IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society最新文献

筛选
英文 中文
Sea Ice Semantic Segmentation in Optical Image Based on Adaptive Training Sample Selection and Cross-Attention ResUNet
Zhiyong Yin;Yuqi Tang;Francesca Bovolo
{"title":"Sea Ice Semantic Segmentation in Optical Image Based on Adaptive Training Sample Selection and Cross-Attention ResUNet","authors":"Zhiyong Yin;Yuqi Tang;Francesca Bovolo","doi":"10.1109/LGRS.2025.3546322","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3546322","url":null,"abstract":"The formation of numerous channels among Arctic sea ice provides potential routes for Arctic navigation and the identification and semantic segmentation of sea ice becomes a crucial task. This letter proposes a sea ice semantic segmentation method with adaptive training sample selection and cross-attention mechanism to enhance the robustness under the complex climatic conditions of the Arctic. First, the image is divided into patches. An adaptive iterative clustering on them automatically selects the training samples. Second, ResUNet with a cross-attention mechanism is used for image segmentation. This approach enhances contextual understanding with relatively low computational overhead, enabling better focus on relevant features across different layers of the network. The experimental results demonstrate that the proposed method can achieve high accuracy segmentation with a small training set. Furthermore, the proposed method exhibits segmentation consistency across two datasets and various types of sea ice.","PeriodicalId":91017,"journal":{"name":"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society","volume":"22 ","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2025-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143706702","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
CWmamba: Leveraging CNN-Mamba Fusion for Enhanced Change Detection in Remote Sensing Images
Yingchao Liu;Guangliang Cheng;Qihang Sun;Chunpeng Tian;Lukun Wang
{"title":"CWmamba: Leveraging CNN-Mamba Fusion for Enhanced Change Detection in Remote Sensing Images","authors":"Yingchao Liu;Guangliang Cheng;Qihang Sun;Chunpeng Tian;Lukun Wang","doi":"10.1109/LGRS.2025.3548145","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3548145","url":null,"abstract":"Remote sensing image change detection is crucial for urban construction and environmental monitoring. Recent advancements have seen convolutional neural networks (CNNs) and transformer structures increasingly applied in this domain. However, CNNs struggle with long-distance feature capture, while transformers suffer from high computational demands. Moreover, the inherently high resolution of remote sensing images and their susceptibility to natural conditions complicate feature extraction and processing, thereby hindering accurate change detection. The introduction of the mamba structure has significantly mitigated the issue of long-distance feature extraction. This letter introduces a model that integrates CNN and Mamba, named CWmamba, which employs a novel architecture combining mamba blocks and a CNN-based feature extraction block (BCGF) to process dual-temporal images. In the encoding phase, CWmamba utilizes the mamba blocks for global feature integration and the BCGF module for local feature enhancement. The decoding phase involves the fusion of multilevel features to augment the model’s expressive capability. The results of CWmamba on three datasets, SYSU-CD, LEVIR-CD+, and S2Looking, demonstrate its effectiveness, with F1 scores of 84.33%, 87.21%, and 67.93%, respectively.","PeriodicalId":91017,"journal":{"name":"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society","volume":"22 ","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2025-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143726462","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Efficient Superpixel-Based Seamline Detection for Large-Scale Image Stitching
Zhongxing Wang;Zhizhong Fu;Jin Xu
{"title":"Efficient Superpixel-Based Seamline Detection for Large-Scale Image Stitching","authors":"Zhongxing Wang;Zhizhong Fu;Jin Xu","doi":"10.1109/LGRS.2025.3548266","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3548266","url":null,"abstract":"As a crucial procedure for image stitching, seamline detection has an important impact on the quality of the final mosaic. However, traditional seamline detection methods are less efficient in determining the optimal seamlines for multiple images. This letter presents an efficient superpixel-level seamline detection method for large-scale unmanned aerial vehicle (UAV) image stitching, which can detect the optimal seamlines for hundreds of images in several minutes. Specifically, a novel superpixel-based energy function which simultaneously considers color difference, gradient magnitude, and texture complexity is devised to determine the superpixel-level optimal seamlines in the overlapping areas of multiple images. The energy minimization problem is efficiently solved by the multilabel optimization algorithm. Experimental results on five remote sensing datasets captured by UAVs have shown that the proposed superpixel-level seamline detection method is very effective in generating high-quality seamless mosaics for large-scale images.","PeriodicalId":91017,"journal":{"name":"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society","volume":"22 ","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2025-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143706755","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Integrated Physically Interpretable Model for SAR Target Recognition: Unified Fusion of Electromagnetic and Deep Features
Leiyao Liao;Zishuo Hong;Ziwei Liu;Gengxin Zhang
{"title":"Integrated Physically Interpretable Model for SAR Target Recognition: Unified Fusion of Electromagnetic and Deep Features","authors":"Leiyao Liao;Zishuo Hong;Ziwei Liu;Gengxin Zhang","doi":"10.1109/LGRS.2025.3548166","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3548166","url":null,"abstract":"Synthetic aperture radar (SAR) target recognition has been a prominent research topic in the field of remote sensing image processing. Traditional methods can extract physical features for SAR target recognition, but they are often time-consuming. Deep learning-based methods can learn representative features, but they often operate as black boxes and lack interpretability. This letter introduces an integrated physically interpretable model (IPIM) for SAR target recognition, which unifies electromagnetic and deep learning features. Our method is an integrative model built with an end-to-end mechanism, achieving promising performance and high time efficiency. Specifically, our method employs a deep-unfolding network to learn physical features by incorporating the generative process of complex SAR images. Additionally, a feature fusion module is designed to combine physical features, which reflect local target characteristics, with deep features that capture global information. Experimental results on a measured SAR image dataset demonstrate that our method effectively learns physical features and achieves high performance in target recognition.","PeriodicalId":91017,"journal":{"name":"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society","volume":"22 ","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2025-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143716482","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Fine-Grained Object Detection of Satellite Video in the Frequency Domain
Yuhan Sun;Shengyang Li
{"title":"Fine-Grained Object Detection of Satellite Video in the Frequency Domain","authors":"Yuhan Sun;Shengyang Li","doi":"10.1109/LGRS.2025.3548104","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3548104","url":null,"abstract":"Satellite video objects often have small scales and the occlusion of their distinguishable regions. Existing fine-grained object detection methods estimate object locations and categories by enhancing object features and increasing feature differences between categories. However, they fail to account for the impact of limited feature information on fine-grained detection, specifically reflected in two aspects: 1) limited pixels lead to limited features. The small pixel coverage of satellite video objects results in a low upper bound on the available feature information, hindering significant improvements in fine-grained detection accuracy and 2) limited differences exacerbate limitations. Occlusion of distinguishable regions in small-scale objects exacerbates the indistinctness of features between different fine-grained categories. It prevents the network from accurately learning unique features for certain object classes, thereby degrades detector performance. To address these challenges, we propose a frequency auxiliary network (FANet), which integrates frequency domain feature learning into fine-grained object detection networks. Specifically, we propose the spectral augmented module (SAM) to extract multispectral features from various frequency components of satellite video frames to complement spatial-domain features, enabling the network to leverage hidden semantic information from the frequency domain. In addition, to better distinguish small-scale objects from the background and emphasize fine-grained category features, we design the frequency domain attention (FDA) mechanism. FDA assigns dynamic weights to spatial and frequency domain features, suppressing background information and enhancing feature differences between fine-grained categories. Extensive experiments on the SAT-MTB dataset demonstrate that FANet achieves superior performance compared to existing methods.","PeriodicalId":91017,"journal":{"name":"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society","volume":"22 ","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2025-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143735417","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Multilateral Cascading Network for Semantic Segmentation of Large-Scale Outdoor Point Clouds
Haoran Gong;Haodong Wang;Di Wang
{"title":"Multilateral Cascading Network for Semantic Segmentation of Large-Scale Outdoor Point Clouds","authors":"Haoran Gong;Haodong Wang;Di Wang","doi":"10.1109/LGRS.2025.3547913","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3547913","url":null,"abstract":"Semantic segmentation of large-scale outdoor point clouds is of significant importance in environment perception and scene understanding. However, this task continues to present a significant research challenge, due to the inherent complexity of outdoor objects and their diverse distributions in real-world environments. In this study, we propose the multilateral cascading network (MCNet) designed to address this challenge. The model comprises two key components: a multilateral cascading attention enhancement (MCAE) module, which facilitates the learning of complex local features through multilateral cascading operations; and a point cross-stage partial (P-CSP) module, which fuses global and local features, thereby optimizing the integration of valuable feature information across multiple scales. Our proposed method demonstrates superior performance relative to state-of-the-art approaches across two widely recognized benchmark datasets: Toronto3D and SensatUrban. Especially on the city-scale SensatUrban dataset, our results surpassed the current best result by 2.1% in overall mean intersection over union (mIoU) and yielded an improvement of 15.9% on average for small-sample object categories comprising less than 2% of the total samples, in comparison to the baseline method. Our code is available at <uri>https://github.com/ranhaogong/MCNet</uri>.","PeriodicalId":91017,"journal":{"name":"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society","volume":"22 ","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2025-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143667443","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Estimation of Top-of-Atmosphere Net Radiation From AVHRR Data
Chuan Zhan;Yong Chen;Zuohua Miao;Wenjing Li;Xiangyang Zeng;Jun Li
{"title":"Estimation of Top-of-Atmosphere Net Radiation From AVHRR Data","authors":"Chuan Zhan;Yong Chen;Zuohua Miao;Wenjing Li;Xiangyang Zeng;Jun Li","doi":"10.1109/LGRS.2025.3547834","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3547834","url":null,"abstract":"The top-of-atmosphere (TOA) net radiation (NR), a key component of the Earth’s energy budget, directly indicates the imbalance between incoming solar radiation from the space and outgoing shortwave/longwave radiation from the Earth’s climate system. However, the spatial resolutions of the existing TOA NR products are too coarse to provide enough details when analyzing the energy budget at regional scales. This letter presents a direct machine learning method to estimate TOA NR by directly linking advanced very high-resolution radiometer (AVHRR) TOA radiances with TOA NR determined by Clouds and the Earth’s Radiant Energy System (CERES) and other information, such as the solar/viewing geometry, land surface temperature (LST), and cloud top temperature determined by Modern-Era Retrospective analysis for Research and Applications, Version 2 (MERRA-2). Models are built using a gradient boosting regression tree. Independent test results show that the root mean square error (RMSE) of the model for estimating instantaneous values is 25.16 W/m2. Daily results are converted from the instantaneous results using climatology conversion ratios derived from CERES daily and hourly data. Intercomparisons of the daily results with CERES TOA NR data show that the RMSEs of the estimated AVHRR NR are less than 30 W/m2. The developed algorithm may contribute to generating relatively high-resolution (5-km) AVHRR TOA NR dataset, which will be beneficial in analyzing the regional energy budget.","PeriodicalId":91017,"journal":{"name":"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society","volume":"22 ","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2025-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143675973","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Learned 2D-TwISTA for 2-D Sparse ISAR Imaging
Quan Huang;Lei Zhang;Shaopeng Wei;Jia Duan
{"title":"Learned 2D-TwISTA for 2-D Sparse ISAR Imaging","authors":"Quan Huang;Lei Zhang;Shaopeng Wei;Jia Duan","doi":"10.1109/LGRS.2025.3547408","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3547408","url":null,"abstract":"By unfolding traditional optimization algorithms into the form of neural networks, the unfolding network methods have attracted more and more attention in sparse inverse synthetic aperture radar (ISAR) imaging because of their high reconstruction performance and good interpretability. However, existing unfolding network methods mainly focus on 1-D sparse ISAR imaging and cannot be directly applied to 2-D sparse ISAR data. For this reason, a novel learned 2D-two-step iterative shrinkage/thresholding algorithm (L-2D-TwISTA) is proposed for high-efficiency and high-accuracy 2-D sparse ISAR imaging. Specifically, each stage of L-2D-TwISTA corresponds to an iterative solution step of the developed 2D-TwISTA approach. Moreover, a complex-valued (CV) residual network is designed in L-2D-TwISTA to improve training efficiency and solve the nonlinear problem of proximal mapping of the 2D-TwISTA more effectively. The experimental results of real-measured data confirm that the L-2D-TwISTA can realize high-performance 2-D sparse ISAR imaging.","PeriodicalId":91017,"journal":{"name":"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society","volume":"22 ","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2025-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143632266","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Reconstruction-Based 2DPCANet for Unsupervised SAR Image Change Detection
Jie Wu;Qimeng Zhang;Rongrong Li;Luis Gomez;Alejandro C. Frery
{"title":"Reconstruction-Based 2DPCANet for Unsupervised SAR Image Change Detection","authors":"Jie Wu;Qimeng Zhang;Rongrong Li;Luis Gomez;Alejandro C. Frery","doi":"10.1109/LGRS.2025.3547844","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3547844","url":null,"abstract":"In this letter, considering the effectiveness of 2-D principal component analysis (2DPCA) on the exploration of local spatial relationships, a reconstruction-based 2DPCA (Rec-2DPCA) operation was designed for feature extraction and injected into the architecture of PCANet for change detection of bitemporal synthetic aperture radar (SAR) image. Specifically, as the projection of an image patch on one eigenvector computed by 2DPCA breaks the one-to-one relationship between feature map and eigenvalue, we adopted Rec-2DPCA at various network layers and developed two variants of PCANet, namely, 2DPCANet and (2-D + 1-D)PCANet. In the experiments, using three real SAR image datasets, we analyzed the performance of all comparison methods, and our proposals achieved a more appealing performance than other methods.","PeriodicalId":91017,"journal":{"name":"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society","volume":"22 ","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2025-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143706709","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
A Pixel Expansion-Based Improvement in Dense Nesting Structures for Infrared Small Target Detection
Zhichao Zhao;Hao Wang;Haiyan Li;Jundon Yang;Pengfei Yu
{"title":"A Pixel Expansion-Based Improvement in Dense Nesting Structures for Infrared Small Target Detection","authors":"Zhichao Zhao;Hao Wang;Haiyan Li;Jundon Yang;Pengfei Yu","doi":"10.1109/LGRS.2025.3547899","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3547899","url":null,"abstract":"In infrared detection, the identification of weak targets is often hindered by low pixel count and resolution, leading to a scarcity of semantic details for small targets and significant blurring of boundary information. To solve these problems, we propose a novel approach for the enhanced cross-stage feature matching network (ECFNet) to learn features beyond a single-scale data source by introducing pixel expansion branching in this letter. First, we introduce the feature attention enhancement module (FAEM), which uses rapid edge feature extraction to effectively enhance the boundary information of weak targets after pixel expansion, thereby improving the network’s fine-grained detection capability. Moreover, inspired by the Monte Carlo attention mechanism used in medical image processing, we introduce the stage randomness enhancement module (SREM) to direct the network’s focus toward small target regions rather than background noise during the learning process, allowing the network to adapt to various random situations independent of a fixed structure. Furthermore, we design a cross-feature matching module (CFMM), which effectively aggregates shallow profile information and deeper semantics at the center of the network, facilitating efficient information transfer and precise feature assignment, thereby narrowing the feature gap between the encoding and decoding stages. Our network achieves an intersection-over-union (IoU) ratio of 78.51% on the publicly available NUAA-SIRST dataset. The experimental results of NUDT-SIRDT and infrared small target detection (IRSTD)-1k can be found in <uri>https://github.com/bobo66597/ECF</uri>.","PeriodicalId":91017,"journal":{"name":"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society","volume":"22 ","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2025-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143667442","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信