{"title":"Control Network Construction for LRO NAC Images Based on Refining Tie Points by Matching With Shaded LOLA DEM","authors":"Sifen Wang;Xun Geng;Jiansheng Li;Tao Li;Junming Yu;Ancheng Wang;Jin Wang;Pengying Liu;Zhen Peng;Xin Ma;Yinhui Wang;Yuying Wang;Guohua Chang","doi":"10.1109/JSTARS.2025.3616321","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3616321","url":null,"abstract":"The upcoming exploration activities in the lunar south pole require high-resolution mapping products to support landing site selection and navigation. The special terrain and illumination conditions in the lunar south pole pose significant challenges to photogrammetric processing. Existing lunar mapping products exhibit limited coverage and accuracy in the south pole region and cannot meet the exploration missions’ requirements. In this study, a new control network construction method is proposed based on refining tie points by image matching between the approximate orthophotos of lunar reconnaissance orbiter narrow-angle camera (NAC) images and shaded digital elevation model (DEM) maps. The shaded DEM maps are generated using lunar orbiter laser altimeter terrain models with the same acquisition time of on-orbit NAC images, making them have very similar illumination conditions to the on-orbit images. Using the shaded DEM maps as a transition, we establish the coordinate transformation relationship between the stereopairs of NAC images by computing the homograph transformation matrix in orthophoto space. Then, the candidate control measures in the control network are refined in orthophoto space and then converted to the original image space. We conducted experiments using two sets of NAC images near the lunar south pole. The experimental results demonstrate that the proposed method can effectively solve the problems of image matching and control network generation for lunar south pole images.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"25512-25531"},"PeriodicalIF":5.3,"publicationDate":"2025-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11185283","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145315282","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":"Frequency Characteristics Guided Network for Few-Shot SAR Target Recognition","authors":"Fei Gao;Fengjun Zhong;Rongling Lang;Jun Wang;Jinping Sun;Amir Hussain","doi":"10.1109/JSTARS.2025.3617129","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3617129","url":null,"abstract":"Contemporary research in synthetic aperture radar (SAR) automatic target recognition (ATR) reveals that few-shot learning algorithms can attain exceptional classification accuracy through training paradigms employing several hundred to thousands of sample inputs. However, existing methods ignore the frequency characteristics in radar images and only rely on the similarity of pixel descriptors for target recognition. To overcome this limitation, this article presents frequency characteristics guided network (FCGN), an architecture explicitly developed for SAR ATR scenarios with limited training samples. First, we propose a frequency-separated feature extractor, which enriches the frequency characteristics of the target. In addition, FCGN further incorporates a frequency-domain sample expander, a dedicated component for generating spectrally congruent pseudosamples that enhance support set heterogeneity, ultimately refining class separation boundaries in the latent representation space. Finally, we propose an adaptive frequency-domain matcher (AFDM). AFDM calculates the inter-sample frequency-domain consistency through selected frequency components, and the network synthesizes the pixel consistency and frequency-domain consistency to discriminate the samples. Rigorous evaluation on the moving and stationary target acquisition and recognition dataset demonstrate that the proposed method surpasses current approaches.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"25821-25832"},"PeriodicalIF":5.3,"publicationDate":"2025-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11190030","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145315291","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 Investigation of Systematic Bias in ALOS-2 Multilooked Interferograms","authors":"Ryu Sugimoto;Yu Morishita;Masanobu Shimada;Ryo Natsuaki;Chiaki Tsutsumi;Ryosuke Nakamura;Toru Kouyama","doi":"10.1109/JSTARS.2025.3617173","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3617173","url":null,"abstract":"Interferometric synthetic aperture radar (SAR) measurements are affected by systematic bias, referred to as “fading signal,” when explicitly using temporally short-term and spatially multilooked interferograms. Investigations using extensive time-series data from the Sentinel-1 <italic>C</i>-band SAR have identified soil moisture and biomass changes as potential causes of the observed biases. Although phase biases are supposed to increase with increasing wavelengths, detailed studies on the biases observed in Advanced Land Observing Satellite-2 (ALOS-2) <italic>L</i>-band SAR have been limited due to restrictive data distribution policies. We, therefore, investigated the systematic bias in ALOS-2 multilooked interferograms across various interferometric pairs and land-cover types over five years of its observation. With regard to the behavior of the bias for positive and negative variations in soil moisture, our results demonstrated consistency with simulations performed using an interferometric model for soil moisture. The observed bias was >4 mm/year for an average temporal baseline of 72 days. Our research suggested by using <italic>L</i>-band SAR that the observed bias can be attributed to changes in both soil moisture and biomass. Furthermore, we developed a methodology to mitigate the systematic bias in ALOS-2 multilooked interferograms. This methodology utilizes our findings that a noise-filtering technique proposed by Pepe et al. (2015) can overcome these biases through the utilization of medium-term interferograms and redundant triplets, regardless of the land-cover type.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"25605-25615"},"PeriodicalIF":5.3,"publicationDate":"2025-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11189979","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145315294","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":"EMViT-DDPM: An Equilibrium-Based ViT Diffusion Framework for Data Augmentation in Multispectral Land Cover Classification","authors":"Víctor Barreiro;Dora B. Heras;Francisco Argüello","doi":"10.1109/JSTARS.2025.3617098","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3617098","url":null,"abstract":"The scarcity and imbalance of labeled samples, common in remote sensing datasets, pose significant challenges for accurate analysis and classification, often leading to substantial bias against minority classes. To address these issues, we propose EMViT-DDPM, an equilibrium-based data augmentation framework leveraging vision transformer (ViT)-based denoising diffusion probabilistic models (DDPMs). Unlike generative adversarial network (GAN)-based augmentation techniques commonly found in the literature, our framework is not tied to any specific classifier. It leverages a ViT architecture enhanced with the AdaLN block, which is designed to minimize computational costs while effectively capturing data complexity. By adopting diffusion models (DDPMs), the framework achieves greater training robustness, improved generalization, and better quality control over generated samples compared to GANs. To address class imbalance, we introduce equilibrium-based data augmentation (), which assigns different augmentation proportions to each class based on their respective sizes. In addition, a superpixel-based segmentation preprocessing step is proposed for patch generation, tailoring the data augmentation method specifically to high-spatial-resolution multispectral remote sensing imagery. Finally, we propose a novel strategy for the evaluation of data-augmentation quality, based on a new judge model trained over balanced classes. This allows a more precise evaluation of Fréchet inception distance, precision (fidelity), and recall (diversity).","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"25923-25938"},"PeriodicalIF":5.3,"publicationDate":"2025-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11189980","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145315284","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 Radargrammetry Algorithm for High-Resolution SAR Satellite Constellations","authors":"Steven Beninati;Stephen Frasier","doi":"10.1109/JSTARS.2025.3616765","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3616765","url":null,"abstract":"The recent development of commercial high-resolution synthetic aperture radar (SAR) satellite constellations provides the opportunity to acquire SAR data with resolutions of 1 m or less with a high temporal repeat rate. One potential use of this technology is the construction of high-resolution digital surface models (DSMs) for use in monitoring rapid topographic changes, for example, coastal erosion caused by a hurricane landfall. Here, we describe a stereo radargrammetry algorithm that is well suited to imagery collected from both parallel and crossing orbit geometries. An epipolar geometry is described to enable its efficient operation. An open-source implementation of the algorithm has been published. DSMs from three coastal test sites with varying terrain properties and surface features are generated from SAR imagery collected in a variety of imaging modes. The DSMs generated from all configurations demonstrate good agreement with reference elevation models, even in low relief regions, with comparable performance for parallel and crossing orbits. A comparison of a radargrammetric DSM to a lidar surface model shows the algorithm can accurately measure heights in vegetated and nonvegetated coastal areas, which may be useful for damage assessment and change detection tasks following landfall.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"25480-25493"},"PeriodicalIF":5.3,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11186229","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145315300","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 Pixel-Object-Knowledge-Based Approach for Fine-Grained Coastal Wetland Mapping: A Case Study of Shandong Province","authors":"Huaqiao Xing;Honglei Du;Linye Zhu;Tongwen Liu;Bingyao Chen;Peiyuan Qiu","doi":"10.1109/JSTARS.2025.3616117","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3616117","url":null,"abstract":"Wetlands play a crucial role as key ecosystems in water quality purification, carbon storage, and biodiversity conservation. To achieve effective protection and scientific management of wetlands, precise and accurate wetland mapping is of utmost importance. Existing high-resolution wetland classification methods still face significant challenges in boundary identification and type differentiation, particularly in complex terrains and areas with high spectral similarity between wetland types. To address these issues, this study proposed a pixel-object-knowledge-based wetland mapping (POK-WM) method. The POK-WM method overcomes the limitation of traditional approaches that rely solely on spectral information by integrating pixel-level spectral features, object-level spatial features, and regional knowledge rules, enabling accurate mapping of seven wetland types in the coastal areas of Shandong Province. Based on validation with test samples, the wetland map achieved an overall accuracy of 90.4% and a Kappa coefficient of 0.89. Compared with datasets such as EA, GLC_FCS, and GLWD, the POK-WM method demonstrates superior performance in wetland type identification and boundary clarity in complex regions, indicating that the integration of pixel–object–knowledge offers significant advantages in improving classification accuracy and spatial consistency. This provides reliable data support for the systematic mapping of complex coastal wetlands as well as regional wetland conservation and ecological management.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"25464-25479"},"PeriodicalIF":5.3,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11185199","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145315298","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":"DAH-TrafficRSNet: Dual-Branch Traffic Remote Sensing Image Dehazing Network Based on Atmospheric Scattering Model and Hierarchical Feature Interaction","authors":"Meiyi Liu;Kaichen Chi;Chuchuan You","doi":"10.1109/JSTARS.2025.3616248","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3616248","url":null,"abstract":"Fog degrades the quality of traffic remote sensing images and severely restricts their applications in scenarios such as intelligent traffic monitoring and road network planning and evaluation. This article proposes a dual-branch traffic remote sensing image dehazing network (DAH-TrafficRSNet), which integrates the advantages of prior-based methods and deep learning to address the clarity degradation caused by fog. The network is based on a dual-branch architecture. One branch incorporates the atmospheric scattering model (ASM), which preliminarily estimates and corrects fog-induced degradation, providing a physical basis for restoring key elements such as road textures and vehicle shapes. The other branch adopts a hierarchical feature interaction mechanism, excavating image features at multiple scales and levels to enhance the ability to capture details like airport runway lengths and tarmac partitions in complex foggy environments. Experimental results show that DAH-TrafficRSNet performs excellently on remote sensing image datasets of various traffic scenes. Compared with traditional dehazing methods and some advanced deep learning-based dehazing models, it can remove fog more effectively, accurately restore road connectivity and vehicle integrity, and significantly improve image visual quality as well as the accuracy of analytical tasks such as road condition evaluation. This provides reliable support for the practical application of remote sensing technology in the field of intelligent transportation.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"25325-25337"},"PeriodicalIF":5.3,"publicationDate":"2025-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11184800","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145315285","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":"CSIFT: A Structural Feature Encoding Framework for Cross-Modal Image Registration","authors":"Lipeng Lian;Leping Chen;Daoxiang An","doi":"10.1109/JSTARS.2025.3616220","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3616220","url":null,"abstract":"Multimodal sensor collaborative detection serves as an indispensable complementary technology in Earth observation. However, significant cross-modal discrepancies in multimodal images severely limit the operational efficiency and alignment accuracy of traditional registration methods. Feature-based multimodal image registration techniques struggle to maintain stable performance across different modalities due to inherent radiometric differences. To address this limitation, this article proposes a cross-modal structural information feature transform (CSIFT) framework by optimizing intermediate modality construction. The method employs the oriented FAST and rotated BRIEF detector to extract keypoints and construct circular Gaussian-weighted oriented gradient features (CGOGFs) through a Gaussian-weighted directional gradient allocation mechanism applied to neighborhood information. The gradient magnitude distribution based on annular distance eliminates truncation effects caused by linear interpolation, while principal direction-aligned blocks ensure rotational consistency. By transforming cross-modal registration into a homogeneous feature matching problem through structural feature encoding, experimental results demonstrate that CGOGF significantly enhances cross-modal performance while preserving information integrity compared to traditional methods. Extensive evaluations on two public datasets show that CSIFT achieves the highest success rates (97.58% and 97.19% ) across various multimodal datasets, outperforming multiple traditional registration approaches.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"25688-25701"},"PeriodicalIF":5.3,"publicationDate":"2025-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11184767","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145315382","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}
Can Lu;Feng Wang;Zhen Wang;Nan Xu;Zhuhong You;De-Shuang Huang
{"title":"BWFNet: Bitemporal Wavelet Frequency Network for Change Detection in High-Resolution Remote Sensing Images","authors":"Can Lu;Feng Wang;Zhen Wang;Nan Xu;Zhuhong You;De-Shuang Huang","doi":"10.1109/JSTARS.2025.3615241","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3615241","url":null,"abstract":"Accurate change detection in high-resolution remote sensing images is essential for a wide range of Earth observation tasks. However, current deep learning (DL)-based methods often struggle with detecting subtle changes, maintain limited robustness to temporal and environmental variations, and face challenges in balancing global semantic understanding with precise boundary localization. To address these issues, we propose bitemporal wavelet frequency network (BWFNet), a novel hybrid architecture that integrates four dedicated modules to systematically improve change detection performance. Specifically, the cosine directional convolution module (CDCM) enhances the extraction of directional and structural features, while the bitemporal cross-modulation mechanism (BCMM) adaptively fuses semantic information from bitemporal images to emphasize relevant changes. The multiscale feature refinement module (MSFM) aggregates and refines features at multiple scales for comprehensive spatial representation, and the wavelet frequency attention mechanism (WFAM) selectively highlights discriminative frequency components via wavelet decomposition to improve sensitivity to subtle and complex changes. Extensive experiments on four public remote sensing change detection benchmarks (LEVIR-CD, LEVIR-CD+, WHU-CD, and SYSU-CD) demonstrate that BWFNet achieves state-of-the-art performance and strong generalization across diverse and challenging scenarios.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"25562-25582"},"PeriodicalIF":5.3,"publicationDate":"2025-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11183649","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145315266","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":"Kinetic Expansion of Linear Structural Elements: A Hybrid Method for Floorplan Reconstruction From Indoor Scene Point Cloud","authors":"Yunlin Tu;Wenzhong Shi;Yangjie Sun;Min Zhang","doi":"10.1109/JSTARS.2025.3615609","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3615609","url":null,"abstract":"Indoor floorplans are widely used in fields like building information modeling, indoor navigation, emergency response, smart buildings, and architectural design simulation. However, reconstructing accurate floorplans from indoor laser point clouds is challenging due to the complexity, clutter, and occlusions of indoor structures. We propose kinetic expansion of linear structural elements (KELSE), an indoor scene floorplan reconstruction method to address these challenges. We design a structural element extraction method that integrates geometric feature constraints with semantic information to identify structural elements such as walls, doors, windows, ceilings, and floors in complex indoor scenes. A kinetic data structure expansion and undirected graph optimization are then used to reconstruct the complete floorplan. Experimental results show that KELSE achieves high accuracy and completeness, with room reconstruction reaching 0.98 and 0.95, respectively. KELSE provides an efficient and precise solution for floorplan reconstruction from indoor LiDAR point cloud data.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"25494-25511"},"PeriodicalIF":5.3,"publicationDate":"2025-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11184404","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145315289","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}