Depth-resolved estimation of soil organic carbon (SOC) remains challenging because optical measurements originate at the surface while carbon dynamics vary vertically. We propose a physics-aware uncrewed aerial vehicle (UAV) framework that integrates multispectral imagery (MSI) and hyperspectral imagery (HSI) to estimate SOC concentration (%) across five depths. The experiment was conducted at Plantheaven Farms, Missouri, with ten sorghum genotypes across three replicates. Feature construction combined spectral derivatives from HSI with texture features from MSI, compressed via principal component analysis (PCA). Physics-based regularization was implemented through: 1) a second-difference penalty to enforce vertical smoothness and 2) a profile-integral consistency constraint to preserve whole-profile balance. Four model configurations evaluated on local data showed progressive improvements: MSI-only, MSI + HSI, MSI + HSI with smoothness, and MSI + HSI with full physics constraints. In addition, transfer learning from the open soil spectral library (OSSL) was tested to address data limitations. Model fitting on the available data achieved ${R} ^{2} = 0.72$ at 0–30 cm, with physics-aware constraints notably improving vertical coherence. The physics-aware model reduced variance and improved plausibility. In-sample, transfer learning achieved ${R} ^{2}=0.60$ at 0–30 cm, with conservative interpretation below 90 cm due to reduced optical sensitivity. Exploratory genotype patterns suggested higher surface SOC percent for PI 656 029 and PI 656 057, and lower values for PI 276 837 and PI 656 044.
{"title":"Physics-Aware Neural Framework for Multidepth Soil Carbon Mapping","authors":"Bishal Roy;Vasit Sagan;Haireti Alifu;Jocelyn Saxton;Cagri Gul;Nadia Shakoor","doi":"10.1109/LGRS.2025.3632815","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3632815","url":null,"abstract":"Depth-resolved estimation of soil organic carbon (SOC) remains challenging because optical measurements originate at the surface while carbon dynamics vary vertically. We propose a physics-aware uncrewed aerial vehicle (UAV) framework that integrates multispectral imagery (MSI) and hyperspectral imagery (HSI) to estimate SOC concentration (%) across five depths. The experiment was conducted at Plantheaven Farms, Missouri, with ten sorghum genotypes across three replicates. Feature construction combined spectral derivatives from HSI with texture features from MSI, compressed via principal component analysis (PCA). Physics-based regularization was implemented through: 1) a second-difference penalty to enforce vertical smoothness and 2) a profile-integral consistency constraint to preserve whole-profile balance. Four model configurations evaluated on local data showed progressive improvements: MSI-only, MSI + HSI, MSI + HSI with smoothness, and MSI + HSI with full physics constraints. In addition, transfer learning from the open soil spectral library (OSSL) was tested to address data limitations. Model fitting on the available data achieved <inline-formula> <tex-math>${R} ^{2} = 0.72$ </tex-math></inline-formula> at 0–30 cm, with physics-aware constraints notably improving vertical coherence. The physics-aware model reduced variance and improved plausibility. In-sample, transfer learning achieved <inline-formula> <tex-math>${R} ^{2}=0.60$ </tex-math></inline-formula> at 0–30 cm, with conservative interpretation below 90 cm due to reduced optical sensitivity. Exploratory genotype patterns suggested higher surface SOC percent for PI 656 029 and PI 656 057, and lower values for PI 276 837 and PI 656 044.","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":"2025-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145612116","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}
This letter presents a low-complexity attention module for fast change detection. The proposed module computes the absolute difference between bitemporal features extracted by a Siamese backbone network and sequentially applies spatial and channel attention to generate key change representations. Spatial attention emphasizes important spatial locations using representative values from channelwise pooling, while channel attention highlights discriminative feature responses using values from spatialwise pooling. By leveraging low-dimensional representative features, the module significantly reduces computational cost. Additionally, its dual-attention structure-driven by feature differences-enhances both spatial localization and semantic relevance of changes. Compared to the change-guided network (CGNet), the proposed method reduces multiply-accumulate operations (MACs) by 53.81% with only a 0.15% drop in ${F}1$ -score, demonstrating high efficiency with minimal performance degradation. These results suggest that the proposed method is suitable for large-scale or real-time remote sensing (RS) applications where computational efficiency is essential.
{"title":"Lightweight Attention Mechanism With Feature Differences for Efficient Change Detection in Remote Sensing","authors":"Jangsoo Park;EunSeong Lee;Jongseok Lee;Seoung-Jun Oh;Donggyu Sim","doi":"10.1109/LGRS.2025.3633179","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3633179","url":null,"abstract":"This letter presents a low-complexity attention module for fast change detection. The proposed module computes the absolute difference between bitemporal features extracted by a Siamese backbone network and sequentially applies spatial and channel attention to generate key change representations. Spatial attention emphasizes important spatial locations using representative values from channelwise pooling, while channel attention highlights discriminative feature responses using values from spatialwise pooling. By leveraging low-dimensional representative features, the module significantly reduces computational cost. Additionally, its dual-attention structure-driven by feature differences-enhances both spatial localization and semantic relevance of changes. Compared to the change-guided network (CGNet), the proposed method reduces multiply-accumulate operations (MACs) by 53.81% with only a 0.15% drop in <inline-formula> <tex-math>${F}1$ </tex-math></inline-formula>-score, demonstrating high efficiency with minimal performance degradation. These results suggest that the proposed method is suitable for large-scale or real-time remote sensing (RS) applications where computational efficiency is essential.","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":"2025-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145612075","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}
Pub Date : 2025-11-14DOI: 10.1109/LGRS.2025.3632860
Qiang Na;Biao Cao;Wanchun Zhang;Limeng Zheng;Xi Zhang;Ziyi Yang;Qinhuo Liu
Satellite-derived surface upward longwave radiation (SULR) is essential for monitoring the global surface radiation budget, ecological processes, and climate change. However, the widely used SULR products derived from thermal infrared (TIR) remote sensing exhibit spatial discontinuities because TIR signals cannot penetrate cloud cover. Conventional cloud-sky SULR estimation approaches often utilize post-processed reanalysis data as inputs, which could not meet the real-time requirement of the operational system. This study proposes a lightweight cloud-sky SULR real-time estimation method for the Fengyun-4A (FY-4A) geostationary satellite using a Light Gradient Boosting Machine (LightGBM) model. The daytime cloud-sky SULR is estimated by applying the established relationship between auxiliary variables and clear-sky SULR to cloudy conditions, while the nighttime cloud-sky SULR values are estimated by applying the determined relationship between input variables and a publicly accessible, gap-filled SULR product. The model inputs include: 1) spatial-temporal location record data; 2) multiple surface characteristic parameters generated from previous-year data; and 3) two categories of operational FY-4A radiation products, with both components being available in real-time. Validation against six Heihe Watershed Allied Telemetry Experimental Research (HiWATER) sites demonstrates that the reconstructed cloud-sky SULR achieves acceptable root mean square error (RMSE) and mean bias error (MBE) values of 33.4 W/m2 (1.5 W/m2) for daytime and 25.2 W/m2 (4.7 W/m2) for nighttime conditions. Therefore, the proposed lightweight method could improve the spatial coverage of the current FY-4A SULR product and further promote real-time SULR-related applications.
{"title":"A Lightweight Method of Cloud-Sky Surface Upward Longwave Radiation Real-Time Estimation for FY-4A Geostationary Satellite","authors":"Qiang Na;Biao Cao;Wanchun Zhang;Limeng Zheng;Xi Zhang;Ziyi Yang;Qinhuo Liu","doi":"10.1109/LGRS.2025.3632860","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3632860","url":null,"abstract":"Satellite-derived surface upward longwave radiation (SULR) is essential for monitoring the global surface radiation budget, ecological processes, and climate change. However, the widely used SULR products derived from thermal infrared (TIR) remote sensing exhibit spatial discontinuities because TIR signals cannot penetrate cloud cover. Conventional cloud-sky SULR estimation approaches often utilize post-processed reanalysis data as inputs, which could not meet the real-time requirement of the operational system. This study proposes a lightweight cloud-sky SULR real-time estimation method for the Fengyun-4A (FY-4A) geostationary satellite using a Light Gradient Boosting Machine (LightGBM) model. The daytime cloud-sky SULR is estimated by applying the established relationship between auxiliary variables and clear-sky SULR to cloudy conditions, while the nighttime cloud-sky SULR values are estimated by applying the determined relationship between input variables and a publicly accessible, gap-filled SULR product. The model inputs include: 1) spatial-temporal location record data; 2) multiple surface characteristic parameters generated from previous-year data; and 3) two categories of operational FY-4A radiation products, with both components being available in real-time. Validation against six Heihe Watershed Allied Telemetry Experimental Research (HiWATER) sites demonstrates that the reconstructed cloud-sky SULR achieves acceptable root mean square error (RMSE) and mean bias error (MBE) values of 33.4 W/m2 (1.5 W/m2) for daytime and 25.2 W/m2 (4.7 W/m2) for nighttime conditions. Therefore, the proposed lightweight method could improve the spatial coverage of the current FY-4A SULR product and further promote real-time SULR-related 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":"2025-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145830838","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}
Infrared small target detection (IRSTD) remains a long challenging problem in infrared imaging technology. To enhance detection performance while more effectively exploiting target-specific characteristics, a novel U-shaped segmentation network called knowledge-embedded CSwin-UNet (KECS-Net) is proposed in this letter. KECS-Net first incorporates a CSwin transformer module into the encoder of the UNet backbone, enabling the extraction of multiscale features from infrared targets within an expanded receptive field, while achieving higher computational efficiency compared to the original Swin transformer. Besides, a multiscale local contrast enhancement module (MLCEM) is introduced, which utilizes hand-crafted dilated convolution operators to amplify locally salient target responses and suppress background noise, thereby guiding the model to focus on potential target regions. Finally, a slicing-aided hypersegmentation (SAHS) method is also designed to resize and rescale the output image, increasing the relative size of small targets and improving segmentation accuracy during inference. Extensive experiments on three benchmark datasets demonstrate that the proposed KECS-Net outperforms the state-of-the-art (SOTA) methods in both quantitative metrics and visual quality. Relevant code will be available at https://github.com/Lilingxiao-image/KECS-Net
{"title":"KECS-Net: Knowledge-Embedded CSwin-UNet With Slicing-Aided Hypersegmentation for Infrared Small Target Detection","authors":"Lingxiao Li;Linlin Liu;Dan Huang;Sen Wang;Xutao Wang;Yunan He;Zhuqiang Zhong","doi":"10.1109/LGRS.2025.3632827","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3632827","url":null,"abstract":"Infrared small target detection (IRSTD) remains a long challenging problem in infrared imaging technology. To enhance detection performance while more effectively exploiting target-specific characteristics, a novel U-shaped segmentation network called knowledge-embedded CSwin-UNet (KECS-Net) is proposed in this letter. KECS-Net first incorporates a CSwin transformer module into the encoder of the UNet backbone, enabling the extraction of multiscale features from infrared targets within an expanded receptive field, while achieving higher computational efficiency compared to the original Swin transformer. Besides, a multiscale local contrast enhancement module (MLCEM) is introduced, which utilizes hand-crafted dilated convolution operators to amplify locally salient target responses and suppress background noise, thereby guiding the model to focus on potential target regions. Finally, a slicing-aided hypersegmentation (SAHS) method is also designed to resize and rescale the output image, increasing the relative size of small targets and improving segmentation accuracy during inference. Extensive experiments on three benchmark datasets demonstrate that the proposed KECS-Net outperforms the state-of-the-art (SOTA) methods in both quantitative metrics and visual quality. Relevant code will be available at <uri>https://github.com/Lilingxiao-image/KECS-Net</uri>","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":"2025-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145612125","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}
Pub Date : 2025-11-14DOI: 10.1109/LGRS.2025.3632918
Tao Wang;Yong Fang;Shuangcheng Zhang;Bincai Cao;Qi Liu
The ice, cloud, and land elevation Satellite-2 (ICESat-2) has been operating continuously in orbit for nearly seven years. Its accuracy is crucial for ensuring the reliability of scientific applications. However, a few external studies have been conducted to assess the long-term consistency of ICESat-2 elevation measurements. In this letter, we evaluate the consistency of elevation accuracy through footprint-level crossover observations. This approach first extracts crossovers by averaging elevations within each ~12 m footprint, then analyzes their elevation differences using statistical and time-series approaches, and finally employs airborne LiDAR data for external validation. The results indicate that ICESat-2 elevation data exhibit excellent internal consistency over bare land areas from 2019 to 2024, with more than 40000 footprint-level crossovers, a mean elevation bias of 0.02 m, and a standard deviation of 0.22 m. The long-term drift of the elevation data is approximately 1.1 mm/yr, well within the mission’s scientific requirement of 4 mm/yr. Compared with airborne LiDAR, ICESat-2 maintains high external accuracy over long-term observations, with an overall root mean square error (RMSE) less than 0.38 m across 377 beam tracks. Overall, this study provides new and independent assessment of the consistency of ICESat-2 elevation data to date.
{"title":"Assessment of Long-Term Elevation Accuracy Consistency for ICESat-2/ATLAS Using Crossover Observations","authors":"Tao Wang;Yong Fang;Shuangcheng Zhang;Bincai Cao;Qi Liu","doi":"10.1109/LGRS.2025.3632918","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3632918","url":null,"abstract":"The ice, cloud, and land elevation Satellite-2 (ICESat-2) has been operating continuously in orbit for nearly seven years. Its accuracy is crucial for ensuring the reliability of scientific applications. However, a few external studies have been conducted to assess the long-term consistency of ICESat-2 elevation measurements. In this letter, we evaluate the consistency of elevation accuracy through footprint-level crossover observations. This approach first extracts crossovers by averaging elevations within each ~12 m footprint, then analyzes their elevation differences using statistical and time-series approaches, and finally employs airborne LiDAR data for external validation. The results indicate that ICESat-2 elevation data exhibit excellent internal consistency over bare land areas from 2019 to 2024, with more than 40000 footprint-level crossovers, a mean elevation bias of 0.02 m, and a standard deviation of 0.22 m. The long-term drift of the elevation data is approximately 1.1 mm/yr, well within the mission’s scientific requirement of 4 mm/yr. Compared with airborne LiDAR, ICESat-2 maintains high external accuracy over long-term observations, with an overall root mean square error (RMSE) less than 0.38 m across 377 beam tracks. Overall, this study provides new and independent assessment of the consistency of ICESat-2 elevation data to date.","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":"2025-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145612171","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}
Pub Date : 2025-11-14DOI: 10.1109/LGRS.2025.3632889
Jingyao Zhang;Xuerong Cui;Juan Li;Song Dai;Bin Jiang;Lei Li
Subsea pipelines are prone to exposure due to natural factors such as earthquakes and vortices, which necessitates regular condition monitoring. Multibeam echo sounders (MBESs) can provide high-precision seabed topographic information, while side-scan sonar (SSS) excels at capturing high-resolution seabed texture features. The integration of these two data sources can complement each other, thereby improving the detection accuracy of subsea pipelines. To achieve effective fusion, high-precision spatial registration is required. However, existing registration algorithms still face challenges such as uneven feature point distribution, dependence on prior knowledge, and unstable matching. This letter proposes a multisource sonar image registration algorithm for subsea pipelines, named a hierarchical feature structure-driven method for multisource sonar image registration of subsea pipelines (HFSM). First, the method designs a grid-based multiscale corner detection (MS-CD), which effectively enhances the spatial distribution balance of feature points. Next, a multiwindow geometric–texture joint feature descriptor (MW-GTD) is proposed, which combines direction-sensitive curvature and spatial shadow distribution features within different scale windows. Finally, a multilayer coarse-to-fine guided matching (ML-CFGM) strategy is introduced to enhance the matching stability of images in feature-sparse regions and realize multilayer feature matching. The superiority of the proposed method is validated with real-world data, providing technical support for the efficient registration of MBES and SSS images and subsea pipeline detection.
{"title":"HFSM: A Hierarchical Feature Structure-Driven Method for Multisource Sonar Image Registration of Subsea Pipelines","authors":"Jingyao Zhang;Xuerong Cui;Juan Li;Song Dai;Bin Jiang;Lei Li","doi":"10.1109/LGRS.2025.3632889","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3632889","url":null,"abstract":"Subsea pipelines are prone to exposure due to natural factors such as earthquakes and vortices, which necessitates regular condition monitoring. Multibeam echo sounders (MBESs) can provide high-precision seabed topographic information, while side-scan sonar (SSS) excels at capturing high-resolution seabed texture features. The integration of these two data sources can complement each other, thereby improving the detection accuracy of subsea pipelines. To achieve effective fusion, high-precision spatial registration is required. However, existing registration algorithms still face challenges such as uneven feature point distribution, dependence on prior knowledge, and unstable matching. This letter proposes a multisource sonar image registration algorithm for subsea pipelines, named a hierarchical feature structure-driven method for multisource sonar image registration of subsea pipelines (HFSM). First, the method designs a grid-based multiscale corner detection (MS-CD), which effectively enhances the spatial distribution balance of feature points. Next, a multiwindow geometric–texture joint feature descriptor (MW-GTD) is proposed, which combines direction-sensitive curvature and spatial shadow distribution features within different scale windows. Finally, a multilayer coarse-to-fine guided matching (ML-CFGM) strategy is introduced to enhance the matching stability of images in feature-sparse regions and realize multilayer feature matching. The superiority of the proposed method is validated with real-world data, providing technical support for the efficient registration of MBES and SSS images and subsea pipeline detection.","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":"2025-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145612163","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}
Current convolutional neural network (CNN)-based tiny object detectors in remote sensing commonly face a resolution transform bottleneck, characterized by irreversible feature information loss during downsampling and reconstruction distortions during upsampling. To address this issue, we propose a lightweight one-stage detector, small-object-aware intelligent lightweight detector (SAILDet). Its core principle is to preserve information fidelity at the source rather than compensating for its loss in downstream stages. This is achieved through a paired design that employs Haar wavelet downsampling (HWD) to retain high-frequency details at the source and Content-Aware ReAssembly of FEatures (CARAFE) to perform artifact-free, fine-grained upsampling, thereby establishing a high-fidelity feature processing loop. Experiments on the DOTA dataset demonstrate that, compared to the baseline model, SAILDet reduces GFLOPs and parameters by 11.7% and 13.0%, respectively, while improving mAP@50–95 from 0.263 to 0.266 and mAP@50 from 0.411 to 0.422. In addition, consistent gains are also observed on AI-TOD, reinforcing that directly optimizing the resolution-transform operators is more effective than downstream compensation.
{"title":"SAILDet: Wavelet-Preserved Lightweight One-Stage Detector for Tiny Objects in Remote Sensing","authors":"Jiaqi Ma;Hui Wang;Tianyou Wang;Haotian Li;Ruixue Xiao","doi":"10.1109/LGRS.2025.3631843","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3631843","url":null,"abstract":"Current convolutional neural network (CNN)-based tiny object detectors in remote sensing commonly face a resolution transform bottleneck, characterized by irreversible feature information loss during downsampling and reconstruction distortions during upsampling. To address this issue, we propose a lightweight one-stage detector, small-object-aware intelligent lightweight detector (SAILDet). Its core principle is to preserve information fidelity at the source rather than compensating for its loss in downstream stages. This is achieved through a paired design that employs Haar wavelet downsampling (HWD) to retain high-frequency details at the source and Content-Aware ReAssembly of FEatures (CARAFE) to perform artifact-free, fine-grained upsampling, thereby establishing a high-fidelity feature processing loop. Experiments on the DOTA dataset demonstrate that, compared to the baseline model, SAILDet reduces GFLOPs and parameters by 11.7% and 13.0%, respectively, while improving mAP@50–95 from 0.263 to 0.266 and mAP@50 from 0.411 to 0.422. In addition, consistent gains are also observed on AI-TOD, reinforcing that directly optimizing the resolution-transform operators is more effective than downstream compensation.","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":"2025-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145560639","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}
Pub Date : 2025-11-12DOI: 10.1109/LGRS.2025.3632153
Zhaoyu Liu;Wei Chen;Lixia Yang
To address core challenges in synthetic aperture radar (SAR) image target detection, including complex background interference, weak small-target features, and multiscale target coexistence, this study proposes the synthetic aperture-optimized real-time detection transformer (SA-RTDETR) model. The framework incorporates three core modules to enhance detection efficacy. First, the bidirectional receptive field boosting module synergistically integrates local details with global contextual information and substantially improves discriminative feature extraction while preserving spatial resolution. Second, the deformable attention-based intrascale feature interaction module employs adaptive sampling of critical scattering regions to address localization difficulties of small targets in SAR imagery. Third, the attention upsampling module mitigates detail loss and aliasing artifacts inherent in traditional interpolation methods through feature compensation strategies. Experimental results on the SARDet-100K dataset demonstrate that SA-RTDETR achieves 90.1% mAP@50, 56.0% mAP@50-95, and 84.7% recall rate representing improvements of 2.7%, 2.6%, and 2.2% over the baseline model, respectively. The end-to-end architecture enables high-precision SAR image analysis and offers considerable potential for military reconnaissance and maritime surveillance applications. The SA-RTDETR model establishes a novel technical paradigm for reliable all-weather remote sensing target detection by harmonizing feature robustness, scale adaptability, and operational efficiency.
{"title":"SA-RTDETR: A High-Precision Real-Time Detection Transformer Based on Complex Scenarios for SAR Object Detection","authors":"Zhaoyu Liu;Wei Chen;Lixia Yang","doi":"10.1109/LGRS.2025.3632153","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3632153","url":null,"abstract":"To address core challenges in synthetic aperture radar (SAR) image target detection, including complex background interference, weak small-target features, and multiscale target coexistence, this study proposes the synthetic aperture-optimized real-time detection transformer (SA-RTDETR) model. The framework incorporates three core modules to enhance detection efficacy. First, the bidirectional receptive field boosting module synergistically integrates local details with global contextual information and substantially improves discriminative feature extraction while preserving spatial resolution. Second, the deformable attention-based intrascale feature interaction module employs adaptive sampling of critical scattering regions to address localization difficulties of small targets in SAR imagery. Third, the attention upsampling module mitigates detail loss and aliasing artifacts inherent in traditional interpolation methods through feature compensation strategies. Experimental results on the SARDet-100K dataset demonstrate that SA-RTDETR achieves 90.1% mAP@50, 56.0% mAP@50-95, and 84.7% recall rate representing improvements of 2.7%, 2.6%, and 2.2% over the baseline model, respectively. The end-to-end architecture enables high-precision SAR image analysis and offers considerable potential for military reconnaissance and maritime surveillance applications. The SA-RTDETR model establishes a novel technical paradigm for reliable all-weather remote sensing target detection by harmonizing feature robustness, scale adaptability, and operational efficiency.","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":"2025-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145612118","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}
Pub Date : 2025-11-12DOI: 10.1109/LGRS.2025.3631806
Haoxuan Xu;Meiguo Gao
Marine radar is widely employed in ocean monitoring systems. However, sea clutter significantly impairs radar data interpretability and degrades maritime target detection performance. Effective clutter suppression methods are thus essential to enhance target characteristics for improved detection. However, environmental sea clutter often exhibits complex statistical characteristics, causing traditional model-based methods to suffer from performance degradation. To address this challenge, this letter proposes a sea clutter suppression method based on a complex-valued neural network (CVNN). First, the network incorporates a wavelet convolution (WTConv) block to expand the receptive field. Second, complex-valued convolutional blocks integrated with an attention mechanism are designed to enhance latent feature extraction. Finally, the model’s performance is rigorously validated using real-measured data. Experimental results demonstrate that the proposed model achieves superior clutter suppression performance.
{"title":"An End-to-End Sea Clutter Suppression Method Using Wavelet Convolution-Enhanced Attentional Complex-Valued Neural Network","authors":"Haoxuan Xu;Meiguo Gao","doi":"10.1109/LGRS.2025.3631806","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3631806","url":null,"abstract":"Marine radar is widely employed in ocean monitoring systems. However, sea clutter significantly impairs radar data interpretability and degrades maritime target detection performance. Effective clutter suppression methods are thus essential to enhance target characteristics for improved detection. However, environmental sea clutter often exhibits complex statistical characteristics, causing traditional model-based methods to suffer from performance degradation. To address this challenge, this letter proposes a sea clutter suppression method based on a complex-valued neural network (CVNN). First, the network incorporates a wavelet convolution (WTConv) block to expand the receptive field. Second, complex-valued convolutional blocks integrated with an attention mechanism are designed to enhance latent feature extraction. Finally, the model’s performance is rigorously validated using real-measured data. Experimental results demonstrate that the proposed model achieves superior clutter suppression performance.","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":"2025-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145612148","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}
Pub Date : 2025-11-12DOI: 10.1109/LGRS.2025.3631871
Haotian Li;Jiaqi Ma;Wenna Guo;Xiaoxia Li;Xiaohui Qin;Zhenhua Ma
With the rapid development of applications such as unmanned aerial vehicle (UAV)-based remote sensing, smart cities, and intelligent transportation, small-object detection has become increasingly important in the field of object recognition. However, existing methods often struggle to balance detection accuracy and inference efficiency under large-scale variations, dense small-object distributions, and complex background interference. To address these challenges, this letter proposes a lightweight perception subnetwork, RSNet-Lite. The network integrates a multiscale attention mechanism to enhance small-object perception, dynamic convolution, and long-range spatial modeling units to improve feature representation, and lightweight convolution with efficient sampling strategies to significantly reduce computational complexity. As a result, RSNet-Lite achieves real-time inference while maintaining high detection accuracy, striking a balance between speed and performance. Finally, the proposed method is validated on the Aerial Image–Tiny Object Detection (AI-TOD) and Vision Meets Drone (VisDrone) datasets, demonstrating its effectiveness and strong potential for small-object detection tasks.
{"title":"RSNet-Lite: A Lightweight Perception Subnetwork for Remote Sensing Object Detection","authors":"Haotian Li;Jiaqi Ma;Wenna Guo;Xiaoxia Li;Xiaohui Qin;Zhenhua Ma","doi":"10.1109/LGRS.2025.3631871","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3631871","url":null,"abstract":"With the rapid development of applications such as unmanned aerial vehicle (UAV)-based remote sensing, smart cities, and intelligent transportation, small-object detection has become increasingly important in the field of object recognition. However, existing methods often struggle to balance detection accuracy and inference efficiency under large-scale variations, dense small-object distributions, and complex background interference. To address these challenges, this letter proposes a lightweight perception subnetwork, RSNet-Lite. The network integrates a multiscale attention mechanism to enhance small-object perception, dynamic convolution, and long-range spatial modeling units to improve feature representation, and lightweight convolution with efficient sampling strategies to significantly reduce computational complexity. As a result, RSNet-Lite achieves real-time inference while maintaining high detection accuracy, striking a balance between speed and performance. Finally, the proposed method is validated on the Aerial Image–Tiny Object Detection (AI-TOD) and Vision Meets Drone (VisDrone) datasets, demonstrating its effectiveness and strong potential for small-object detection tasks.","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":"2025-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145612151","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：