Pub Date : 2025-01-30DOI: 10.1109/LGRS.2025.3537104
Zhao Yang;Jia Chen;Jun Li;Xiangan Zheng
Scene classification of remote sensing images plays a vital role in Earth observation applications. Among various challenges, occlusion is a prevalent and critical issue in practical applications, particularly when dealing with large-area occlusions caused by clouds, shadows, and man-made structures. Current methods, whether based on occlusion recovery or occlusion-robust feature extraction, generally show limited performance when processing extensive occluded regions due to ignoring the inconsistency in feature representation caused by multiscale occlusions. To address the occlusion challenge, this letter proposes a novel contrastive learning-based multiscale occlusion framework with three key components: 1) a pretext task module that distinguishes between small and large occlusions to enable occlusion-invariant feature learning; 2) a multibranch feature extraction network based on ResNet-50’s shared-weight convolutional layers for consistent feature extraction across occlusion levels; and 3) a joint loss function that adaptively balances contrastive feature learning and classification. Extensive experiments were evaluated on the DIOR-Occ and LEVIR-Occ benchmark datasets, demonstrating significant improvements in classification accuracy across different occlusion scenarios. Compared with existing approaches, the proposed framework achieves superior robustness and generalization capabilities, with notable advantages in the analysis of highly occluded data. Future research will explore the adaptation of this framework to detection and segmentation tasks.
{"title":"Multiscale Occlusion-Robust Scene Classification in Remote Sensing Images via Supervised Contrastive Learning","authors":"Zhao Yang;Jia Chen;Jun Li;Xiangan Zheng","doi":"10.1109/LGRS.2025.3537104","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3537104","url":null,"abstract":"Scene classification of remote sensing images plays a vital role in Earth observation applications. Among various challenges, occlusion is a prevalent and critical issue in practical applications, particularly when dealing with large-area occlusions caused by clouds, shadows, and man-made structures. Current methods, whether based on occlusion recovery or occlusion-robust feature extraction, generally show limited performance when processing extensive occluded regions due to ignoring the inconsistency in feature representation caused by multiscale occlusions. To address the occlusion challenge, this letter proposes a novel contrastive learning-based multiscale occlusion framework with three key components: 1) a pretext task module that distinguishes between small and large occlusions to enable occlusion-invariant feature learning; 2) a multibranch feature extraction network based on ResNet-50’s shared-weight convolutional layers for consistent feature extraction across occlusion levels; and 3) a joint loss function that adaptively balances contrastive feature learning and classification. Extensive experiments were evaluated on the DIOR-Occ and LEVIR-Occ benchmark datasets, demonstrating significant improvements in classification accuracy across different occlusion scenarios. Compared with existing approaches, the proposed framework achieves superior robustness and generalization capabilities, with notable advantages in the analysis of highly occluded data. Future research will explore the adaptation of this framework to detection and segmentation tasks.","PeriodicalId":91017,"journal":{"name":"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society","volume":"22 ","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2025-01-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143496498","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}
The ionosonde is one of the most widely used ionospheric detection devices. It has significant implications for the study of space physics and wireless communication technology. To solve the problem of low resolution with traditional iososonde imaging method, this letter proposes a high-resolution 2-D spatial-frequency spectral estimation imaging method. By reconstructing the echo signal matrix and constructing the guidance vector that simultaneously reflects the range and motion characteristics of the target, high-precision estimation of the range-Doppler spectrum is achieved in 2-D Capon estimation. The analysis of experimental sporadic-E (Es) sounding data of August 13, 2021 in Wuhan ($114^{circ } 22^{prime } $ E, $30^{circ } 30^{prime } $ N), China, demonstrates its ability of the precise measurement for single-layer echoes and the identification ability for multilayer fine structures. This method further enhances the potential of traditional ionosonde for precise observation and analysis of the ionosphere.
{"title":"A High-Resolution Imaging Method of Ionosonde Based on Spatial-Frequency 2-D Spectrum Estimation Technology","authors":"Tongxin Liu;Guobin Yang;Chunhua Jiang;Hao Li;Chongzhe Lao","doi":"10.1109/LGRS.2025.3537288","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3537288","url":null,"abstract":"The ionosonde is one of the most widely used ionospheric detection devices. It has significant implications for the study of space physics and wireless communication technology. To solve the problem of low resolution with traditional iososonde imaging method, this letter proposes a high-resolution 2-D spatial-frequency spectral estimation imaging method. By reconstructing the echo signal matrix and constructing the guidance vector that simultaneously reflects the range and motion characteristics of the target, high-precision estimation of the range-Doppler spectrum is achieved in 2-D Capon estimation. The analysis of experimental sporadic-E (Es) sounding data of August 13, 2021 in Wuhan (<inline-formula> <tex-math>$114^{circ } 22^{prime } $ </tex-math></inline-formula>E, <inline-formula> <tex-math>$30^{circ } 30^{prime } $ </tex-math></inline-formula>N), China, demonstrates its ability of the precise measurement for single-layer echoes and the identification ability for multilayer fine structures. This method further enhances the potential of traditional ionosonde for precise observation and analysis of the ionosphere.","PeriodicalId":91017,"journal":{"name":"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society","volume":"22 ","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2025-01-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143403908","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 : 2025-01-29DOI: 10.1109/LGRS.2025.3536038
Lei Zhang;Peng Zhang;Chengpeng Song;Longsheng Zhang
The Consultative Committee for Space Data Systems (CCSDS) has released the CCSDS 123.0-B-2 standard, which supports lossless and near-lossless compression for multispectral and hyperspectral images. This standard introduces a quantization feedback loop in the predictor. However, this feedback loop significantly reduces throughput efficiency in hardware implementations, hindering real-time on-board compression. To address this issue, this letter proposes a single-step prediction strategy. In the modes of band interleaved by line (BIL) data transmission mode, throughput is improved from 17.86 to 101 Msamples/s, achieving real-time processing. Furthermore, this letter introduces an adaptive maximum reconstruction error to achieve a controllable compression ratio, thus addressing the challenges posed by fixed and limited downlink bandwidth in harsh environments.
{"title":"A Simplified Predictor With Adjustable Compression Ratio Based on CCSDS 123.0-B-2","authors":"Lei Zhang;Peng Zhang;Chengpeng Song;Longsheng Zhang","doi":"10.1109/LGRS.2025.3536038","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3536038","url":null,"abstract":"The Consultative Committee for Space Data Systems (CCSDS) has released the CCSDS 123.0-B-2 standard, which supports lossless and near-lossless compression for multispectral and hyperspectral images. This standard introduces a quantization feedback loop in the predictor. However, this feedback loop significantly reduces throughput efficiency in hardware implementations, hindering real-time on-board compression. To address this issue, this letter proposes a single-step prediction strategy. In the modes of band interleaved by line (BIL) data transmission mode, throughput is improved from 17.86 to 101 Msamples/s, achieving real-time processing. Furthermore, this letter introduces an adaptive maximum reconstruction error to achieve a controllable compression ratio, thus addressing the challenges posed by fixed and limited downlink bandwidth in harsh environments.","PeriodicalId":91017,"journal":{"name":"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society","volume":"22 ","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2025-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143388607","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 : 2025-01-29DOI: 10.1109/LGRS.2025.3536164
Zhenghao Jiang;Biao Wang;Xiao Xu;YaoBo Zhang;Peng Zhang;Yanlan Wu;Hui Yang
Remote sensing change detection (CD) has garnered extensive research and application due to its ability to identify changes in land features within the same area across different periods. CD tasks require features with strong intraclass distinctions and precise spatial boundary details. Existing methods enhance the extraction of difference features but significantly increase computational complexity in high-resolution remote sensing imagery. Moreover, these methods focus on pixel-level difference extraction while neglecting feedback from the overall change object. As a result, they lack global information perception, leading to blurred edges and fragmented interiors in the change areas. To address these challenges, we propose a feature enhancement and feedback network (FEFNet) for CD. First, we designed a multilevel dual-feature fusion enhancement module (DFFM) to improve the representation of latent features between the bitemporal images. Second, we developed a feature coupling feedback module (FCFM) that efficiently decodes multiscale change features to generate extraction results. The experimental results show that FEFNet outperforms recent models in both computational efficiency and detection performance. With only 10.56G FLOPs and 2.26M parameters, FEFNet achieves an ${F}_{1}$ score of 92.32% on the LEVIR-CD dataset and 93.77% on the WHU-CD dataset. The code will be available at https://github.com/XiaoJ058/RS-CD.
{"title":"Feature Enhancement and Feedback Network for Change Detection in Remote Sensing Images","authors":"Zhenghao Jiang;Biao Wang;Xiao Xu;YaoBo Zhang;Peng Zhang;Yanlan Wu;Hui Yang","doi":"10.1109/LGRS.2025.3536164","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3536164","url":null,"abstract":"Remote sensing change detection (CD) has garnered extensive research and application due to its ability to identify changes in land features within the same area across different periods. CD tasks require features with strong intraclass distinctions and precise spatial boundary details. Existing methods enhance the extraction of difference features but significantly increase computational complexity in high-resolution remote sensing imagery. Moreover, these methods focus on pixel-level difference extraction while neglecting feedback from the overall change object. As a result, they lack global information perception, leading to blurred edges and fragmented interiors in the change areas. To address these challenges, we propose a feature enhancement and feedback network (FEFNet) for CD. First, we designed a multilevel dual-feature fusion enhancement module (DFFM) to improve the representation of latent features between the bitemporal images. Second, we developed a feature coupling feedback module (FCFM) that efficiently decodes multiscale change features to generate extraction results. The experimental results show that FEFNet outperforms recent models in both computational efficiency and detection performance. With only 10.56G FLOPs and 2.26M parameters, FEFNet achieves an <inline-formula> <tex-math>${F}_{1}$ </tex-math></inline-formula> score of 92.32% on the LEVIR-CD dataset and 93.77% on the WHU-CD dataset. The code will be available at <uri>https://github.com/XiaoJ058/RS-CD</uri>.","PeriodicalId":91017,"journal":{"name":"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society","volume":"22 ","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2025-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143360899","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 : 2025-01-29DOI: 10.1109/LGRS.2025.3536005
Amir Hosein Oveis;Alessandro Cantelli-Forti;Elisa Giusti;Meysam Soltanpour;Neda Rojhani;Marco Martorella
The increasing reliance on convolutional neural networks (CNNs) for automatic target recognition (ATR) in critical applications necessitates robust defenses against adversarial attacks, which can undermine their reliability. To address this challenge, this letter proposes a novel classification framework that enhances CNN robustness for ATR under adversarial perturbations. Although CNNs are renowned for their high recognition accuracy, their performance can be compromised by subtle adversarial perturbations designed to deceive the classifier. Our methodology is based on extracting specific features from Shapley additive explanations (SHAP) analysis within and outside the detected target area. These features are then used to train a multinomial logistic regression model using the training labels, and the trained regressor performs the classification. The key strength of our framework relies on robustness enhancement against adversarial attacks, particularly designed by the fast gradient sign method (FGSM). We validate our findings through extensive evaluations using two publicly available datasets: the multitype aircraft remote sensing images (MTARSI) dataset, which contains optical images of various aircraft types, and the moving and stationary target acquisition and recognition (MSTAR) dataset, which contains radar images.
{"title":"SHAP-Assisted Resilience Enhancement Against Adversarial Perturbations in Optical and SAR Image Classification","authors":"Amir Hosein Oveis;Alessandro Cantelli-Forti;Elisa Giusti;Meysam Soltanpour;Neda Rojhani;Marco Martorella","doi":"10.1109/LGRS.2025.3536005","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3536005","url":null,"abstract":"The increasing reliance on convolutional neural networks (CNNs) for automatic target recognition (ATR) in critical applications necessitates robust defenses against adversarial attacks, which can undermine their reliability. To address this challenge, this letter proposes a novel classification framework that enhances CNN robustness for ATR under adversarial perturbations. Although CNNs are renowned for their high recognition accuracy, their performance can be compromised by subtle adversarial perturbations designed to deceive the classifier. Our methodology is based on extracting specific features from Shapley additive explanations (SHAP) analysis within and outside the detected target area. These features are then used to train a multinomial logistic regression model using the training labels, and the trained regressor performs the classification. The key strength of our framework relies on robustness enhancement against adversarial attacks, particularly designed by the fast gradient sign method (FGSM). We validate our findings through extensive evaluations using two publicly available datasets: the multitype aircraft remote sensing images (MTARSI) dataset, which contains optical images of various aircraft types, and the moving and stationary target acquisition and recognition (MSTAR) dataset, which contains radar images.","PeriodicalId":91017,"journal":{"name":"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society","volume":"22 ","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2025-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143360968","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 : 2025-01-28DOI: 10.1109/LGRS.2025.3535524
Hao Chang;Xiongjun Fu;Kunyi Guo;Jian Dong;Jialin Guan;Chuyi Liu
With the significant advancements in deep learning technology and the substantial improvement in remote sensing image resolution, remote sensing semantic segmentation has garnered widespread attention. Synthetic aperture radar (SAR) and optical images are the primary sources of remote sensing data, offering complementary information. SAR images can capture surface information even under cloud cover and at night, whereas optical images provide higher resolution in clear weather conditions. Deep learning-based feature fusion methods can effectively integrate multisource information to obtain more comprehensive surface data. However, there are significant spatiotemporal differences in multisource information, making it challenging to select and extract the most discriminative features for segmentation tasks. To address this, we propose a lightweight and efficient fusion semantic segmentation network, SOLSTM, which mixes SAR and optical images as inputs and performs cyclic cross-fusion to establish a new network paradigm. To tackle multisource data heterogeneity, we introduce SAR-OPT matching attention, which aggregates multisource image features by adaptively adjusting fusion weights, thereby achieving comprehensive perception of feature channels and contextual information. Additionally, to mitigate the high computational complexity of processing multidimensional data, we introduce the mLSTM block, which employs linear operations to mine global contextual information in fused images, thus reducing computational complexity and enhancing image segmentation performance. Experiments on the WHU-OPT-SAR dataset show that SOLSTM has excellent performance, achieving up to 52.9 mIoU and outperforming single source image segmentation, verifying the effective fusion of OPT-SAR.
{"title":"SOLSTM: Multisource Information Fusion Semantic Segmentation Network Based on SAR-OPT Matching Attention and Long Short-Term Memory Network","authors":"Hao Chang;Xiongjun Fu;Kunyi Guo;Jian Dong;Jialin Guan;Chuyi Liu","doi":"10.1109/LGRS.2025.3535524","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3535524","url":null,"abstract":"With the significant advancements in deep learning technology and the substantial improvement in remote sensing image resolution, remote sensing semantic segmentation has garnered widespread attention. Synthetic aperture radar (SAR) and optical images are the primary sources of remote sensing data, offering complementary information. SAR images can capture surface information even under cloud cover and at night, whereas optical images provide higher resolution in clear weather conditions. Deep learning-based feature fusion methods can effectively integrate multisource information to obtain more comprehensive surface data. However, there are significant spatiotemporal differences in multisource information, making it challenging to select and extract the most discriminative features for segmentation tasks. To address this, we propose a lightweight and efficient fusion semantic segmentation network, SOLSTM, which mixes SAR and optical images as inputs and performs cyclic cross-fusion to establish a new network paradigm. To tackle multisource data heterogeneity, we introduce SAR-OPT matching attention, which aggregates multisource image features by adaptively adjusting fusion weights, thereby achieving comprehensive perception of feature channels and contextual information. Additionally, to mitigate the high computational complexity of processing multidimensional data, we introduce the mLSTM block, which employs linear operations to mine global contextual information in fused images, thus reducing computational complexity and enhancing image segmentation performance. Experiments on the WHU-OPT-SAR dataset show that SOLSTM has excellent performance, achieving up to 52.9 mIoU and outperforming single source image segmentation, verifying the effective fusion of OPT-SAR.","PeriodicalId":91017,"journal":{"name":"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society","volume":"22 ","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2025-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143396319","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 : 2025-01-28DOI: 10.1109/LGRS.2025.3535723
Yongjian Zhou;Haochen Qi;Wang Zhang;Xiaocai Shan
As an indispensable part of geophysical exploration, seismic inversion can obtain the properties of subsurface media based on seismic data and available well-log information. With the nonlinear mapping ability, deep neural networks can map seismic data to well-log of interest. Interpreting gamma is crucial as it is essential for determining lithology and indicating sediment characteristics. Stratigraphic frameworks can approximate low-frequency trends in subsurface properties and are often used to guide well-log interpolation effectively. However, the existing deep neural network models cannot effectively explicitly fuse critical stratigraphic information, which will restrict the physical explainability and correctness of the seismic inversion. Thus, we propose a stratigraphic-encoded transformer algorithm, named SeisWellTrans, to build a gamma log inversion model using horizon position encoding and seismic trace as inputs. Specifically, the incorporation of stratigraphic information from several horizons is crucial for improving the resolution of the output; and SeisWellTrans can efficiently model context in seismic sequences by capturing the interactions between horizon position encodings. We take the Volve field data as an example and use several gamma curves as training labels, and numerical experiments demonstrate the geologically reasonable performance and high validation accuracy of this network and the crucial role that stratigraphic information plays. On the four validation wells, stratigraphic-encoded SeisWellTrans obtained an average correlation coefficient of 86%, exceeding 79% of stratigraphic-encoded convolutional neural network (CNN).
{"title":"Gamma Log Inversion of Seismic Data Based on Transformer With Stratigraphic Position Encoding","authors":"Yongjian Zhou;Haochen Qi;Wang Zhang;Xiaocai Shan","doi":"10.1109/LGRS.2025.3535723","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3535723","url":null,"abstract":"As an indispensable part of geophysical exploration, seismic inversion can obtain the properties of subsurface media based on seismic data and available well-log information. With the nonlinear mapping ability, deep neural networks can map seismic data to well-log of interest. Interpreting gamma is crucial as it is essential for determining lithology and indicating sediment characteristics. Stratigraphic frameworks can approximate low-frequency trends in subsurface properties and are often used to guide well-log interpolation effectively. However, the existing deep neural network models cannot effectively explicitly fuse critical stratigraphic information, which will restrict the physical explainability and correctness of the seismic inversion. Thus, we propose a stratigraphic-encoded transformer algorithm, named SeisWellTrans, to build a gamma log inversion model using horizon position encoding and seismic trace as inputs. Specifically, the incorporation of stratigraphic information from several horizons is crucial for improving the resolution of the output; and SeisWellTrans can efficiently model context in seismic sequences by capturing the interactions between horizon position encodings. We take the Volve field data as an example and use several gamma curves as training labels, and numerical experiments demonstrate the geologically reasonable performance and high validation accuracy of this network and the crucial role that stratigraphic information plays. On the four validation wells, stratigraphic-encoded SeisWellTrans obtained an average correlation coefficient of 86%, exceeding 79% of stratigraphic-encoded convolutional neural network (CNN).","PeriodicalId":91017,"journal":{"name":"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society","volume":"22 ","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2025-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10856238","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143465881","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-01-28DOI: 10.1109/LGRS.2025.3528935
Bo Wan;Lei Zhang;Jianxin Wu;Guanyong Wang;Zirui Xi
An efficient raw data generation (RDG) algorithm in the hybrid domain is proposed, which can be applied to the accurate echo generation of spotlight mode synthetic aperture radar (SAR) with trajectory deviation, even in cases of terrain undulation. Generally, the accuracy required for the signal’s envelope is on the order of the range resolution cell. However, the requirement for the phase is significantly higher, on the order of the wavelength. Therefore, the proposed algorithm calculates the phase of the SAR raw data in the time domain through a point-by-point approach to ensure accuracy and computes the envelope of the raw data through subblock processing in the frequency domain to improve efficiency. To balance the computational efficiency and accuracy, the optimal selection of subblock size is discussed in detail. Simulation experiments verify the accuracy and efficiency of the method.
{"title":"An Efficient Hybrid Domain Algorithm for Accurate SAR Raw Data Generation With Trajectory Deviations","authors":"Bo Wan;Lei Zhang;Jianxin Wu;Guanyong Wang;Zirui Xi","doi":"10.1109/LGRS.2025.3528935","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3528935","url":null,"abstract":"An efficient raw data generation (RDG) algorithm in the hybrid domain is proposed, which can be applied to the accurate echo generation of spotlight mode synthetic aperture radar (SAR) with trajectory deviation, even in cases of terrain undulation. Generally, the accuracy required for the signal’s envelope is on the order of the range resolution cell. However, the requirement for the phase is significantly higher, on the order of the wavelength. Therefore, the proposed algorithm calculates the phase of the SAR raw data in the time domain through a point-by-point approach to ensure accuracy and computes the envelope of the raw data through subblock processing in the frequency domain to improve efficiency. To balance the computational efficiency and accuracy, the optimal selection of subblock size is discussed in detail. Simulation experiments verify the accuracy and efficiency of the method.","PeriodicalId":91017,"journal":{"name":"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society","volume":"22 ","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2025-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143422804","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}
Feature representation plays a key role in matching keypoints, especially for the multispectral images of large spectral difference. On such image pairs, existing methods typically use the two images only, but it is challenging to directly learn spectrum-invariant feature representation due to the complex nonlinear distortion between them. To address this issue, this letter proposes using intermediate-band images to facilitate learning spectrum-invariant feature representation. For this purpose, this work designs a spectrum adaptive gate network (SAG-Net) that consists of a SPectral gate (SPeG) module and a deep feature extractor. The SPeG module selectively activates the spectrum-invariant features according to input image content on-the-fly. It hence allows for training on the images of over two bands simultaneously with a single network without the need of an individual branch per band. To investigate the SPeG module, we also constructed a Landsat 9 Multi-Spectral Images (L9-MSI) dataset including 3167 scenes of aligned images across five spectral bands (visible, B5, B6, B7, and B10) from the Landsat 9 imagery. The experimental results demonstrate the SPeG module can learn common feature representation for varying-band images, and the intermediate B5, B6, and B7 images are useful for the SAG-Net to learn the common feature between visible and B10. On the L9-MSI dataset, the SAG-Net significantly improved the number of correct matches and the matching score (MS). Our dataset will be released at https://github.com/bohanlee/L9MSI-Dataset.git.
{"title":"SAG-Net: Spectrum Adaptive Gate Network for Learning Feature Representation From Multispectral Imagery","authors":"Yong Li;Bohan Li;Zhongqun Chen;Yixuan Li;Guohan Zhang","doi":"10.1109/LGRS.2025.3535635","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3535635","url":null,"abstract":"Feature representation plays a key role in matching keypoints, especially for the multispectral images of large spectral difference. On such image pairs, existing methods typically use the two images only, but it is challenging to directly learn spectrum-invariant feature representation due to the complex nonlinear distortion between them. To address this issue, this letter proposes using intermediate-band images to facilitate learning spectrum-invariant feature representation. For this purpose, this work designs a spectrum adaptive gate network (SAG-Net) that consists of a SPectral gate (SPeG) module and a deep feature extractor. The SPeG module selectively activates the spectrum-invariant features according to input image content on-the-fly. It hence allows for training on the images of over two bands simultaneously with a single network without the need of an individual branch per band. To investigate the SPeG module, we also constructed a Landsat 9 Multi-Spectral Images (L9-MSI) dataset including 3167 scenes of aligned images across five spectral bands (visible, B5, B6, B7, and B10) from the Landsat 9 imagery. The experimental results demonstrate the SPeG module can learn common feature representation for varying-band images, and the intermediate B5, B6, and B7 images are useful for the SAG-Net to learn the common feature between visible and B10. On the L9-MSI dataset, the SAG-Net significantly improved the number of correct matches and the matching score (MS). Our dataset will be released at <uri>https://github.com/bohanlee/L9MSI-Dataset.git</uri>.","PeriodicalId":91017,"journal":{"name":"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society","volume":"22 ","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2025-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143455229","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}
SAR colorization aims to enrich gray-scale SAR images with color while ensuring the preservation of original radiometric and spatial details. However, researchers often limit themselves to using only the red, green, and blue bands of a multispectral image as the source of color information, coupled with a single-polarization channel from the SAR image. This approach neglects the intrinsic characteristics of remote sensing data and thus fails to fully leverage available information. To overcome this limitation, this research attempts to explore inclusion of all available bands from multispectral images along with dual-polarization channels from SAR imagery in the colorization process. Furthermore, we present a new colorization method called improved conditional generative adversarial network for SAR colorization (IcGAN4ColSAR). This method tries to include the spectral angle mapper index within its loss function. Sufficient experiments show that our explorations in the number of data channels and the loss function are helpful in improving the colorization performance of the SAR image.
{"title":"IcGAN4ColSAR: A Novel Multispectral Conditional Generative Adversarial Network Approach for SAR Image Colorization","authors":"Kangqing Shen;Gemine Vivone;Simone Lolli;Michael Schmitt;Xiaoyuan Yang;Jocelyn Chanussot","doi":"10.1109/LGRS.2025.3534795","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3534795","url":null,"abstract":"SAR colorization aims to enrich gray-scale SAR images with color while ensuring the preservation of original radiometric and spatial details. However, researchers often limit themselves to using only the red, green, and blue bands of a multispectral image as the source of color information, coupled with a single-polarization channel from the SAR image. This approach neglects the intrinsic characteristics of remote sensing data and thus fails to fully leverage available information. To overcome this limitation, this research attempts to explore inclusion of all available bands from multispectral images along with dual-polarization channels from SAR imagery in the colorization process. Furthermore, we present a new colorization method called improved conditional generative adversarial network for SAR colorization (IcGAN4ColSAR). This method tries to include the spectral angle mapper index within its loss function. Sufficient experiments show that our explorations in the number of data channels and the loss function are helpful in improving the colorization performance of the SAR image.","PeriodicalId":91017,"journal":{"name":"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society","volume":"22 ","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2025-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143396318","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：