IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing最新文献

{"title":"Deep Learning-Based Interpolation for Ground Penetrating Radar Data Reconstruction","authors":"Ziyang Zhou;Meijia Huang;Hong Xu;Xinyu Yang;Yinpeng Li;Zhuo Jia","doi":"10.1109/JSTARS.2025.3543256","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3543256","url":null,"abstract":"Ground Penetrating Radar (GPR), with its high resolution and real-time monitoring capabilities, is widely used in fields such as underground structure detection, archaeological excavation, environmental monitoring, and engineering surveying. However, the complexity of the subsurface, such as geological heterogeneity and inhomogeneity, can cause signal attenuation or incomplete reflection. In addition, external factors like electromagnetic interference, temperature fluctuations, or other noise can result in data loss or anomalies. To address these challenges, this article proposes a deep learning-based interpolation method for GPR data. Convolutional Neural Networks (CNNs) are used to learn signal patterns from large datasets, enabling the model to predict missing data and restore the integrity and continuity of the GPR data. Deep learning models also capture complex nonlinear features in GPR data, identifying underlying patterns and correlations. In noisy or high-reflection environments, these methods offer more precise interpolation, significantly improving data quality. Experiments on both synthetic and real-world data show that the deep learning method effectively recovers GPR data features, enhances data continuity and integrity, and reduces interpolation errors. The method exhibits strong adaptability and high-precision performance, making it effective in complex underground structures and varying environments. Whether with synthetic or real-world data, deep learning provides a reliable solution for GPR data processing.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"6329-6335"},"PeriodicalIF":4.7,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10891706","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143564203","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A New Fast Sparse Unmixing Algorithm Based on Adaptive Spectral Library Pruning and Nesterov Optimization","authors":"Kewen Qu;Fangzhou Luo;Huiyang Wang;Wenxing Bao","doi":"10.1109/JSTARS.2025.3541257","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3541257","url":null,"abstract":"In recent years, hyperspectral sparse unmixing (HSU) has garnered extensive research and attention due to its unique characteristic of not requiring the estimation of endmembers and their number. However, the high coherence and large-scale nature of the prior spectral library frequently lead to substantial computational costs and limited unmixing accuracy in the optimization model, thereby hindering the efficiency and further promotion of HSU in practical engineering applications. To address these shortcomings, this article proposes a new fast two-step sparse unmixing algorithm, called NeSU-LP, which is based on adaptive spectral library pruning technology and the Nesterov fast optimization strategy. In this method, HSU is divided into two independent and consecutive subprocesses: coarse unmixing and fine unmixing. Specially, first, in the coarse unmixing stage, we design a sparse optimization model based on the initial large spectral library, requiring only a few iterations to initially estimate the row-sparse abundance matrix. Subsequently, the proposed atomic (i.e., endmember) activity evaluation method is utilized to screen the active endmembers, analyze the abundance matrix, and prune the endmembers in the spectral library. Irrelevant endmembers are removed, reducing the spectral library size and generating a low-coherence, small-scale endmember matrix. Finally, in the fine unmixing process, we retain the effective atomic abundance rows obtained in the previous stage and design the final fine hyperspectral unmixing model based on the pruned, small-scale endmember matrix. In addition, to enhance the smoothness of the abundance maps, graph Laplacian regularization is introduced during the fine unmixing stage. The Nesterov fast gradient strategy is employed to accelerate the iterative process of fine unmixing, ultimately achieving second-order convergence efficiency for the algorithm. Numerous experiments were conducted on both synthetic and real datasets, comparing them with state-of-the-art methods. The experimental results demonstrate the high efficiency and advancement of the proposed method.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"6134-6151"},"PeriodicalIF":4.7,"publicationDate":"2025-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10887113","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143564201","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Kriging Interpolation-Enhanced MART for Nonuniform Observational Data in Geosynchronous SAR-Based Computerized Ionospheric Tomography","authors":"Yi Sui;Xichao Dong;Yuanhao Li;Zhiyang Chen;Cheng Hu","doi":"10.1109/JSTARS.2025.3542074","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3542074","url":null,"abstract":"The ionosphere affects spaceborne synthetic aperture radar (SAR) and Global Navigation Satellite System (GNSS) missions, and reflects solar activity and Earth magnetic field, making its monitoring essential. Computerized ionospheric tomography (CIT) is a key technique for this application, using total electron content (TEC) along signal paths to reconstruct electron density. Unlike GNSS-based CIT using ground receivers, and low Earth orbit (LEO) SAR-based CIT limited by coverage and revisit time, geosynchronous (GEO) SAR-based CIT directly reconstructs ionospheric electron density using TEC from ground permanent scatterer (PS) points. The high orbit, wide coverage, and short revisit time of GEO SAR enable observation of the full vertical ionosphere structure and larger areas with better time resolution. However, GEO SAR-based CIT faces challenges due to the nonuniform distribution of PS points, leading to significant spatial differences in tomographic quality, making it difficult to provide reliable data support for subsequent research. To address this, a Kriging interpolation-enhanced multiplicative algebraic reconstruction technique (MART) is proposed. This proposed method embeds Kriging interpolation into the conventional MART iteration, utilizing the spatial correlation of electron density to compensate for voxels with sparse TEC data, while still incorporating the voxel's own TEC data. This improves the electron density reconstruction accuracy and robustness. Finally, both simulation and real GNSS data experiments demonstrate that the proposed method significantly improves reconstruction in data-sparse voxels and reduces spatial differences in electron density estimation quality compared to conventional method, albeit with a slight tradeoff in accuracy for a small number of voxels.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"6600-6616"},"PeriodicalIF":4.7,"publicationDate":"2025-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10887358","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143553367","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enabling Advanced Land Cover Analytics: An Integrated Data Extraction Pipeline for Predictive Modeling With the Dynamic World Dataset","authors":"Victor Radermecker;Andrea Zanon;Nancy Thomas;Annita Vapsi;Saba Rahimi;Rama Ramakrishnan;Daniel Borrajo","doi":"10.1109/JSTARS.2025.3542282","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3542282","url":null,"abstract":"Understanding land cover holds considerable potential for a myriad of practical applications, particularly as data accessibility transitions from being exclusive to governmental and commercial entities to now including the broader research community. Nevertheless, although the data is accessible to any community member interested in exploration, there exists a formidable learning curve and no standardized process for accessing, preprocessing, and leveraging the data for subsequent tasks. In this study, we democratize this data by presenting a flexible and efficient end-to-end pipeline for working with the Dynamic World dataset, a cutting-edge near-real-time land use/land cover (LULC) dataset. This includes a preprocessing and representation framework which tackles noise removal, efficient extraction of large amounts of data, and re-representation of LULC data in a format well suited for several downstream tasks. To demonstrate the power of our pipeline, we use it to extract data for an urbanization prediction problem and build a suite of machine learning models with excellent performance. This task is easily generalizable to the prediction of any type of land cover and our pipeline is also compatible with a series of other downstream tasks. To facilitate further research and validation, all code and data used in this study are made available online.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"6440-6450"},"PeriodicalIF":4.7,"publicationDate":"2025-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10887251","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143553133","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Wilcoxon Nonparametric CFAR Scheme for Ship Detection in SAR Image","authors":"Xiangwei Meng","doi":"10.1109/JSTARS.2025.3533140","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3533140","url":null,"abstract":"The parametric constant false alarm rate (CFAR) detection algorithms, which are based on various statistical distributions, such as Gaussian, Gamma, Weibull, log-normal, <inline-formula><tex-math>$G^{0}$</tex-math></inline-formula>, and alpha-stable distribution, are most widely used to detect the ship targets in SAR images at present. However, the clutter background in SAR images is complicated and variable. When the actual clutter background deviates from the assumed statistical distribution, the performance of the parametric CFAR detector deteriorates, whereas the advantage of the nonparametric CFAR detector that its false alarm rate is independent of the background distribution is exhibited. In this work, the Wilcoxon nonparametric CFAR scheme for the ship detection in SAR images is proposed and analyzed, and a closed form of the false alarm rate for the Wilcoxon nonparametric CFAR detector to determine the decision threshold is presented. By comparison with several typical parametric CFAR schemes on Sentinel-1A, ICEYE-X6, and Gaofen-3 SAR images, the robustness of the ability of the Wilcoxon nonparametric CFAR detector to control the actual false alarm rate at a suitably low level in different detection backgrounds is revealed, and its detection performance for the weak ships in the rough sea backgrounds is evidently improved. Moreover, the detection speed of the Wilcoxon nonparametric CFAR detector is fast, and it has a simple hardware implementation.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"5360-5377"},"PeriodicalIF":4.7,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10886933","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143489141","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Early Forest Fire Detection With UAV Image Fusion: A Novel Deep Learning Method Using Visible and Infrared Sensors","authors":"Kunlong Niu;Chongyang Wang;Jianhui Xu;Jianrong Liang;Xia Zhou;Kaixiang Wen;Minjian Lu;Chuanxun Yang","doi":"10.1109/JSTARS.2025.3541205","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3541205","url":null,"abstract":"Global warming has significantly increased the frequency of forest fires. Unmanned aerial vehicles (UAVs) provide rapid response and real-time monitoring, offering unique advantages over traditional human inspections and satellite monitoring. Their ability to monitor large forest areas during the early stages of fires supports timely warning. UAVs typically detect fires by capturing visible and infrared images. Visible images are effective for smoke detection but are influenced by environmental factors, while infrared images are better at detecting heat but can misidentify fires when the temperature difference between the fire and its surroundings is minimal. Additionally, challenges in image registration often occur when aligning the two image types for fusion. Therefore, this research proposes a novel method to early forest fire detection by fusing visible and infrared images and creating a dataset. The main contributions include: 1) the creation of a dataset containing 2752 synchronized visible and infrared image pairs to overcome existing dataset limitations; 2) the application of deep learning techniques to enhance image registration and fusion, incorporating an improved algorithm that increases automation; and 3) the development of the Forest Fire Detection Model—Fusion (FFDM-F) model, based on YOLOv5s and fused images, designed to accurately detect small fires at their early stages. The results show that the improved registration method effectively aligns visible and infrared images, optimizing the fusion process and enhancing the use of multisource information. Additionally, FFDM-F achieves over a 10% improvement in precision for small fire detection compared to traditional methods and reduces misidentifications associated with single-source images. This research contributes to multisource image fusion for forest fire detection, providing a more accurate and reliable early warning tool and laying the foundation for future work in this field.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"6617-6629"},"PeriodicalIF":4.7,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10884036","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143553290","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An Improved Man-Made Structure Detection Method for Multi-aspect Polarimetric SAR Data","authors":"Fabin Dong;Qiang Yin;Wen Hong","doi":"10.1109/JSTARS.2025.3532018","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3532018","url":null,"abstract":"Multiaspect polarimetric synthetic aperture radar (SAR) captures the polarimetric properties of targets from various observational aspects. The comprehensive multiaspect scattering characteristics are valuable for man-made structure detection and classification. Typically, the anisotropic scattering of targets could be characterized by the differences in the statistical properties of polarimetric data across aspects. However, both the statistical similarities in man-made structures and variabilities in natural targets at different aspects can negatively impact the ability to distinguish between them. Consequently, relying solely on anisotropic analysis may not yield favorable man-made structure detection results. Since man-made structures usually include special shapes, such as dihedral angle, there are significant variations in scattering power across different aspects. Therefore, this article proposes an improved man-made structure detection method that integrates scattering power characteristics and anisotropic features. First, to highlight differences between aspects, this article introduces a similarity matrix to perform azimuth sequence filtering. Subsequently, anisotropic features are extracted through differences in statistical distribution, and scattering power characteristics at individual aspects, along with their variations, are extracted using the fuzzy C-means clustering combined with spatial neighborhood. Two different features are fused to distinguish man-made structures from natural targets. Finally, the most significant azimuth aspect is determined by comparing the scattering contributions of individual subapertures. Experimental verification with airborne circular polarimetric SAR data confirms that the multifeature fusion method, following azimuth sequence filtering, effectively improves the detection of man-made structures and their most anisotropic subapertures.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"5717-5732"},"PeriodicalIF":4.7,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10886939","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143480745","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Mapping Urban Areas and Infrastructure Through Fusion of Airborne SAR 3-D Images: A Comparative Study With ALS Sensors","authors":"Elías Méndez Domínguez;Peter Brotzer;Emiliano Casalini;David Small","doi":"10.1109/JSTARS.2025.3541425","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3541425","url":null,"abstract":"3-D urban maps from optical, LiDAR, or synthetic aperture radar (SAR) data are crucial for urban planning, solar panel installation, visibility analysis, and shadow estimation. Digital surface models (DSMs) from airborne laser scanning (ALS) serve as high-quality references but often lack wall information and exhibit gaps in vertical structures. This study explores the effectiveness of airborne SAR in mapping complex urban geometries and compares the results to ALS data, including point clouds and DSMs. We also propose a framework for fusing 3-D SAR and ALS data to enhance the accuracy of 3-D city models. This fusion approach ensures precise alignment, reduces outliers near walls, rooftops, and ground surface (commonly caused by SAR phase noise) and preserves valuable information about walls and vertical structures absent in ALS data. Given the diversity of urban areas, we performed class-specific analyses (ground, trees, buildings, and power lines). Multiaspect SAR was found to be critical for addressing radar shadows and gaps caused by nonbackscattering objects. Using six SAR aspects covering <inline-formula><tex-math>$270^{circ }$</tex-math></inline-formula> provided comprehensive 3-D data, minimizing the need to consider building orientation. While SAR and LiDAR provided similar scene information, only 30% of voxels contained the same information from both sources, highlighting their complementary nature. Datasets with more SAR aspects proved more informative than those with fewer aspects and more baselines. Ground and tree reconstructions benefited from multiple baselines due to the resolution of low-backscattering objects, whereas building and power line reconstruction showed minimal improvement. The findings suggest that a combination of ALS and SAR data is essential for a complete understanding of urban environments.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"6164-6181"},"PeriodicalIF":4.7,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10884047","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143521457","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"GACNet: A Geometric and Attribute Co-Evolutionary Network for Citrus Tree Height Extraction From UAV Photogrammetry-Derived Data","authors":"Haiqing He;Fuyang Zhou;Yongjun Zhang;Ting Chen;Yan Wei","doi":"10.1109/JSTARS.2025.3541395","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3541395","url":null,"abstract":"The undulating terrain and complex backgrounds of citrus plantations introduce nonlinear variations that significantly impede the high-precision estimation of citrus tree heights from remote sensing data. To overcome these obstacles, we introduce a novel geometric and attribute co-evolutionary network, tailored for extracting citrus tree heights using unmanned aerial vehicle photogrammetry-derived data. Our approach integrates a multisource feature interaction module with a multisource feature aggregation module, fostering the co-evolution of deep feature responses across various datasets. Notably, this includes a sophisticated triple-feature interaction mechanism that considers position, channel, and spatial correlation to enhance the aggregation of geometric features. In addition, we employ a multilevel feature aggregation decoder leveraging cross-attention, ensuring attribute context consistency and facilitating efficient tree height extraction. Quantitative analysis across datasets reveals our method's superior performance, with a 2% –7% increase in mean intersection over union for canopy segmentation and a robust correlation of 0.77 between estimated and reference tree heights, accompanied by an MAE of 0.25 m and an RMSE of 0.38 m. Comparative experiments indicate that our method outperforms current state-of-the-art networks, showing resilience to terrain undulations and offering reliable cross-region and cross-scale tree height estimation capabilities.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"6363-6381"},"PeriodicalIF":4.7,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10884035","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143564202","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Oriented Bounding Box Representation Based on Continuous Encoding in Oriented SAR Ship Detection","authors":"Peng Li;Cunqian Feng;Weike Feng;Xiaowei Hu","doi":"10.1109/JSTARS.2025.3541217","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3541217","url":null,"abstract":"Ship detection of synthetic aperture radar (SAR) images holds significant value for both civilian and military applications. Compared to horizontal ship detection, oriented ship detection based on oriented bounding boxes can capture the orientation and aspect ratio of ships, thus receiving increasing attention. However, in oriented ship detection, when ships rotate near the specific angles, the angle prediction result obtained by the deep learning network may have a severe mutation, which is the well-known boundary discontinuity problem. To address the issue of boundary discontinuity in SAR ship detection, researchers have proposed numerous methods. However, through our systematic analysis, we found that these methods do not fundamentally solve the problem. To this end, we first clarified the reasons for the existence of boundary discontinuity and how it affects the detection network. Based on this, we proposed the conditions that the encoding methods and loss functions of the detection network must satisfy to address the issue of boundary discontinuity. In line with these conditions, we designed a continuous encoding method called coordinate decomposition method (CDM). In addition, we also analyzed the impact of different optimization methods on the detection network and, based on this, presented a joint optimization paradigm based on continuous encoding. Experimental results on two commonly used SAR ship detection datasets demonstrate that our proposed CDM encoding method effectively addresses the boundary discontinuity issue and enhances the detection performance. Compared to the state-of-the-art methods, the fully convolutional one-stage network using the CDM-based joint optimization achieves optimal detection results without employing any additional techniques.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"6350-6362"},"PeriodicalIF":4.7,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10884059","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143563973","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}