Pub Date : 2024-11-25DOI: 10.1109/LGRS.2024.3505855
Ruida Chen;Yicheng Jiang;He Ni;Yun Zhang
In spaceborne inverse synthetic aperture radar (ISAR) imaging of space targets, the high-speed motion of the radar and target can make the intrapulse motion not negligible. It can cause the range dimension matched filtering error, resulting in image defocusing. In traditional ISAR imaging scenarios, existing analysis and methods only focus on the high-speed motion of the target, without considering the radar, which is not suitable for spaceborne ISAR imaging of space targets. In this letter, the intrapulse motion of spaceborne ISAR imaging of space targets is analyzed in detail, and the corresponding compensation method based on modified phase difference (MPD) is proposed. First, the specific expression of the signal’s time delay considering the intrapulse motion is derived. Then, the range-dimension matched filtering error is analyzed, and the condition of ignoring the intrapulse motion is also obtained. This condition can be used to judge whether the intrapulse motion can be ignored in practical processing. According to the error analysis, an intrapulse motion compensation method based on MPD is proposed. This method does not need to estimate the motion parameters of the radar and target. The coefficient used to construct the compensation term can be directly estimated from the echo signal. Finally, the corresponding spaceborne ISAR imaging method with intrapulse motion compensation for space targets is proposed. Isolated scatterer and satellite electromagnetic calculation data experiments using the orbital data verify the effectiveness of the proposed method.
{"title":"Spaceborne ISAR Imaging of Space Target With Intrapulse Motion Compensation Based on Modified Phase Difference","authors":"Ruida Chen;Yicheng Jiang;He Ni;Yun Zhang","doi":"10.1109/LGRS.2024.3505855","DOIUrl":"https://doi.org/10.1109/LGRS.2024.3505855","url":null,"abstract":"In spaceborne inverse synthetic aperture radar (ISAR) imaging of space targets, the high-speed motion of the radar and target can make the intrapulse motion not negligible. It can cause the range dimension matched filtering error, resulting in image defocusing. In traditional ISAR imaging scenarios, existing analysis and methods only focus on the high-speed motion of the target, without considering the radar, which is not suitable for spaceborne ISAR imaging of space targets. In this letter, the intrapulse motion of spaceborne ISAR imaging of space targets is analyzed in detail, and the corresponding compensation method based on modified phase difference (MPD) is proposed. First, the specific expression of the signal’s time delay considering the intrapulse motion is derived. Then, the range-dimension matched filtering error is analyzed, and the condition of ignoring the intrapulse motion is also obtained. This condition can be used to judge whether the intrapulse motion can be ignored in practical processing. According to the error analysis, an intrapulse motion compensation method based on MPD is proposed. This method does not need to estimate the motion parameters of the radar and target. The coefficient used to construct the compensation term can be directly estimated from the echo signal. Finally, the corresponding spaceborne ISAR imaging method with intrapulse motion compensation for space targets is proposed. Isolated scatterer and satellite electromagnetic calculation data experiments using the orbital data verify the effectiveness of the proposed 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":"2024-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142777731","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 : 2024-11-25DOI: 10.1109/LGRS.2024.3506034
Muhammad Ahmad;Muhammad Usama;Manuel Mazzara;Salvatore Distefano
Hyperspectral imaging (HSI) has proven to be a powerful tool for capturing detailed spectral and spatial information across diverse applications. Despite the advancements in deep learning (DL) and Transformer architectures for HSI classification, challenges such as computational efficiency and the need for extensive labeled data persist. This letter introduces WaveMamba, a novel approach that integrates wavelet transformation with the spatial-spectral Mamba (SSMamba) architecture to enhance HSI classification. WaveMamba captures both local texture patterns and global contextual relationships in an end-to-end trainable model. The Wavelet-based enhanced features are then processed through the state-space architecture to model spatial-spectral relationships and temporal dependencies. The experimental results indicate that WaveMamba surpasses existing models, achieving an accuracy improvement of 4.5% on the University of Houston dataset and a 2.0% increase on the Pavia University dataset.
{"title":"WaveMamba: Spatial-Spectral Wavelet Mamba for Hyperspectral Image Classification","authors":"Muhammad Ahmad;Muhammad Usama;Manuel Mazzara;Salvatore Distefano","doi":"10.1109/LGRS.2024.3506034","DOIUrl":"https://doi.org/10.1109/LGRS.2024.3506034","url":null,"abstract":"Hyperspectral imaging (HSI) has proven to be a powerful tool for capturing detailed spectral and spatial information across diverse applications. Despite the advancements in deep learning (DL) and Transformer architectures for HSI classification, challenges such as computational efficiency and the need for extensive labeled data persist. This letter introduces WaveMamba, a novel approach that integrates wavelet transformation with the spatial-spectral Mamba (SSMamba) architecture to enhance HSI classification. WaveMamba captures both local texture patterns and global contextual relationships in an end-to-end trainable model. The Wavelet-based enhanced features are then processed through the state-space architecture to model spatial-spectral relationships and temporal dependencies. The experimental results indicate that WaveMamba surpasses existing models, achieving an accuracy improvement of 4.5% on the University of Houston dataset and a 2.0% increase on the Pavia University dataset.","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":"2024-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142844476","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}
Traditional ground-penetrating radar (GPR) inversion techniques, while capable of providing high-resolution subsurface imaging, suffer from issues, such as heavy reliance on initial models, high computational demands, and sensitivity to noise and data incompleteness. In contrast, deep-learning-based methods excel in feature extraction and model fitting. However, as a data-driven algorithm, the practical application of convolutional neural networks (CNNs) is limited by the quantity of labeled samples. To reduce the dependence of CNN-based GPR inversion methods on observational data and labels, this project proposes an inversion method based on closed-loop CNNs (CL-CNNs). This approach improves inversion accuracy and reduces the ill-posedness of GPR inversion by modeling both the forward and inverse GPR processes. The CL structure increases the number of features that CNNs can learn from limited labeled samples, while the mutual inversion constraints between the forward and inverse subnetworks help alleviate the ill-posedness of the inversion problem, making the inversion results more consistent with geological principles. Research using synthetic data demonstrates that this method outperforms traditional approaches, as evidenced by enhanced structural similarity index (SSIM) and peak signal-to-noise ratio (PSNR), and a significantly lower mean-squared error (mse), highlighting its advanced performance compared with traditional open-loop CNNs (OL-CNNs). Furthermore, applying this method to real measurement data further validates its effectiveness and practical applicability in engineering contexts, emphasizing its significant practical value.
{"title":"Enhanced Ground-Penetrating Radar Inversion With Closed-Loop Convolutional Neural Networks","authors":"Meijia Huang;Jieyong Liang;Ziyang Zhou;Xuelei Li;Zhijun Huo;Zhuo Jia","doi":"10.1109/LGRS.2024.3505594","DOIUrl":"https://doi.org/10.1109/LGRS.2024.3505594","url":null,"abstract":"Traditional ground-penetrating radar (GPR) inversion techniques, while capable of providing high-resolution subsurface imaging, suffer from issues, such as heavy reliance on initial models, high computational demands, and sensitivity to noise and data incompleteness. In contrast, deep-learning-based methods excel in feature extraction and model fitting. However, as a data-driven algorithm, the practical application of convolutional neural networks (CNNs) is limited by the quantity of labeled samples. To reduce the dependence of CNN-based GPR inversion methods on observational data and labels, this project proposes an inversion method based on closed-loop CNNs (CL-CNNs). This approach improves inversion accuracy and reduces the ill-posedness of GPR inversion by modeling both the forward and inverse GPR processes. The CL structure increases the number of features that CNNs can learn from limited labeled samples, while the mutual inversion constraints between the forward and inverse subnetworks help alleviate the ill-posedness of the inversion problem, making the inversion results more consistent with geological principles. Research using synthetic data demonstrates that this method outperforms traditional approaches, as evidenced by enhanced structural similarity index (SSIM) and peak signal-to-noise ratio (PSNR), and a significantly lower mean-squared error (mse), highlighting its advanced performance compared with traditional open-loop CNNs (OL-CNNs). Furthermore, applying this method to real measurement data further validates its effectiveness and practical applicability in engineering contexts, emphasizing its significant practical value.","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":"2024-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142777664","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}
Elastic parameters such as compressional-wave velocity and shear-wave velocity are essential for characterizing and predicting oil-gas reservoirs. However, the current commonly used shear-wave velocity prediction methods have problems such as weak generalization of empirical formulas and difficulty in obtaining some rock parameters in various rock physics models. We proposed a deep learning network based on the self-attention mechanism to predict shear-wave velocity. First, we need to extract the spatial and temporal features of well logging data using convolutional neural network (CNN) and gated recurrent unit (GRU), respectively. However, the spatial and temporal features exhibit different correlations in the depth direction due to the gradual variation of sedimentary layers. Thus, we fuse the self-attention mechanism with the deep learning network to enhance the network’s sensitivity to crucial spatiotemporal features. Finally, we take the tight sandstone reservoir of Tarim Basin as the research object to estimate shear-wave velocity using CNN, GRU network, and our optimized method. The results show that the CNN-GRU fusion network based on the self-attention mechanism network we proposed is better than the other two networks in the prediction accuracy and generalization degree.
{"title":"Shear-Wave Velocity Prediction by CNN-GRU Fusion Network Based on the Self-Attention Mechanism","authors":"Yahua Yang;Junfeng Zhao;Huanfu Du;Xingyao Yin;Tengfei Chen","doi":"10.1109/LGRS.2024.3506017","DOIUrl":"https://doi.org/10.1109/LGRS.2024.3506017","url":null,"abstract":"Elastic parameters such as compressional-wave velocity and shear-wave velocity are essential for characterizing and predicting oil-gas reservoirs. However, the current commonly used shear-wave velocity prediction methods have problems such as weak generalization of empirical formulas and difficulty in obtaining some rock parameters in various rock physics models. We proposed a deep learning network based on the self-attention mechanism to predict shear-wave velocity. First, we need to extract the spatial and temporal features of well logging data using convolutional neural network (CNN) and gated recurrent unit (GRU), respectively. However, the spatial and temporal features exhibit different correlations in the depth direction due to the gradual variation of sedimentary layers. Thus, we fuse the self-attention mechanism with the deep learning network to enhance the network’s sensitivity to crucial spatiotemporal features. Finally, we take the tight sandstone reservoir of Tarim Basin as the research object to estimate shear-wave velocity using CNN, GRU network, and our optimized method. The results show that the CNN-GRU fusion network based on the self-attention mechanism network we proposed is better than the other two networks in the prediction accuracy and generalization degree.","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":"2024-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142798001","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 : 2024-11-25DOI: 10.1109/LGRS.2024.3505193
Enze Zhu;Zhan Chen;Dingkai Wang;Hanru Shi;Xiaoxuan Liu;Lei Wang
Semantic segmentation of high-resolution remote sensing images is vital in downstream applications such as land-cover mapping, urban planning, and disaster assessment. Existing Transformer-based methods suffer from the constraint between accuracy and efficiency, while the recently proposed Mamba is renowned for being efficient. Therefore, to overcome the dilemma, we propose UNetMamba, a UNet-like semantic segmentation model based on Mamba. It incorporates a Mamba segmentation decoder (MSD) that can efficiently decode the complex information within high-resolution images, and a local supervision module (LSM), which is train-only but can significantly enhance the perception of local contents. Extensive experiments demonstrate that UNetMamba outperforms the state-of-the-art (SOTA) methods with mIoU increased by 0.87% on LoveDA and 0.39% on ISPRS Vaihingen while achieving high efficiency through the lightweight design, less memory footprint, and reduced computational cost. The source code is available at https://github.com/EnzeZhu2001/UNetMamba