检索结果-内蒙古大学图书馆

A Lightweight Network for Ship Detection in SAR images Based on Edge Feature Aware and Fusion

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND remote sensing 2025年 18卷 3782-3796页

作者： Li, Yuming Liu, Jin Li, Xingye Zhang, Xiliang Wu, Zhongdai Han, Bing Shanghai Maritime Univ Coll Informat Engn Shanghai 201306 Peoples R China Shanghai Ship & Shipping Res Inst Co Ltd Shanghai 200135 Peoples R China

Recently, with the increasing adoption of synthetic aperture radar (SAR) ship detection methods on mobile platforms, the lightweighting of detection methods has become a research focus. Despite certain achievements, there are still several limitations: 1) Existing studies have mainly focused on reducing model complexity through shallow network structures. However, this approach frequently results in performance degradation, as they neglected a thorough investigation into achieving a better balance point between inference speed and detection accuracy. 2) Under the lightweight network structure, the rich edge features contained in SAR images, which are crucial for distinguishing ship targets from complex backgrounds, are often underutilized. To address these issues, we propose a novel lightweight detection method based on edge feature aware and fusion. Specifically, to effectively extract edge feature, we introduce an Edge Feature-Aware (EFA) network that incorporates a multiscale channel attention module. Furthermore, a lightweight feature fusion network, Filter-Pruned Bi-directional Feature Pyramid Network (FP-BiFPN), is carefully designed, which can not only suppresses background information, but also accentuates ship targets. Finally, we propose a selective quantization algorithm based on a bit-width selection mechanism to reduce model memory usage without compromising performance. To validate the superiority of our proposed method, we conduct extensive experiments on multiple public datasets, achieving average accuracy scores of 94.2%, 97.6%, and 97.7% on the HRSID, SAR-Ship-Dataset, and SSDD, respectively, with a model parameter size of only 3.36 M, and the fastest processing time for a single frame is 7.2 ms.

关键词： Marine vehicles Feature extraction image edge detection radar polarimetry Accuracy Quantization (signal) synthetic aperture radar Computational complexity Adaptation models Inference algorithms Deep learning lightweight network ship detection synthetic aperture radar (SAR)

来源：评论

学校读者我要写书评

暂无评论

A Joint Suppression Method of Scalloping and Inter-Scan Banding for SAR images

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND remote sensing 2025年 18卷 6681-6693页

作者： An, Xinwei Yang, Wei Shen, Haijun Zeng, Hongcheng Zou, Fei Deng, Jiadong Su, Can Liu, Wei Beihang Univ Sch Elect & Informat Engn Beijing 100191 Peoples R China Shanghai Inst Satellite Engn Shanghai 200240 Peoples R China Beijing Inst Remote Sensing Informat Beijing 100192 Peoples R China Hong Kong Polytech Univ Dept Elect & Elect Engn Hong Kong Peoples R China

Due to a wide swath at the order of hundreds of kilometres, interscan banding (ISB) may occur in both ScanSAR and TOPS modes of a synthetic aperture radar (SAR), leading to degraded image quality. In this aticle, the causes of ISB are analyzed and an ISB suppression method based on Retinex theory and global weighting is proposed. First, the image with ISB is considered as an image with uneven lighting, and ISB is considered as a lighting component. The ISB component is calculated using a global weighting method. Based on previous studies, the coupling relationship between ISB and scalloping (another issue commonly found in ScanSAR) is identified, and a joint procedure for suppressing ISB and scalloping is established. The proposed method is a post-processing technique that does not require any other additional information, such as the noise equivalent sigma zero. Experimental results based on real SAR images from Gaofen-3 and Sentinel-1 indicate that the proposed method can significantly reduce the effect of ISB and improve the image quality, and it is more efficient and robust compared to existing methods.

关键词： radar polarimetry Lighting Couplings Sentinel-1 Satellites remote sensing radar imaging Phased arrays Kalman filters Electronic mail Gaofen-3 (GF-3) interscan banding (ISB) suppression ScanSAR TOPSAR

来源：评论

学校读者我要写书评

暂无评论

Quantum Optimization for Phase Unwrapping in SAR Interferometry

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND remote sensing 2025年 18卷 3488-3500页

作者： Glatting, Kay Meyer, Jan Huber, Sigurd Krieger, Gerhard German Aerosp Ctr DLR D-82234 Wessling Germany

Phase unwrapping is the reconstruction of a phase given its values mod 2 pi. Phase unwrapping is an important image processing technique used in synthetic aperture radar interferometry, in the context of height estimation and ground deformation. By formulating the phase unwrapping problem as a global minimization problem, L(p )norm techniques form the backbone of many established phase unwrapping algorithms. The L-0 norm is commonly agreed to produce the best unwrapping solutions, but the necessary brute-force calculations are infeasible for the phase unwrapping of SAR interferograms. Developments in variational quantum algorithms suggest computational advantages, when compared to classical approaches, for a multitude of applications. We therefore investigate the application of quantum algorithms to the phase unwrapping problem and introduce and derive an approximate L-0 norm optimization solver utilizing the quantum approximate optimisation algorithm. This hybrid algorithm uses classical nonconvex parameter optimization to produce optimal parameters for a quantum circuit encoding the L-0 phase unwrapping. Subsequent execution of this quantum circuit allows for an estimate of the solution of the phase unwrapping problem with advantages compared to brute force approaches. We validate our approach for small topographies, by demonstrating improved results when compared to established L-1 optimization.

关键词： Optimization Quantum computing Quantum circuit Approximation algorithms synthetic aperture radar Qubit Quantum algorithm Phase measurement Geophysical measurements Deformation Interferometric synthetic aperture radar (InSAR) phase unwrapping (PU) quantum approximate optimization algorithm (QAOA) quantum computing

来源：评论

学校读者我要写书评

暂无评论

Fine classification of multi-frequency PolSAR images using an adaptive fusion network

引用

remote sensing LETTERS 2025年第5期16卷 461-471页

作者： Wang, Zehua Wang, Zezhong Qiu, Xiaolan Zhang, Zhe Harbin Inst Technol Shenzhen Shenzhen Guangdong Peoples R China Suzhou Key Lab Microwave Imaging Proc & Applicat T 158 Dushuhu Ave Suzhou 215123 Jiangsu Peoples R China Suzhou Aerosp Informat Res Inst Suzhou Peoples R China Univ Chinese Acad Sci Sch Elect Elect & Commun Engn Beijing Peoples R China Natl Key Lab Microwave Imaging Beijing Peoples R China Chinese Acad Sci Aerosp Informat Res Inst Beijing Peoples R China

Multi-frequency polarimetric synthetic aperture radar (MF-PolSAR) possesses the observational capabilities of traditional radar while also allowing for the acquisition of multi-frequency electromagnetic scattering information from observed targets, making it highly promising for various applications. To efficiently harness the wealth of multi-frequency information, this paper first introduces a scattering matrix extension method. Compared to other polarization data processing techniques, this method excels in preserving the original information, thereby facilitating the fusion of multi-frequency data. Furthermore, to address the issue of inter-band interference, an adaptive fusion model is proposed. Experimental results demonstrate that this method effectively leverages the information gain from different frequency bands, resulting in higher classification accuracy.

关键词： Multi-frequency polarimetric synthetic aperture radar image classification deep learning adaptive fusion model

来源：评论

学校读者我要写书评

暂无评论

Recent Advances in Deep-Learning-Based SAR image Target Detection and Recognition

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND remote sensing 2025年 18卷 6884-6915页

作者： Lang, Ping Fu, Xiongjun Dong, Jian Yang, Huizhang Yin, Junjun Yang, Jian Martorella, Marco Tsinghua Univ Dept Elect Engn Beijing 100084 Peoples R China Beijing Inst Technol Sch Integrated Circuits & Elect Beijing 100081 Peoples R China Nanjing Univ Sci & Technol Sch Elect & Opt Engn Nanjing 210094 Peoples R China Univ Sci & Technol Beijing Sch Comp & Commun Engn Beijing 100083 Peoples R China Univ Pisa Dept Informat Engn I-56127 Pisa Italy

synthetic aperture radar (SAR) image target detection and recognition (SAR-TDR) tasks have become research hot spots in the remote sensing application. These targets include ships, vehicles, aircraft, oil tanks, bridges, and so on. However, with the rapid development of SAR technology and increasingly complex electromagnetic environment, complex characteristics of SAR images bring severe challenges to the accurate SAR-TDR via traditional physical models or manual feature-extraction-based machine learning methods. In recent years, deep learning (DL), as a powerful automatic feature extraction algorithm, has been widely used in the computer vision domain. More specifically, DL has also been introduced into the SAR-TDR tasks and has effectively achieved good performance in terms of accuracy, real-time processing, etc. With the rapid development of DL, SAR image processing, and practical requirements of SAR-TDR in civilian and military domains, it is crucial to conduct a systematic survey on SAR-TDR in the past few years. In this survey article, we mainly conduct a systematic overview of DL-based SAR-TDR literature on two tasks, i.e., target recognition (e.g., ground vehicles, ships, and aircraft) and target detection (e.g., ships, aircraft, change detection, sea surface oil spills, and oil tanks). More specifically, our related works about these topics are also presented to verify the effectiveness of DL-based methods. First, several DL methods (e.g., convolutional neural networks, recurrent neural networks, autoencoders, and generative adversarial networks), commonly used in SAR-TDR, are briefly introduced. Then, a systematic review of DL-based SAR-TDR (including our related works) is presented. Finally, the current challenges and future possible research directions are deeply analyzed and discussed.

关键词： radar polarimetry Target recognition synthetic aperture radar Marine vehicles Feature extraction Object detection Aircraft Surveys Accuracy Deep learning Automatic target recognition change detection (CD) deep learning (DL) SAR image interpretation target detection

来源：评论

学校读者我要写书评

暂无评论

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

Autofocus Algorithm for Real-Time Correction of Residual RCM Based on ANCPS

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND remote sensing 2025年 63卷

作者： Xie, Yi Chen, Longyong Zhang, Fubo Xu, Yihao Yang, Ling Chinese Acad Sci Aerosp Informat Res Inst Natl Key Lab Microwave Imaging Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Elect Elect & Commun Engn Beijing 100049 Peoples R China Beijing Inst Elect Syst Engn Beijing 100854 Peoples R China

With synthetic aperture radar (SAR) systems being developed with miniaturization, lightweight, low-cost, high-resolution, and real-time capabilities, the scope of their application has expanded to some lightweight platforms that cannot carry a high-precision position and orientation system (POS) and whose trajectories are susceptible to interference. This often results in residual range cell migration (RCM) exceeding several or even dozens of range resolution cells, which notably degrades the performance of traditional autofocus algorithms and seriously affects the quality of real-time imaging. Considering this, we propose a real-time residual RCM correction scheme based on the autocorrelated normalized cross-power spectrum (ANCPS). First, the range-compressed image is segmented into blocks based on the azimuth and range. The ANCPS is then used to estimate the optimal residual RCM for each subblock. Second, the optimal segment is selected from the residual RCM curve fragments estimated by various subblocks. Finally, the residual RCM fragments are spliced and filtered to correct the complete data. When the algorithm is deployed on a GPU platform, it only takes 1.39 s to process an 8 x 40 K high-resolution original SAR image, and the calculation time is reduced by 94.6% compared with only using a CPU for calculation. The experimental results demonstrate that the proposed residual RCM correction scheme has good convergence, can achieve subpixel residual RCM compensation without iteration and interpolation, has a simple calculation process, is efficient, and has strong parallelism. It is thus suitable for deployment in GPUs and is conducive to realizing real-time SAR autofocus at a low cost and with a high resolution.

关键词： image segmentation Imaging Graphics processing units radar imaging apertures Real-time systems Robustness Trajectory synthetic aperture radar Field programmable gate arrays Autocorrelated normalized cross-power spectrum (ANCPS) correction of range cell migration (RCM) parallel computing synthetic aperture radar (SAR) real-time autofocus

来源：评论

学校读者我要写书评

暂无评论

Robust Imaging of Aerial Targets With Maneuvering Trajectory Based on Multioptimization Strategies Under a Spaceborne SAR/ISAR Hybrid Mode

引用

IEEE GEOSCIENCE AND remote sensing LETTERS 2025年 22卷

作者： Wan, Zhiqiang Shao, Shuai Fan, Jiabo Xu, Gang Chen, Bo Xidian Univ Natl Key Lab Radar Signal Proc Xian 710071 Peoples R China Innovat Acad Microsatellites Chinese Acad Sci Shanghai 201304 Peoples R China Southeast Univ Sch Informat Sci & Engn State Key Lab Millimeter Waves Nanjing 210096 Peoples R China

The aerial targets with maneuvering trajectories can result in severe defocusing in inverse synthetic aperture radar (ISAR) images, while the low signal-to-noise ratio (SNR) from remote observations can also pose challenges to imaging. However, due to the stable motion state of satellites and their higher speeds compared to aerial targets, the accumulation time required for imaging is relatively short. This makes the impact of aerial target trajectory maneuvers on imaging effects relatively minor, providing a significant advantage for robust imaging of aerial targets with maneuvering trajectory under a spaceborne SAR/ISAR hybrid mode. This letter proposes an algorithm for robust imaging of aerial targets with maneuvering trajectory based on multioptimization strategies (OSs) under a spaceborne SAR/ISAR hybrid mode. In this algorithm, robust imaging is divided into two parts: 1) multistep optimal imaging time interval selection method based on OSs (MS-OITI-OSs). Through multiple optimization steps based on the target's aerial trajectory and image information, the method achieves robust selection of the OITI by utilizing an "attitude first, quality later" optimization strategy, reducing computational complexity and increasing imaging success rates;and 2) joint translational motion compensation method based on OSs (JTMC-OSs). Characterizing motion parameters using a polynomial model, the method optimizes the motion parameters using image entropy as the objective function through the Grasshopper optimization algorithm (GOA). During the optimization process, a "high-order first, low-order later" optimization strategy is employed based on the impact of motion parameters on imaging quality to achieve robust translational motion compensation. The proposed algorithm enables robust imaging of aerial targets with maneuvering trajectory based on multi-OSs under a spaceborne SAR/ISAR hybrid mode. Extensive experimental validation confirms the effectiveness and robustness of the

关键词： Imaging Spaceborne radar radar imaging Trajectory Entropy Optimization Solid modeling Polynomials Motion compensation radar Aerial targets inverse synthetic aperture radar (ISAR) minimum entropy optimal imaging time interval (OITI) selection translational motion compensation

来源：评论

学校读者我要写书评

暂无评论

AIR-POLSAR-CR1.0: A Benchmark Dataset for Cloud Removal in High-Resolution Optical remote sensing images with Fully Polarized SAR

引用

remote sensing 2025年第2期17卷 275-275页

作者： Wang, Yuxi Zhang, Wenjuan Pan, Jie Jiang, Wen Yuan, Fangyan Zhang, Bo Yue, Xijuan Zhang, Bing Chinese Acad Sci Aerosp Informat Res Inst Key Lab Digital Earth Sci Beijing 100094 Peoples R China Int Res Ctr Big Data Sustainable Dev Goals Beijing 100094 Peoples R China Univ Chinese Acad Sci Coll Resources & Environm Beijing 100049 Peoples R China Chinese Acad Sci Aerosp Informat Res Inst Beijing 100094 Peoples R China

Due to the all-time and all-weather characteristics of synthetic aperture radar (SAR) data, they have become an important input for optical image restoration, and various cloud removal datasets based on SAR-optical have been proposed. Currently, the construction of multi-source cloud removal datasets typically employs single-polarization or dual-polarization backscatter SAR feature images, lacking a comprehensive description of target scattering information and polarization characteristics. This paper constructs a high-resolution remote sensing dataset, AIR-POLSAR-CR1.0, based on optical images, backscatter feature images, and polarization feature images using the fully polarimetric synthetic aperture radar (PolSAR) data. The dataset has been manually annotated to provide a foundation for subsequent analyses and processing. Finally, this study performs a performance analysis of typical cloud removal deep learning algorithms based on different categories and cloud coverage on the proposed standard dataset, serving as baseline results for this benchmark. The results of the ablation experiment also demonstrate the effectiveness of the PolSAR data. In summary, AIR-POLSAR-CR1.0 fills the gap in polarization feature images and demonstrates good adaptability for the development of deep learning algorithms.

关键词： remote sensing cloud removal deep learning dataset full PolSAR

来源：评论

学校读者我要写书评

暂无评论

NBDNet: A Self-Supervised CNN-Based Method for InSAR Phase and Coherence Estimation

引用

remote sensing 2025年第7期17卷 1181-1181页

作者： Li, Hongxiang Wang, Jili Ai, Chenguang Wu, Yulun Ren, Xiaoyuan Chinese Acad Sci Aerosp Informat Res Inst Dept Space Microwave Remote Sensing Syst Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Elect Elect & Commun Engn Beijing 101408 Peoples R China

Phase denoising constitutes a critical component of the synthetic aperture radar interferometry (InSAR) processing chain, where noise suppression and detail preservation are two mutually constraining objectives. Recently, deep learning has attracted considerable interest due to its promising performance in the field of image denoising. In this paper, a Neighbor2Neighbor denoising network (NBDNet) is proposed, which is capable of simultaneously estimating phase and coherence in both single-look and multi-look cases. Specifically, repeat-pass PALSAR real interferograms encompassing a diverse range of coherence, fringe density, and terrain features are used as the training dataset, and the novel Neighbor2Neighbor self-supervised training framework is leveraged. The Neighbor2Neighbor framework eliminates the necessity of noise-free labels, simplifying the training process. Furthermore, rich features can be learned directly from real interferograms. In order to validate the denoising capability and generalization ability of the proposed NBDNet, simulated data, repeat-pass data from Sentinel-1 Interferometric Wide (IW) swath mode, and single-pass data from Hongtu-1 stripmap mode are used for phase denoising experiments. The results demonstrate that NBDNet performs well in terms of noise suppression, detail preservation and computation efficiency, validating its potential for high-precision and high-resolution topography reconstruction.

关键词： convolutional neural network (CNN) Neighbor2Neighbor phase denoising self-supervised training synthetic aperture radar interferometry (InSAR)

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：