni, Alessandro Ferro, Adele Montano, Florian Bertoldo, Alessandra Persico, Nicola Boito, Simona Triulzi, Fabio Maria Conte, Giorgio Brambilla, Paolo Peruzzo, Denis Sci Inst IRCCS Eugenio Medea NeuroImaging Lab Bosisio Parini Italy Univ Padua Dept Informat Engn Padua Italy Univ Milan Dept Pathophysiol & Transplantat Milan Italy IMT Sch Adv Studies Lucca Social & Affect Neurosci Grp Lucca Italy Fdn IRCCS Ca Granda Osped Maggiore Policlin Dept Neurosci & Mental Hlth Milan Italy Fdn IRCCS Ca Granda Osped Maggiore Policlin Dept Woman Child & Newborn Milan Italy Fdn IRCCS Ca Granda Osped Maggiore Policlin Dept Serv & Prevent Med Milan Italy Univ Padua Padova Neurosci Ctr Padua Italy

Fetal Magnetic Resonance Imaging (MRI) is an important noninvasive diagnostic tool to characterize the central nervous system (CNS) development, significantly contributing to pregnancy management. In clinical practice, fetal MRI of the brain includes the acquisition of fast anatomical sequences over different planes on which several biometric measurements are manually extracted. Recently, modern toolkits use the acquired two-dimensional (2D) images to reconstruct a super-resolution (SR) isotropic volume of the brain, enabling three-dimensional (3D) analysis of the fetal *** analyzed 17 fetal MR exams performed in the second trimester, including orthogonal T2-weighted (T2w) Turbo Spin Echo (TSE) and balanced Fast Field Echo (b-FFE) sequences. For each subject and type of sequence, three distinct high-resolution volumes were reconstructed via NiftyMIC, MIALSRTK, and SVRTK toolkits. Fifteen biometric measurements were assessed both on the acquired 2D images and SR reconstructed volumes, and compared using Passing-Bablok regression, Bland-Altman plot analysis, and statistical *** indicate that NiftyMIC and MIALSRTK provide reliable SR reconstructed volumes, suitable for biometric assessments. NiftyMIC also improves the operator intraclass correlation coefficient on the quantitative biometric measures with respect to the acquired 2D images. In addition, TSE sequences lead to more robust fetal brain reconstructions against intensity artifacts compared to b-FFE sequences, despite the latter exhibiting more defined anatomical *** findings strengthen the adoption of automatic toolkits for fetal brain reconstructions to perform biometry evaluations of fetal brain development over common clinical MR at an early pregnancy stage.

关键词： Fetal brain Magnetic Resonance Imaging super-resolution algorithm Fetal biometry Pediatric Imaging

来源：评论

学校读者我要写书评

暂无评论

super-resolution Localization and Tracking in WiFi Sensing 33

Super-resolution Localization and Tracking in WiFi Sensing

引用

33rd IEEE International Conference on Computer Communications and Networks (ICCCN)

作者： Wang, Jian Chuang, Jack Sempert, Sebastian Golmie, Nada NIST Wireless Networks Div Gaithersburg MD 20899 USA Tech Univ Ilmenau Inst Informat Technol Ilmenau Germany

ISBN: (纸本)9798350348439;9798350384611

Integrated sensing and communication (ISAC) systems have been investigated by the research and standardization communities in the recent past. Accurately localizing the target and tracking the target's movement are critical for numerous smart Internet of Things (IoT) systems (smart manufacturing, smart transportation, etc.). This paper aims to realize super-resolution localization and tracking in WiFi sensing by leveraging the IEEE 802.11ad beamforming training procedure. We leverage the CLEAN-Space-Alternating Generalized Expectation-maximization (CLEAN-SAGE) algorithm on a single beam sweeping cycle for target localization and investigate the targets' delays and angle estimation. For tracking moving targets, we design mechanisms to estimate the target's motion, including the target's velocity and motion pattern, such as estimating the target's spatial positions over time to obtain the Doppler shift or tracking its trajectory using a Kalman filter. In order to prove that our approach works effectively, we conduct a thorough performance evaluation study. Our evaluation results confirm that the CLEAN-SAGE algorithm can achieve estimation performance beyond the ISAC system's inherent bandwidth and beamwidth constraints. Furthermore, we provide insights into how system configurations, including antenna size, beam overlap, and the number of iterations in the SAGE algorithm, influence its performance.

关键词： Edge processing IoT applications mmWave CLEAN and SAGE WiFi sensing super-resolution algorithm Localization and tracking

来源：评论

学校读者我要写书评

暂无评论

Improving the Ability of Measuring the Thickness of Thin Oil Slick With Ultrasound Using the Sparse Optimization Method

引用

IEEE SENSORS JOURNAL 2024年第21期24卷 35374-35385页

作者： Yao, Di Du, HuaLong Li, Shuo Zhang, QiFeng Northeastern Univ Sch Comp Sci & Engn Shenyang 110819 Peoples R China Chinese Acad Sci Shenyang Inst Automat State Key Lab Robot Shenyang 110169 Peoples R China Chinese Acad Sci Inst Robot & Intelligent Mfg Shenyang 110169 Peoples R China

During oil spills, using ultrasound to measure the thickness of thick oil slick can provide critical information for determining the oil spill response strategy and improving the response efficiency. However, the ultrasonic measuring ability is strictly limited by the wavelength of ultrasound. To expand the ability to measure a thin oil slick thickness, a super-resolution algorithm based on a generalization of the sparse iterative covariance estimation (SPICE) algorithm was proposed to calculate the time of flight (TOF) by processing ultrasonic data collected with two transducers installed on a remotely operated vehicle (ROV). First, the cross correlation of ultrasonic signals was performed to improve the signal-to-noise ratio (SNR). Then, the outputs were processed with the inverse discrete Fourier transform (IDFT) to directly generate snapshot samples. At last, a sparse iterative covariance-based algorithm taking account of the signal sparseness was developed to deal with snapshot samples to achieve the TOF. The simulations were conducted to compare the proposed method with the generalized cross correlation (GCC) method and the modified orthogonal matching pursuit (MOMP) method. The experimental results show that the proposed method can significantly improve the ability to measure thin oil slick thickness by almost halving the minimum measurable thickness with superior measurement accuracy in comparison to the GCC method. It could be applied to measure the thickness of an oil slick during an oil spill response.

关键词： Reduce the minimum measurable thickness of an oil slick sparse signal reconstruction super-resolution algorithm ultrasonic measurement

来源：评论

学校读者我要写书评

暂无评论

Deep-Learning-Based Wireless Human Motion Tracking for Mobile Ship Environments

引用

IEEE INTERNET OF THINGS JOURNAL 2022年第23期9卷 24186-24198页

作者： Liu, Kezhong Yang, Wen Chen, Mozi Zheng, Kai Zeng, Xuming Zhang, Shengkai Liu, Cong Wuhan Univ Technol Sch Nav Natl Engn Res Ctr Water Transport Safety Wuhan 430063 Peoples R China Wuhan Univ Technol Hubei Key Lab Inland Shipping Technol Wuhan 430063 Peoples R China Wuhan Univ Technol Sch Nav Wuhan 430063 Peoples R China Wuhan Univ Technol Sch Informat Engn Wuhan 430063 Peoples R China Univ Calif Riverside Dept Elect & Comp Engn Riverside CA 92521 USA

Being able to track passengers' movement without invasion of their privacy plays an important role in cruise ships;it enables crucial location-based services, such as maritime search and rescue, tourist services, and epidemic prevention. The past few years have witnessed commodity WiFi holding great potential that provides such services available thanks to its ubiquitous in indoor scenarios. However, existing WiFi-based tracking methods suffer from huge performance degradation in sailing ships due to their complex metal structures and dynamic hull deformation caused by engines and waves/payloads pressure. In this article, we present CRLoc, a deep learning-based passive human tracking system that can overcome the practical limitations of traditional WiFi-based localization approaches applied in a multipath-rich and mobile ship environment, and provide decimeter-level tracking accuracy in cruise ships. Specifically, we make two contributions, i.e., we propose a super-resolution parameter estimation algorithm that better characterizes ship indoor environments, and a deep neural network-based end-to-end solution to remove the impact of noise, interference, and mobility in ships. The real-world implementation and extensive experiments in several passenger ships demonstrate that CRLoc tracks human motions with a median error of 92 cm, better than state-of-the-art localization methods. To our knowledge, this is one of the first WiFi-based passive human motion tracking system in a cruise ship environment.

关键词： Convolutional recurrent neural network (CRNN) mobile ship environment super-resolution algorithm WiFi localization

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：