IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society最新文献_第6页

Evaluation of the Velocity Recovery and Dealiasing Algorithm for Dual-PRF Scans 双prf扫描速度恢复与去噪算法评价

IF 4.4

IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society Pub Date : 2026-01-01 Epub Date: 2026-01-21 DOI: 10.1109/LGRS.2026.3656843

David Schvartzman;Robert D. Palmer

{"title":"Evaluation of the Velocity Recovery and Dealiasing Algorithm for Dual-PRF Scans","authors":"David Schvartzman;Robert D. Palmer","doi":"10.1109/LGRS.2026.3656843","DOIUrl":"https://doi.org/10.1109/LGRS.2026.3656843","url":null,"abstract":"Doppler radars are susceptible to range–velocity ambiguities resulting from the use of uniformly spaced sequences of transmitted pulses. Dual-pulse repetition frequency (PRF) batch scanning strategies, commonly employed in operational weather radars, mitigate some ambiguities by transmitting two pulse trains with different repetition frequencies in sequence. However, they still suffer from significant velocity ambiguities beyond the unambiguous range of the sequence with the shorter pulse repetition time. In this letter, the velocity recovery and dealiasing (VRAD) algorithm is adapted for “batch-mode” scans to recover obscured Doppler velocities. The method blends data from both pulse sequences by dealiasing and filling censored regions using velocities from the long-pulse repetition time (PRT) sequence. Experimental results on Weather Surveillance Radar-1988 Doppler (WSR-88D) data collected during Hurricane Ian demonstrate substantial improvements in velocity coverage; a correlation coefficient exceeding 0.99 between recovered long- and existing short-PRT velocities (where available) was obtained to validate consistency of recovered velocities. These results highlight the potential to enhance operational Doppler velocity fields in dual-PRF batch scans.","PeriodicalId":91017,"journal":{"name":"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society","volume":"23 ","pages":"1-5"},"PeriodicalIF":4.4,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148486840","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

SCD-Net: A Semantic–Contour–Disparity Triadic Collaborative Network for 3-D Building Reconstruction From Stereo Satellite Imagery 基于语义-轮廓-视差三坐标协同网络的立体卫星影像三维建筑重建

IF 4.4

IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society Pub Date : 2026-01-01 Epub Date: 2026-03-25 DOI: 10.1109/LGRS.2026.3696738

Maozhen Zou;Liwei Li;Lingfeng Mei;Jianjun Sha;Jiajun Yu;Jianwei Meng

{"title":"SCD-Net: A Semantic–Contour–Disparity Triadic Collaborative Network for 3-D Building Reconstruction From Stereo Satellite Imagery","authors":"Maozhen Zou;Liwei Li;Lingfeng Mei;Jianjun Sha;Jiajun Yu;Jianwei Meng","doi":"10.1109/LGRS.2026.3696738","DOIUrl":"https://doi.org/10.1109/LGRS.2026.3696738","url":null,"abstract":"For the task of 3-D building reconstruction from stereo satellite imagery, existing methods often treat semantic segmentation, contour regularization, and disparity estimation as independent or loosely coupled tasks, failing to fully exploit their geometric correlations. To address this, this letter proposes the semantic–contour–disparity triadic collaborative network (SCD-Net). This network establishes a deeply coupled computational framework that extracts multiscale features through a shared encoder, subsequently routing them to dedicated branches. Specifically, we design a multiscale edge aggregation (MEA) module that significantly enhances the refined representation of building edges, and also propose a SCD Upsampling (SCDU) module, which leverages dual geometric priors from semantic categories and building contours to guide disparity optimization, effectively resolving the issue of blurred building boundaries in the disparity map. Furthermore, a novel building contour loss function is introduced, strengthening multitask constraints by quantifying the geometric consistency between disparity edges and semantic contours. Experiments on the US3D and WHU datasets demonstrate that the SCD-Net achieves state-of-the-art (SOTA) performance on key metrics for stereo matching and building semantic segmentation.","PeriodicalId":91017,"journal":{"name":"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society","volume":"23 ","pages":"6012705-6012705"},"PeriodicalIF":4.4,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148487306","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

Weakly Supervised Learning for Oriented Ship Detection in SAR Images Using Multiscale Feature Enhancement and Angle Encoding 基于多尺度特征增强和角度编码的弱监督学习SAR图像定向船舶检测

IF 4.4

IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society Pub Date : 2026-01-01 Epub Date: 2025-11-25 DOI: 10.1109/LGRS.2025.3637100

Yi Yang;Yanmei Zhang

{"title":"Weakly Supervised Learning for Oriented Ship Detection in SAR Images Using Multiscale Feature Enhancement and Angle Encoding","authors":"Yi Yang;Yanmei Zhang","doi":"10.1109/LGRS.2025.3637100","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3637100","url":null,"abstract":"This letter proposes a weakly supervised learning (WSL) framework for oriented ship detection in synthetic aperture radar (SAR) images, which tackles the challenges of detecting ships with arbitrary orientations using only horizontal bounding box (HBB) annotations. The proposed approach integrates three key modules: the Swin transformer with local context augmentation (STLCA) for enhanced multiscale feature extraction, recursive and hierarchical feature reconstruction (RHFR) for improved small-ship detection through iterative feature fusion, and the angle correct module with constraint (ACMC) to stabilize orientation prediction. The STLCA block enhances local feature extraction by dynamically adjusting attention windows, while RHFR performs multiscale feature fusion recursively to boost detection accuracy in complex environments. ACMC ensures precise angle prediction by applying constraints and leveraging periodic ambiguity properties. Comprehensive experiments on the SSDD and HRSID datasets demonstrate that our method achieves competitive performance with fully supervised methods, reaching 89.2% and <inline-formula> <tex-math>$90.9% text {AP}_{50}$ </tex-math></inline-formula>, confirming its effectiveness and practical value for SAR-based applications.","PeriodicalId":91017,"journal":{"name":"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society","volume":"23 ","pages":"1-5"},"PeriodicalIF":4.4,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148487453","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

Low-Light Remote Sensing Image Enhancement Guided Collaboratively by Memory and Illumination Map 记忆与光照地图协同引导的低照度遥感图像增强

IF 4.4

IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society Pub Date : 2026-01-01 Epub Date: 2026-03-16 DOI: 10.1109/LGRS.2026.3674220

Le Dong;Yang An;Weisheng Dong;Zhenyu Wang;Lichao Mou

{"title":"Low-Light Remote Sensing Image Enhancement Guided Collaboratively by Memory and Illumination Map","authors":"Le Dong;Yang An;Weisheng Dong;Zhenyu Wang;Lichao Mou","doi":"10.1109/LGRS.2026.3674220","DOIUrl":"https://doi.org/10.1109/LGRS.2026.3674220","url":null,"abstract":"Low-light remote sensing image (RSI) enhancement aims to improve illumination and restore hidden information in the dark. Deep learning-based approaches have achieved remarkable performance with powerful learning capabilities. However, existing convolutional neural network (CNN)-based low-light enhancement methods fail to fully exploit the spatial self-similarity of RSIs, leading to structural distortions and inadequate detail preservation in the enhanced results. In this letter, we propose a three-stage learning framework for low-light RSI enhancement, which is collaboratively guided by the memory unit and illumination map prior. First, leveraging long-range self-similarity in RSIs, we propose decomposing normal-light images into basic elements. A self-reconstruction stage trained on these images encodes fundamental RSI representations into a memory module. Second, we adopt knowledge distillation strategy with a pretrained normal-light encoder guiding low-light encoder training, combined with a spatially-adaptive feature modulation (SAFM) module for noise suppression during feature extraction. Finally, inspired by Retinex theory, an illumination prior-guided luminance correction module is designed for adaptively adjusting feature intensities to restore brightness and fine details consistent with normal-light distributions. Extensive experiments demonstrate that the proposed method outperforms existing state-of-the-art (SOTA) approaches. The code will be open-sourced after this letter is accepted.","PeriodicalId":91017,"journal":{"name":"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society","volume":"23 ","pages":"1-5"},"PeriodicalIF":4.4,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148487466","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

Simulation of the Longwave Radiance Tendency on Sea Surface Temperature Observed From Moon-Based Platform 月球平台观测海表温度的长波辐射趋势模拟

IF 4.4

IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society Pub Date : 2026-01-01 Epub Date: 2026-03-19 DOI: 10.1109/LGRS.2026.3694023

Yuhan Wei;Guoqiang Chen;Mingyang Lv;Wenhui Wan;Dan Song;Pei Tan;Huadong Guo

{"title":"Simulation of the Longwave Radiance Tendency on Sea Surface Temperature Observed From Moon-Based Platform","authors":"Yuhan Wei;Guoqiang Chen;Mingyang Lv;Wenhui Wan;Dan Song;Pei Tan;Huadong Guo","doi":"10.1109/LGRS.2026.3694023","DOIUrl":"https://doi.org/10.1109/LGRS.2026.3694023","url":null,"abstract":"Longwave radiance (LWR), a fundamental measure of Earth’s thermal radiation, serves as a key indicator of global climate change. A future Moon-based radiation observatory (MBRO), characterized by stable orbital configuration, unique spatial environment, and etc., facilitates the acquisition of LWR data and underpins associated climate research. This study has developed a model to simulate earth LWR observed from Moon and corresponding coefficient of determination (R<inline-formula> <tex-math>${}^{mathbf {2}}$ </tex-math></inline-formula>) with sea surface temperature (SST) in critical zone, utilizing outgoing longwave radiation (OLR) based on CERES Edition 4 ADMs, and MCD12C1 data. Results show 1) relatively small monthly variations standard deviation ~0.5 W/(m<inline-formula> <tex-math>${}^{mathbf {2}}{,}cdot $ </tex-math></inline-formula> sr) and stable, periodic interannual fluctuations ranging from approximately 70.5–80.5 W/(m<inline-formula> <tex-math>${}^{mathbf {2}}~cdot $ </tex-math></inline-formula> sr); 2) the ocean contribute the largest share (~70%) to earth’s total LWR; 3) long-term data from 2004 to 2022 has no significant trend in global LWR; and 4) R<inline-formula> <tex-math>${}^{mathbf {2}}$ </tex-math></inline-formula> between SST and global oceanic LWR exhibits a distinct zonal distribution pattern. During El Niño events, R<inline-formula> <tex-math>${}^{mathbf {2}}$ </tex-math></inline-formula> in affected regions varied synchronously with event intensity, exhibiting a proportional relationship between event strength and the magnitude of R<inline-formula> <tex-math>${}^{mathbf {2}}$ </tex-math></inline-formula> enhancement. In general, this study lays a foundation and a novel approach for interpreting earth radiation features in future missions.","PeriodicalId":91017,"journal":{"name":"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society","volume":"23 ","pages":"1503305-1503305"},"PeriodicalIF":4.4,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148487477","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

Adaptive Radar Approaches for Doppler Moment Estimation 多普勒矩估计的自适应雷达方法

IF 4.4

IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society Pub Date : 2026-01-01 Epub Date: 2025-12-19 DOI: 10.1109/LGRS.2025.3646459

Apostolos Pappas;Tworit Dash;Alexander Yarovoy;Francesco Fioranelli;Shafi Sardar;Marc Schleiss

{"title":"Adaptive Radar Approaches for Doppler Moment Estimation","authors":"Apostolos Pappas;Tworit Dash;Alexander Yarovoy;Francesco Fioranelli;Shafi Sardar;Marc Schleiss","doi":"10.1109/LGRS.2025.3646459","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3646459","url":null,"abstract":"To characterize atmospheric turbulence, the Doppler moments are estimated by weather radars. However, moment accuracy is highly sensitive to radar transmission parameters such as the pulse repetition time (<inline-formula> <tex-math>${T}_{s}$ </tex-math></inline-formula>) and the number of pulses (<inline-formula> <tex-math>${N}_{p}$ </tex-math></inline-formula>), which affects Doppler ambiguity and estimation variance. Traditional fixed-parameter radars face tradeoffs between aliasing and measurement precision. This letter proposes an adaptive radar framework that dynamically adjusts <inline-formula> <tex-math>${T}_{s}$ </tex-math></inline-formula> and <inline-formula> <tex-math>${N}_{p}$ </tex-math></inline-formula> on a per-scan basis to improve Doppler moment estimation at a single resolution cell level. Inspired by the fully adaptive radar (FAR) concept, the method also includes a novel multilag Doppler width estimation scheme. Results demonstrate enhanced estimation accuracy, enabling better responsiveness to localized and nonstationary weather conditions.","PeriodicalId":91017,"journal":{"name":"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society","volume":"23 ","pages":"1-5"},"PeriodicalIF":4.4,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148487576","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

Hyperbolic Prototype Learning for Open-Set Joint HSI–LiDAR Classification 开放集联合HSI-LiDAR分类的双曲原型学习

IF 4.4

IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society Pub Date : 2026-01-01 Epub Date: 2026-04-29 DOI: 10.1109/LGRS.2026.3688851

Amirreza Khoshbakht;Erchan Aptoula

引用次数: 0

Adaptive Residual Mamba Network for Remote Sensing Change Detection 遥感变化检测的自适应残差曼巴网络

IF 4.4

IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society Pub Date : 2026-01-01 Epub Date: 2026-04-23 DOI: 10.1109/LGRS.2026.3686887

Junyi Zhang;Renwen Chen;Fei Liu;Aocheng He;Boyu Zheng;Xintong Hou

{"title":"Adaptive Residual Mamba Network for Remote Sensing Change Detection","authors":"Junyi Zhang;Renwen Chen;Fei Liu;Aocheng He;Boyu Zheng;Xintong Hou","doi":"10.1109/LGRS.2026.3686887","DOIUrl":"https://doi.org/10.1109/LGRS.2026.3686887","url":null,"abstract":"Although convolutional neural networks (CNNs) and transformer-based models have achieved considerable success in the remote sensing change detection (RSCD) field, they often struggle to balance local detail preservation and global dependency modeling. Recently, state-space models such as Mamba have shown promising potential for efficient long-range representation learning. However, most existing Mamba-based RSCD methods are constrained by fixed residual connection mechanisms and selective scanning strategies, resulting in limited feature adaptability in spatial dependency modeling. To address these challenges, we propose adaptive residual Mamba (AR-Mamba), a novel Mamba-based framework that introduces adaptive residual and cross-gated scanning mechanisms. Specifically, the adaptive residual state (ARS) block employs adaptive kernel convolver and learnable scaling to dynamically calibrate residual signals. The cross-gated bi-scanning (CGBS) strategy performs bidirectional spatial scanning and cross-directional gating. Experimental results on the LEVIR-CD, SYSU-CD, and WHU-CD datasets demonstrate the effectiveness of the proposed AR-Mamba, which achieves F1-score improvements of 0.82%, 1.95%, and 1.62% over ChangeMamba, respectively.","PeriodicalId":91017,"journal":{"name":"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society","volume":"23 ","pages":"1-5"},"PeriodicalIF":4.4,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148487754","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 Closed-Form Analytical Solution for HFSWR Wind Direction Inversion Using the von Mises Model 利用von Mises模型反演HFSWR风向的封闭解析解

IF 4.4

IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society Pub Date : 2026-01-01 Epub Date: 2026-03-20 DOI: 10.1109/LGRS.2026.3676277

Xiaoyan Li;Xiongbin Wu;Fuqi Mo;Liang Yu;Heng Zhou

{"title":"A Closed-Form Analytical Solution for HFSWR Wind Direction Inversion Using the von Mises Model","authors":"Xiaoyan Li;Xiongbin Wu;Fuqi Mo;Liang Yu;Heng Zhou","doi":"10.1109/LGRS.2026.3676277","DOIUrl":"https://doi.org/10.1109/LGRS.2026.3676277","url":null,"abstract":"Wind direction inversion in high-frequency surface wave radar (HFSWR) relies heavily on the directional distribution model (DDM). The classical Longuet–Higgins (L–H) model causes nonphysical spatial discontinuities due to energy truncation in the upwind direction. While the Donelan model corrects this defect and achieves higher accuracy, its inversion still relies on nonlinear optimization or numerical discretization, resulting in low computational efficiency. The Apel model, though simple in form, also lacks a unified analytical inversion formula. To address these issues, this letter introduces the von Mises (VM) model—a natural circular distribution ensuring physical continuity—into HFSWR wind direction inversion. We derive an explicit closed-form analytical solution for dual-station inversion by exploiting the VM model’s exponential properties, transforming complex numerical searches into efficient algebraic calculations. Field experiments in the Taiwan Strait demonstrate that the VM model achieves slightly better accuracy than the Donelan model, with an overall root mean square error (RMSE) of 9.49° and mean absolute error (MAE) of 7.28° across cross-wind and onshore scenarios, while ensuring spatial smoothness and accelerating the computation by over three orders of magnitude.","PeriodicalId":91017,"journal":{"name":"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society","volume":"23 ","pages":"1-5"},"PeriodicalIF":4.4,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148488178","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

MKD-Net: A Multikernel Downsampling Network for Adjacent and Small-Scale Ship Detection in SAR Images MKD-Net：一种多核下采样网络，用于SAR图像的邻域和小尺度船舶检测

IF 4.4

IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society Pub Date : 2026-01-01 Epub Date: 2026-04-27 DOI: 10.1109/LGRS.2026.3687720

Yuhu Qiao;Zhihui Xin;Guisheng Liao;Penghui Huang;Rui Wang;Jiahui Wu

{"title":"MKD-Net: A Multikernel Downsampling Network for Adjacent and Small-Scale Ship Detection in SAR Images","authors":"Yuhu Qiao;Zhihui Xin;Guisheng Liao;Penghui Huang;Rui Wang;Jiahui Wu","doi":"10.1109/LGRS.2026.3687720","DOIUrl":"https://doi.org/10.1109/LGRS.2026.3687720","url":null,"abstract":"Synthetic aperture radar (SAR), as an important remote sensing technology, is playing an increasingly important role in marine monitoring. Nevertheless, in ship detection tasks of SAR images involving complex near-shore backgrounds, blurred edges of adjacent targets, and dense small ships, false alarms and missed detections remain difficult to avoid. To this end, this letter proposes a ship detection network, termed MKD-Net, which is based on a multikernel downsampling (MKD) module. This method integrates two key designs with low-parameter complexity. The MKD transfers spatial information into the channel domain and extracts information using multikernel convolution, which can obtain features under different receptive fields while preserving fine-grained image details. The content-adaptive coordinate attention (CACA) introduces a dual-layer gating mechanism that consists of basic learnable weights and content-adaptive weights. Compared with other methods, the proposed method uses only 2.9M parameters. Furthermore, it can effectively detect adjacent targets in complex backgrounds, as well as dense small-scale targets. The proposed method achieves optimal detection performance.","PeriodicalId":91017,"journal":{"name":"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society","volume":"23 ","pages":"4007805-4007805"},"PeriodicalIF":4.4,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148488231","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