检索结果-内蒙古大学图书馆

GLDet: Real-Time SAR Ship Detector Based on Global Semantic Information Enhancement and Local Gradient Information Mining

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND remote sensing 2025年 63卷

作者： Chang, Hao Fu, Xiongjun Lang, Ping Guo, Kunyi Dong, Jian Chang, Shibo Beijing Inst Technol Sch Integrated Circuits & Elect Beijing 100081 Peoples R China Tsinghua Univ Dept Elect Engn Beijing 100084 Peoples R China

Detecting ships in synthetic aperture radar (SAR) images is a challenging task due to various factors, such as the diverse distribution of ships and the intricate nature of SAR images. In recent years, deep learning has made excellent progress in the field of SAR interpretation. Models that focus on extracting global semantic information can effectively achieve balanced detection of multiscale SAR targets, but their computational complexity is relatively high. Models that focus on processing local information have redundant calculations and poor robustness, but are prone to mistaking the background information of SAR images for targets. To address the above issues, we propose a real-time SAR ship detector based on global semantic information enhancement and local gradient information mining. The lightweight feature extraction backbone based on linear computing is designed, with the network structure of global information augmentation encoder (GIAE), local gradient information miner (LGIM), and decoder, which can quickly perform feature extraction. GIAE enhances the expression of image content through the long-sequence modeling capability of the state-space model (SSM). LGIM uses gradient modules composed of depthwise separable convolutions to extract local information of image and utilizes directed self-attention (DSA) to mine channel context information. Global-local detector (GLDet) can complete object detection, rotated object detection, and instance segmentation tasks by transforming the detection head. Excellent performance has been achieved on the SAR ship instance segmentation datasets: SAR ship detection dataset (SSDD) and high-resolution SAR image dataset (HRSID), as well as the SAR rotated ship datasets: rotated ship detection dataset (RSDD)-SAR and SSDD+. Meanwhile, GLDet demonstrated excellent generalization performance in large-scale SAR images captured by GF-3 and Terra-SAR satellites.

关键词： Marine vehicles Feature extraction radar polarimetry synthetic aperture radar Computational modeling Transformers Instance segmentation Data mining Object detection Scattering lightweight network multitask learning real-time detection rotated object detection ship detection synthetic aperture radar (SAR)

来源：评论

学校读者我要写书评

暂无评论

Systematical Error Estimation and Compensation for Ultra-Wideband Microwave Photonic SAR Based on the Coarse-Focused image

引用

IEEE Transactions on Geoscience and remote sensing 2025年 63卷

作者： Chen, Min Qiu, Xiaolan Cheng, Yao Li, Ruoming Chinese Academy of Sciences National Key Laboratory of Microwave Imaging Aerospace Information Research Institute Beijing100190 China University of Chinese Academy of Sciences School of Electronic Electrical and Communication Engineering Beijing100049 China Suzhou Key Laboratory of Microwave Imaging Processing and Application Technology Suzhou215123 China Suzhou Aerospace Information Research Institute Suzhou215123 China

The combination of microwave photonic (MWP) technology and synthetic aperture radar (SAR) facilitates the generation, transmission, and reception of ultra-wideband (UWB) signals, thereby enabling the production of centimeter-resolution SAR images. Recently, an experimental MWP SAR system with a bandwidth of 14 GHz has been constructed at Aerospace Information Research Institute, Chinese Academy of Sciences, which has been tested by outfield SAR experiments. In the context of this system, we analyzed the manifestation of systematical errors in the coarse-focused image and found that deviations occur in both the envelope and the phase of the range cell migration (RCM) curves, which can be considered as inherent slant range error and center frequency error. In addition, the inclusion of a radio frequency power amplifier (PA) in this system can introduce frequency-dependent error. In this article, we analyze the sources and establish signal models for the above three types of systematical errors individually and propose a systematical error estimation method by exploiting the trihedral reflectors (TRCs) within the coarse-focused image. Utilizing the error estimation results and the measured frequency response of the PA, a post-processing compensation method is also proposed. The estimation and compensation method is applied to the processing of the vehicle-borne data acquired by this experimental MWP SAR system, yielding superior performance and a fine-focused SAR image with a resolution of approximately 0.013 m in the range dimension. © 1980-2012 IEEE.

关键词： Systematic errors

来源：评论

学校读者我要写书评

暂无评论

Proceedings of SPIE - image processing, signal processing, and synthetic aperture radar I for remote Sensina

Proceedings of SPIE - Image Processing, Signal Processing, a...

引用

image processing, signal processing, and synthetic aperture radar for remote sensing

The proceedings contain 47 papers. The topics discussed include: the scale representation of signals;simulation of low resolution SAR image products;vector quantization of raw polarimetric SAR data by using their statistical properties;local residue coupling strategies by neural network for InSAR phase unwrapping;polarimetric SAR data classification using scattering models and neural networks;parallel computing implementation for ScanSAR mode data;two dimensional processing for airborne synthetic aperture radar;systolic arrays for 2D digital filters;new parallel multiplier design;robust algorithms for phase unwrapping in SAR interferometry;automatic extraction of cartographic information from airborne interferometric SAR data;possitivity and support: a comparison;2D FIR filters implementation using radix-differential arithmetic;and an automated registration method to correspond control points with sub-pixel accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

High Resolution Millimeter Wave Imaging Based on FMCW radar Systems at W-Band

High Resolution Millimeter Wave Imaging Based on FMCW Radar ...

引用

IEEE Annual Computing and Communication Workshop and conference (CCWC)

作者： Shahrokh Hamidi MR Nezhad-Ahmadi Department of Electrical and Computer Engineering University of Waterloo Canada MMSENSE Technologies Inc. Waterloo Canada

ISBN: (数字)9798331507695

ISBN: (纸本)9798331507701

In this paper, we present a unique 2D high resolution, compact, low-cost, lightweight, and highly accurate millimeter-wave imagery system capable of operating in all weather conditions. We explain different aspects of the imagery system in detail and describe the process of millimeter-wave image formation thoroughly. To create the array, we utilize the synthetic aperture radar (SAR) concept. The imagery system presented in this paper, can strongly compete with the Lidar systems as the resolution limit is at the same level. Furthermore, in contrast to the Lidar systems, our imagery system can operate in heavy rain as well as dense fog and produce high quality images. Finally, we utilize our wide-band custom-made Frequency Modulated Continuous Wave (FMCW) radar, which operates at W-band with 33 GHz bandwidth, for data collection and present the results.

关键词： image resolution Laser radar Frequency modulation Imaging signal processing algorithms Millimeter wave radar radar imaging Millimeter wave communication synthetic aperture radar signal resolution

来源：评论

学校读者我要写书评

暂无评论

Monitoring of High-Speed Railway Ground Deformation Using Interferometric synthetic aperture radar image Analysis

引用

APPLIED SCIENCES-BASEL 2025年第8期15卷 4318-4318页

作者： Lee, Seung-Jun Yun, Hong-Sik Kim, Tae-Yun Sungkyunkwan Univ SKKU Dept Civil Architectural & Environm Syst Engn Geodesy Lab Suwon 16419 Gyeonggi Do South Korea

Ground subsidence is a critical factor affecting the structural integrity and operational safety of high-speed railways, especially in areas with widespread soft ground. This study applies Persistent Scatterer Interferometric synthetic aperture radar (PS-InSAR) techniques to monitor ground deformation along the Honam High-Speed Railway in South Korea. By processing a time series of 29 high-resolution SAR images from 2016 to 2019, the analysis yielded continuous, millimeter-level measurements of surface displacement. Maximum subsidence rates exceeding -12 mm/year were detected in embankment zones with soft subsoil conditions Validation using leveling data and corner reflectors showed strong agreement (R-2 > 0.93), confirming the accuracy and reliability of PS-InSAR-derived results. The study also revealed seasonal variation in settlement patterns, highlighting the influence of rainfall and pore water pressure. The findings underscore the utility of PS-InSAR as a sustainable and cost-effective tool for long-term infrastructure monitoring. This study further contributes to the development of predictive maintenance strategies and highlights the need for future research integrating PS-InSAR with geotechnical, hydrological, and construction-related variables to enhance monitoring precision and expand its practical applicability in infrastructure management.

关键词： high-speed railway ground subsidence persistent scatterer interferometric synthetic aperture radar (PS-InSAR) satellite remote sensing ground deformation monitoring

来源：评论

学校读者我要写书评

暂无评论

Three-Dimensional Reconstruction of Target Based on Phase-Derived Technology

引用

IEEE Transactions on Geoscience and remote sensing 2025年 63卷

作者： Hou, Kaifu Fan, Huayu Liu, Quanhua Ren, Lixiang Mao, Erke Beijing Institute of Technology School of Information and Electronics Key Laboratory of Electronic and Information Technology in Satellite Navigation Ministry of Education Beijing100081 China Beijing Institute of Technology School of Information and Electronics Beijing100081 China Beijing Institute of Technology Jiaxing314033 China Beijing Institute of Technology Chongqing Innovation Center Chongqing401135 China

Three-dimensional images can accurately reflect the target's posture and structure, providing rich feature information for spatial target recognition. However, challenges arise in image registration and phase reconstruction for interferometric inverse synthetic aperture radar (InISAR) 3-D imaging when observation perspectives significantly differ, the target size is relatively large, or the squint model is present. Therefore, we propose a target 3-D reconstruction method based on phase-derived technology. For the issue of image distortion misregistration caused by differing observation perspectives, we propose transforming the traditional image registration problem into a multiscatterer association problem by extracting target scatterer information from inverse synthetic aperture radar (ISAR) 2-D images and using the iterative closest point (ICP) algorithm to achieve scatterer association between different ISAR images. To tackle the interference phase ambiguity problem caused by large target size or squint model in InISAR 3-D imaging, we propose transforming the 3-D reconstruction problem into a 3-D positioning problem for each scatterer and achieving 3-D reconstruction through a 3-D positioning method based on phase-derived angle measurement (PDAM) and phase-derived range measurement (PDRM). In cases where the extracted scatterers are generally nonideal, the nonideal scatterers can be treated as a whole, and cross correlation processing can be performed between different antennas to extract the interferometric phase. Both simulation and measured data have verified the effectiveness of the proposed method. © 1980-2012 IEEE.

关键词： radar imaging

来源：评论

学校读者我要写书评

暂无评论

A Review of Spaceborne High-Resolution Spotlight/Sliding Spotlight Mode SAR Imaging

引用

remote sensing 2025年第1期17卷 38-38页

作者： Wu, Baolong Liu, Chengjin Chen, Jianlai Northwestern Polytech Univ Sch Elect & Informat Xian 710072 Peoples R China Cent South Univ Sch Automat Changsha 410083 Peoples R China

Spotlight/sliding spotlight modes can achieve higher resolution than the other imaging modes and are widely used in object detection and recognition applications. This paper reviews the progress of the spaceborne spotlight/sliding spotlight SAR imaging field. The three steps of the current spaceborne spotlight/sliding spotlight SAR imaging algorithm framework are discussed in this paper. These include the following: eliminating the azimuth spectral aliasing by azimuth deramp preprocessing;implementing imaging processing using imaging kernels (RD, CS, RMA, etc.);and degrading the back-folded phenomenon in the final focused image domain by reference function multiplication post-processing. The different imaging kernels, consisting of RD, CS, RMA, BAS, FS, and PFA, are presented. The phase errors in high-resolution spaceborne spotlight/sliding spotlight SAR imaging, especially the stop-and-go error, curved orbit error, and tropospheric delay error, are analyzed in detail. Furthermore, the autofocus methods are described. In addition, some new imaging SAR systems based on spotlight/sliding spotlight SAR mode, which have more advantages than the classic spaceborne spotlight/sliding spotlight SAR imaging, were shown in this paper. These include FMCW-based systems, multichannel systems, varying-PRF systems, and bistatic systems.

关键词： synthetic aperture radar spaceborne high-resolution SAR spotlight SAR sliding spotlight SAR

来源：评论

学校读者我要写书评

暂无评论

Divide-and-Conquer Variational Bayesian Inference for Multi-task Learning of High-resolution SAR imagery

Divide-and-Conquer Variational Bayesian Inference for Multi-...

引用

International conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Lei Yang Ming Sun Zhongwei Hu Zenan Zhang Wenxuan Yuan College of Electronic Information and Automation Civil Aviation University of China Tianjin China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Conventional statistical-driven synthetic aperture radar (SAR) imaging algorithms can only encode a single and/or static prior, leading to that limited features can be accessed quantitatively. To this end, a novel multi-task learning framework is proposed by devising a divide-and-conquer variational Bayesian (DC-VB) inference, so that elaborated features of interests can be exploited for a high-resolution SAR imagery. Specifically, a flexible generalized Gaussian distribution (GGD) and a customized hybrid probability distribution are introduced and employed for the priors of features of interests. To resolve the resultant complicated Bayesian inference, splitted random variables are incorporated, so that the joint posterior problem can be decomposed into multiple local problems that are easy to be solved. Simultaneously, dual variables are established for residual errors of the decomposition. To guarantee a global solution for the image of the target of interests, the data augmentation is employed to coordinate multiple local solutions. Therefore, the intended Bayesian inference works in a divide-and-conquer manner, which is superior in quantization of multiple features of high-resolution SAR imagery. It is capable of incorporating multiple priors in a fully-statistical probability and guaranteeing closed-form solutions of posterior distributions. Unavoidable propagation errors can be minimized in the DC-VB process. Raw SAR data is applied to validate the effectiveness of the proposed algorithm. Comparisons with conventions show the superiority in terms of qualitative and quantitative aspects.

关键词： Quantization (signal) Closed-form solutions signal processing algorithms Multitasking Data augmentation radar polarimetry Inference algorithms Bayes methods Speech processing synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

An Overview on Millimeterwave FMCW radar Techniques for Precise Ranging and Material Imaging

An Overview on Millimeterwave FMCW Radar Techniques for Prec...

引用

International Workshop on Mobile Terahertz Systems (IWMTS)

作者： Kristof Dausien Francesca Schenkel Jochen Altholz Lukas Piotrowsky Nils Pohl Jan Barowski Institute for Microwave Systems Ruhr University Bochum Bochum Germany Institute for Integrated Systems Ruhr University Bochum Bochum Germany

ISBN: (数字)9798350365832

ISBN: (纸本)9798350365849

This scientific paper is an outcome of the MARIE project (for more information, see ***) [M04]. This paper provides an overview, on recent developments as well as future challenges and prospects in measurement methods and algorithms for the determination of an object’s geometrical shape, its position, and its electromagnetic properties using FMCW radar sensors. The current research integrates radar imaging techniques with material characterization algorithms to evaluate the dielectric constant and losses, leveraging ultrawideband systems to capture dispersive features and enable µm-precise localization. Unlike single antenna synthetic aperture radar (SAR) methods, multiple-input multiple-output (MIMO) radar enhances imaging by capturing data from multiple channels and varying incident angles, enriching the information obtained. In conjunction with sensor calibration methods and radar-based material characterization, these imaging techniques provide a mobile platform for spatially resolved, precise reflection measurements in magnitude and phase that are used to derive the electromagnetic properties and, subsequently, to provide a semantically annotated material image. Due to the short wavelength and large apertures near-field wave propagation effects must be incorporated into the signal processing to achieve µm-precise ranging and imaging. Furthermore, the impact of environmental influences on the measurement accuracy must be investigated.

关键词： image sensors Accuracy Wavelength measurement signal processing algorithms radar imaging Sensor phenomena and characterization radar antennas Distance measurement Ultra wideband radar synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

Quanv4EO: Empowering Earth Observation by Means of Quanvolutional Neural Networks

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND remote sensing 2025年 63卷

作者： Sebastianelli, Alessandro Mauro, Francesco Ciabatti, Giulia Spiller, Dario Le Saux, Bertrand Gamba, Paolo Liberata Ullo, Silvia European Space Agcy Lab I-00044 Frascati Italy Univ Sannio Dept Engn I-82100 Benevento Italy Sapienza Univ Rome Dept Comp Control & Management Engn I-00185 Rome Italy Sapienza Univ Rome Sch Aerosp Engn I-00185 Rome Italy AI4EARTH Toulouse France Univ Pavia Dept Elect Comp & Biomed Engn I-27100 Pavia Italy

A significant amount of remotely sensed data is generated daily by many Earth observation (EO) spaceborne and airborne sensors over different countries of our planet. Different applications use those data, such as natural hazard monitoring, global climate change, urban planning, and more. Many challenges are brought by the use of these big data in the context of remote sensing (RS) applications. In recent years, the employment of machine learning (ML) and deep learning (DL)-based algorithms has allowed a more efficient use of these data, but the issues in managing, processing, and efficiently exploiting them have even increased as classical computers have reached their limits. This article highlights a significant shift toward leveraging quantum computing (QC) techniques in processing large volumes of RS data. The proposed Quanv4EO framework introduces a quanvolution method for (pre)processing multidimensional EO data. Its effectiveness was first demonstrated on standard image classification datasets (MNIST and FashionMNIST), achieving accuracies of 99.84% and 96.81%, respectively, with a significantly reduced model size of 42 k parameters and 16 frozen qubits. Its capabilities were then checked on EO datasets, such as EuroSAT, with a mean accuracy of 96% using balanced iterative reducing and clustering using hierarchies (BIRCHs) clustering and 93% using automated DL (AutoDL), surpassing or matching state-of-the-art (SOTA) classical nonquantum models. Applying the framework to synthetic aperture radar (SAR) data, the QSPeckleFilter demonstrates notable improvements in speckle noise reduction, achieving a peak signal-to-noise ratio (PSNR) of 21.72 and a structural similarity index measure (SSIM) of 0.81, surpassing all tested classical counterparts. The proposed results underscore the potential of quantum-enhanced approaches in RS data analysis, paving the way for more efficient and effective solutions for wide geographical area EO data exploitation.

关键词： Feature extraction Quantum computing Quantum circuit Filters Qubit Integrated circuit modeling remote sensing Data mining Climate change Deep learning Convolutional neural networks Earth Observing System Earth observation (EO) quantum computing (QC) quantum convolutional neural networks (CNNs) quantum deep learning (DL) remote sensing (RS)

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：