IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing最新文献_第4页

A Modified EVD-Based Phase Linking Method in Decorrelated Scenario With Time Series Polarimetric Scattering Consistency

IF 4.7 2区地球科学

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Pub Date : 2025-03-04 DOI: 10.1109/JSTARS.2025.3547947

Guanya Wang;Zhiwei Li;Jun Hu;Peng Ren;Yan Zhu

{"title":"A Modified EVD-Based Phase Linking Method in Decorrelated Scenario With Time Series Polarimetric Scattering Consistency","authors":"Guanya Wang;Zhiwei Li;Jun Hu;Peng Ren;Yan Zhu","doi":"10.1109/JSTARS.2025.3547947","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3547947","url":null,"abstract":"Decorrelated scenarios, such as vegetated areas, are influenced by multiple scattering mechanisms and temporal decorrelation, which introduce phase noise and coherence estimation bias, posing challenges for phase linking (PL). The eigenvalue decomposition (EVD) method, well-suited for multiscattering environments, mitigates these issues by decomposing signals into orthogonal eigenvectors, thus reducing the impact of multiscattering mix on PL. However, EVD's effectiveness relies on the assumption of polarimetric stationarity, which is often violated in low-coherence scenarios due to the dynamic nature of vegetation and meteorological factors. Multipolarization SAR data can address this challenge by enabling quantitative assessment of polarimetric stationarity via likelihood statistics of time series polarimetric covariance matrices. To enhance EVD, we introduce the time series polarimetric scattering consistency contribution (TSCC) metric, which evaluates the contribution of each interferometric pair to overall scattering consistency. The TSCC metric, based on the ratio of local to global scattering consistency, identifies interferometric data that meet the polarimetric stationarity assumption. Based on the scattering amplitude variations, it offers an available data quality assessment in decorrelated regions. Replacing traditional coherence weights, the TSCC metric modifies EVD to prioritize temporally stable interferometric pairs, improving phase consistency with actual deformation signals. Experimental results show that the proposed method outperforms traditional methods, achieving a 15% improvement in point density for distributed scatterers in evergreen forest areas and an 82% improvement in point number of positive posterior coherence difference compared to classical EVD.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"7694-7706"},"PeriodicalIF":4.7,"publicationDate":"2025-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10909407","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143706610","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}

引用次数: 0

Alpine Wetlands Information Extraction Using Optimized Multifeatures and Random Forest Algorithm

IF 4.7 2区地球科学

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Pub Date : 2025-03-04 DOI: 10.1109/JSTARS.2025.3547725

Dongchuan Wang;Fei Yang;Shijie Jia;Zhiheng Wang;Chunhua Dong;Mingwei Lang;Kai Ye;Haotian Liu;Tingrong Li

{"title":"Alpine Wetlands Information Extraction Using Optimized Multifeatures and Random Forest Algorithm","authors":"Dongchuan Wang;Fei Yang;Shijie Jia;Zhiheng Wang;Chunhua Dong;Mingwei Lang;Kai Ye;Haotian Liu;Tingrong Li","doi":"10.1109/JSTARS.2025.3547725","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3547725","url":null,"abstract":"Alpine wetlands are a special ecosystem that is extremely sensitive to global climate change. The unique geographical location and climatic conditions of the Yellow-River-Source National Park give rise to diverse wetland types at the land-water interface, which exhibit phenomena such as “same object with different spectra” and “different objects with the same spectrum.” These complexities pose significant challenges in accurately extracting information from alpine wetlands in the study area. To address these challenges, this study proposes a novel integrated multialgorithm feature optimization model that combines three filtering algorithms with a random forest (RF) algorithm for classifying alpine wetland information. First, the rich feature information in the image is initially filtered using a fusion of the three algorithms. Then, the RF algorithm is applied to optimize the filtered features. Finally, the RF classification model is used to refine wetland extraction based on this optimized feature set. The results show that 1) the fused filtering algorithm demonstrates higher stability than each individual algorithm and takes into consideration the strengths and weaknesses of each individual algorithm; 2) the classification accuracy of the RF algorithm reaches its highest value when the number of feature variables is 21; 3) the optimal classification of alpine wetlands is achieved using the RF classification model based on the best set of feature variables, resulting in an overall accuracy of 93.32% and a Kappa coefficient of 91.65% . Compared to existing land cover datasets, the proposed method provides a more detailed classification of alpine wetlands.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"7347-7363"},"PeriodicalIF":4.7,"publicationDate":"2025-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10909416","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143698346","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}

引用次数: 0

3D LiDAR-Based Semantic SLAM for Intelligent Irrigation Using UAV 基于 3D 激光雷达的语义 SLAM，利用无人机实现智能灌溉

IF 4.7 2区地球科学

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Pub Date : 2025-03-04 DOI: 10.1109/JSTARS.2025.3547717

Jeonghyeon Pak;Hyoung Il Son

{"title":"3D LiDAR-Based Semantic SLAM for Intelligent Irrigation Using UAV","authors":"Jeonghyeon Pak;Hyoung Il Son","doi":"10.1109/JSTARS.2025.3547717","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3547717","url":null,"abstract":"Ensuring water use and food security is essential due to the growing world population and global warming. Agriculture is the largest consumer of freshwater, and attention has been focused on improving water-use efficiency in irrigated agriculture. We propose 3-D light detection and ranging (LiDAR)-based semantic simultaneous localization and mapping using unmanned aerial vehicles (UAVs) for intelligent irrigation. The proposed system uses the water-absorbing property of LiDAR to define a water point cloud and segment the surface water area based on singular value decomposition. A path is created using random sample consensus as the median point of the divided surface water area. By extracting the width and height information from the surrounding point cloud, the system aids in proactive natural disaster prevention and has potential applications for Big Data. The performance and practical utility of the proposed system were demonstrated via field data using a UAV and 3-D LiDAR. The robustness of the proposed system is verified by experiments in two irrigation environments with different surface water widths and temporal conditions.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"7495-7508"},"PeriodicalIF":4.7,"publicationDate":"2025-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10909471","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143698347","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}

引用次数: 0

A Novel Geometry Agnostic Delay and Doppler Tracking Technique for GNSS-Reflectometry: Application to the GNOS-II Payload Onboard the FY-3E

IF 4.7 2区地球科学

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Pub Date : 2025-03-03 DOI: 10.1109/JSTARS.2025.3546483

Changyang Wang;Adriano Camps;Xiuqing Hu;Hyuk Park;Kegen Yu;Xiaochun Zhai;Wenqiang Lu;Feixiong Huang;Mi Liao;Peng Zhang;Nanshan Zheng;Kefei Zhang;Zhongmin Ma

{"title":"A Novel Geometry Agnostic Delay and Doppler Tracking Technique for GNSS-Reflectometry: Application to the GNOS-II Payload Onboard the FY-3E","authors":"Changyang Wang;Adriano Camps;Xiuqing Hu;Hyuk Park;Kegen Yu;Xiaochun Zhai;Wenqiang Lu;Feixiong Huang;Mi Liao;Peng Zhang;Nanshan Zheng;Kefei Zhang;Zhongmin Ma","doi":"10.1109/JSTARS.2025.3546483","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3546483","url":null,"abstract":"Global Navigation Satellite System-Reflectometry (GNSS-R) uses GNSS signals as signals of opportunity as a multistatic radar. Most GNSS-R instruments conduct 1 ms coherent integration, followed by 500 or 1000 incoherent averages, leading to level-1 products [delay Doppler map (DDM)]. For remote sensing missions with higher spatio-temporal resolution requirements, raw data, and fewer incoherent averages are required for DDM computations. Fengyun-3E (FY-3E) GNSS Occultation Sounder II (GNOS-II) payload can acquire reflected signal's intermediate frequency (IF) raw data for specific areas, but there is no channel to record raw direct signals. Obtaining level-1 products DDM from raw data requires tracking the delay and Doppler frequency centroid coordinates, as they change during the incoherent integration time. Otherwise, the level-1 DDMs would appear blurring, which would result in wider DDMs and lower peaks. Besides, the geometry of transmitter-specular reflection point-receiver of GNOS-II is unobtainable, so classical algorithms cannot be used. Therefore, an innovative processing technique is presented, which can estimate the peak coordinates of all individual DDMs by appropriately grouping the individual DDMs and incoherently accumulating within each group. The feasibility of this method is demonstrated with representative data from sea, ice, and soil. Furthermore, incoherent averaging DDMs at a temporal resolution of 200 ms can well detect the boundary between sea, ice, and soil in high-latitude and complex environments while maintaining high quality. This work is an important basis for future analysis of the raw data from GNOS-II and will also inspire other work of individual DDM tracking where geometric information is agnostic.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"8040-8056"},"PeriodicalIF":4.7,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10908653","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143706600","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}

引用次数: 0

Specific Spectral Target Detection for Multispectral Images via Target-Focused Spectral Super-Resolution 通过目标聚焦光谱超分辨率检测多光谱图像中的特定光谱目标

IF 4.7 2区地球科学

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Pub Date : 2025-03-03 DOI: 10.1109/JSTARS.2025.3547347

Hongyan Zhang;Wei Wang;Xiaolin Han;Weidong Sun

{"title":"Specific Spectral Target Detection for Multispectral Images via Target-Focused Spectral Super-Resolution","authors":"Hongyan Zhang;Wei Wang;Xiaolin Han;Weidong Sun","doi":"10.1109/JSTARS.2025.3547347","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3547347","url":null,"abstract":"Spectral target detection using spectral information provided by hyperspectral (HS) images has been deeply studied. However, due to low spatial resolution and difficulty in obtaining HS images, spectral target detection based on it faces extremely serious problems of small-scale and mixed spectra. To address this problem, taking the more easily obtained high-spatial-resolution multispectral (HMS) image as an appropriate input, this article proposes a specific spectral target detection method through target-focused spectral super-resolution (SSR). Specifically, by taking the given target spectrum and the spectral library as priors, a target-focused SSR model under the sparse representation framework is proposed first, to enrich the spectral information of the HMS image, and to accurately reconstruct the corresponding high-spatial-resolution HS image, especially for the target area. Then, a target-specific band selection strategy is designed, to extract the most distinguishable spectral bands against background, which can enhance the separation between the target and background and help to reduce the false alarm rate of the detection. Finally, a background separation-based spectral target detection method for the selected bands is proposed, to locate the spectral targets directly by using the optimized target sparse coefficient matrix. Experimental results on four different datasets show that, our proposed method achieves the best target detection performance in comparison to other relative state-of-the-art methods, and can even efficiently handle the detection of subpixel-level spectral targets through this unmixing-like spectral dictionary expression.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"7529-7542"},"PeriodicalIF":4.7,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10909183","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143667206","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}

引用次数: 0

A Hierarchical ViT With Dynamic Window Shift Unit and Curriculum Learning for Remote Sensing Image Scene Classification

IF 4.7 2区地球科学

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Pub Date : 2025-03-03 DOI: 10.1109/JSTARS.2025.3546970

Yi Liu;Xiang Wu;Jihuan Ren;Jiacun Wang;Yuming Bo;Yuanhao Wang

{"title":"A Hierarchical ViT With Dynamic Window Shift Unit and Curriculum Learning for Remote Sensing Image Scene Classification","authors":"Yi Liu;Xiang Wu;Jihuan Ren;Jiacun Wang;Yuming Bo;Yuanhao Wang","doi":"10.1109/JSTARS.2025.3546970","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3546970","url":null,"abstract":"The remote sensing image (RSI) scene classification is currently a popular research topic among many remote sensing tasks. However, RSI scene classification still faces challenges such as complex multiscale key features concentrated in different local regions, large interclass imbalance, and intraclass variation in insufficient well-labeled RSI samples. To address these challenges, we proposed a novel RSI scene classification method based on an improved vision transformer. This method has better multiscale feature representation ability due to the improved hierarchical vision transformer structure, in which a feature map fusion layer produces feature maps of different sizes, and a window transformer block with dynamic window shift unit actively shifts to the local region with dense information, flexibly extracting and associating key features with multiscale in different input regions. Furthermore, we design a curriculum transfer learning framework to alleviate the problems of lacking well-labeled training samples, intraclass variation, and interclass imbalance during the training process of the improved vision transformer. This framework employs a dual-criteria difficulty evaluator to evaluate training samples and provides supplementary supervision to the model by generating training task schedules. Finally, experimental results demonstrate that the proposed vision transformer model achieves rapid convergence and superior performance in RSI scene classification task.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"8011-8024"},"PeriodicalIF":4.7,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10908633","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143706612","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}

引用次数: 0

Research on Remote Sensing Quantitative Inversion of Oil Spills and Emulsions Using Fusion of Optical and Thermal Characteristics

IF 4.7 2区地球科学

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Pub Date : 2025-03-03 DOI: 10.1109/JSTARS.2025.3547719

Zongchen Jiang;Jie Zhang;Yi Ma;Xingpeng Mao

{"title":"Research on Remote Sensing Quantitative Inversion of Oil Spills and Emulsions Using Fusion of Optical and Thermal Characteristics","authors":"Zongchen Jiang;Jie Zhang;Yi Ma;Xingpeng Mao","doi":"10.1109/JSTARS.2025.3547719","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3547719","url":null,"abstract":"Marine oil spill disasters significantly threaten the environment, economic development, and human health. Accurate quantification and inversion of oil spills and emulsions are essential for an effective emergency response. This study systematically investigated oil spill quantitative inversion from land-based to airborne and then to satellite-based, focusing on the optical and thermal response characteristics of nonemulsified crude oils (NEO) and fuel oils of varying thicknesses, as well as oil spill emulsions (OE) with different emulsification concentrations. A novel modular oil spill quantitative inversion model (OQIM) combining optical and thermal characteristics was developed, which comprehensively utilized the inversion advantages of optical and thermal infrared remote sensing in the thin and thick oil film ranges, respectively, enabling the simultaneous quantitative inversion of NEO and OE. The study demonstrates that the OQIM exhibited excellent quantitative inversion capabilities and stability under ideal land-based scenarios, with <italic>R</i><sup>2</sup>; values for NEO and OE exceeding 0.978 and 0.983, respectively. The OQIM effectively utilized the technical strengths of optical and thermal remote sensing, successfully mitigating the interference from sun glint, and inverting the thickness of NEO and fuel oil based on the UAV actual measurement data. By employing the oil–water brightness temperature difference polar coordinate thermal model, the absolute thickness of the oil-in-water emulsions was inverted with an average relative error below 12.7%. When applied to airborne and satellite remote sensing images of actual oil spill incidents, the OQIM model exhibited significant inversion potential and generalization capabilities in practical applications, offering crucial methodological support for emergency responses to marine oil spills.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"8472-8489"},"PeriodicalIF":4.7,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10909410","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143726345","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}

引用次数: 0

MiniCPM-V LLaMA Model for Image Recognition: A Case Study on Satellite Datasets

IF 4.7 2区地球科学

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Pub Date : 2025-03-03 DOI: 10.1109/JSTARS.2025.3547144

Kürşat Kömürcü;Linas Petkevičius

{"title":"MiniCPM-V LLaMA Model for Image Recognition: A Case Study on Satellite Datasets","authors":"Kürşat Kömürcü;Linas Petkevičius","doi":"10.1109/JSTARS.2025.3547144","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3547144","url":null,"abstract":"This study evaluates the performance of the MiniCPM-V model on four distinct satellite image datasets: MAI, RSICD, RSSCN7, and a newly created merged dataset that combines these three. The merged dataset was developed to expand the generalization and variation of data distribution associated with the labeling and training processes inherent in satellite image analysis. We systematically collected prediction results for each individual dataset and conducted a comparative analysis against results reported in previous studies to benchmark the model's effectiveness. The findings indicate that large language models (LLMs), such as MiniCPM-V, exhibit promising capabilities in the realm of satellite image recognition. On the RSSCN7 dataset, MiniCPM-V achieved an accuracy of 70.57%, while on RSICD it reached 62.19%, on MAI 7.01%, and on the merged dataset 43.49% . Specifically, the model demonstrated mostly high accuracy (more than 80% ) in identifying a majority of object classes across the datasets. Also, we identified, it underperformed in accurately classifying certain object categories and recognizing all objects in multilabeled images, which suggests that while the model is robust overall, there are specific areas where its performance can be enhanced. Despite these limitations, the successful recognition of most objects underscores the potential of LLMs in advancing satellite imagery analysis. These results highlight the significant potential of integrating LLMs into remote sensing applications, offering a foundation for future research aimed at improving classification accuracy and expanding the range of detectable object classes by having caption level textual information.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"7892-7903"},"PeriodicalIF":4.7,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10908656","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143706781","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}

引用次数: 0

Image Inpainting and Digital Camouflage: Methods, Applications, and Perspectives for Remote Sensing

IF 4.7 2区地球科学

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Pub Date : 2025-03-03 DOI: 10.1109/JSTARS.2025.3547917

Kinga Karwowska;Damian Wierzbicki;Michal Kedzierski

{"title":"Image Inpainting and Digital Camouflage: Methods, Applications, and Perspectives for Remote Sensing","authors":"Kinga Karwowska;Damian Wierzbicki;Michal Kedzierski","doi":"10.1109/JSTARS.2025.3547917","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3547917","url":null,"abstract":"Image inpainting refers to the process of restoring missing or damaged areas in an image. This research field has been very active in recent years, driven by various applications such as reconstructing lost fragments, concealing data loss in corrupted image transmissions, removing objects in image editing, and interpolating image content for reconstruction in image-based rendering from various fields of view. This article presents existing methods of image inpainting, covering classical approaches, CNN-based methods, and GAN-based methods. In addition, it explores techniques related to steganography, adversarial image synthesis, and false image generation. Examples of applications are provided for each category of image modification methods. Although image inpainting and digital camouflage are not yet widely studied in the remote sensing community, there has been a growing interest in these topics in recent years. To broaden the understanding of these methods, this study also reviews techniques developed in the field of computer science, which have the potential to be adapted for remote sensing applications. The main contribution of this article is the presentation of various forms of digital masking, extending beyond traditional inpainting. We also provide a curated list of publicly available datasets that can support the development of new solutions, along with a selection of qualitative metrics for the robust evaluation of image inpainting algorithms.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"8215-8247"},"PeriodicalIF":4.7,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10909411","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143740323","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}

引用次数: 0

Hyperspectral Image Completion Using Fully-Connected Extended Tensor Network Decomposition and Total Variation

IF 4.7 2区地球科学

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Pub Date : 2025-02-28 DOI: 10.1109/JSTARS.2025.3546630

Yao Li;Yujie Zhang;Hongwei Li

{"title":"Hyperspectral Image Completion Using Fully-Connected Extended Tensor Network Decomposition and Total Variation","authors":"Yao Li;Yujie Zhang;Hongwei Li","doi":"10.1109/JSTARS.2025.3546630","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3546630","url":null,"abstract":"The task of hyperspectral image completion generally involves random missing entries completion, stripes inpainting, and cloud removal, which can enhance the accuracy of subsequent image analysis. Recently, tensor completion has been presented for image recovery. Owing to the framelet basis redundancy, the tensor rank of the extended tensor via feature extraction is smaller, which can characterize the correlation between any two modes of the tensor more accurately. In this work, the fully connected tensor network decomposition has been suggested to depict the low-rankness of the extended tensor with feature extraction. The process of feature extraction via framelet transform reduces the need for fewer principal components to depict the low-rankness of the underlying tensor. Moreover, total variation is incorporated into the proposed completion model to capture the spatial smoothness of the underlying tensor via minimizing the sum of the gradients across the image. To solve the large-scale resulting model, the augmented Lagrange multiplier-based proximal alternating minimization algorithm has been proposed. To accelerate the optimization algorithm, the leverage score sampling and fast Fourier transform have been introduced. Numerical results on several types of hyperspectral image completion problem demonstrate that the proposed method performs better than the compared methods in data completion.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"7543-7558"},"PeriodicalIF":4.7,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10908089","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143667522","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}

引用次数: 0