Hyperspectral image (HSI) is pivotal in ground object classification, owing to its rich spatial and spectral information. Recently, convolutional neural networks and graph neural networks have become hotspots in HSI classification. Although various methods have been developed, the problem of detail loss may still exist when extracting complex features within homogenous regions. To solve this issue, in this article, we proposed a double-hop graph attention multiview fusion network. This model is adept at pinpointing precise attention features by integrating a double-hop graph with the graph attention network, thereby enhancing the aggregation of multilevel node information and surmounting the limitations of a restricted receptive field. Furthermore, the spectral-coordinate attention module (SCAM) is presented to seize more nuanced spectral and spatial attention features. SCAM harnesses the coordinate attention mechanism for in-depth pixel-level global spectral–spatial view. Coupled with the multiscale Gabor texture view, we forge a multiview fusion network that meticulously highlights edge details across varying scales and captures beneficial features. Our experimental validation across four renowned benchmark HSI datasets showcases our model's superiority, outstripping comparative methods in classification accuracy with limited labeled samples.
{"title":"Hyperspectral Image Classification Based on Double-Hop Graph Attention Multiview Fusion Network","authors":"Ying Cui;Li Luo;Lu Wang;Liwei Chen;Shan Gao;Chunhui Zhao;Cheng Tang","doi":"10.1109/JSTARS.2024.3486283","DOIUrl":"https://doi.org/10.1109/JSTARS.2024.3486283","url":null,"abstract":"Hyperspectral image (HSI) is pivotal in ground object classification, owing to its rich spatial and spectral information. Recently, convolutional neural networks and graph neural networks have become hotspots in HSI classification. Although various methods have been developed, the problem of detail loss may still exist when extracting complex features within homogenous regions. To solve this issue, in this article, we proposed a double-hop graph attention multiview fusion network. This model is adept at pinpointing precise attention features by integrating a double-hop graph with the graph attention network, thereby enhancing the aggregation of multilevel node information and surmounting the limitations of a restricted receptive field. Furthermore, the spectral-coordinate attention module (SCAM) is presented to seize more nuanced spectral and spatial attention features. SCAM harnesses the coordinate attention mechanism for in-depth pixel-level global spectral–spatial view. Coupled with the multiscale Gabor texture view, we forge a multiview fusion network that meticulously highlights edge details across varying scales and captures beneficial features. Our experimental validation across four renowned benchmark HSI datasets showcases our model's superiority, outstripping comparative methods in classification accuracy with limited labeled samples.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"17 ","pages":"20080-20097"},"PeriodicalIF":4.7,"publicationDate":"2024-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10735087","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142645537","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}
Pub Date : 2024-10-24DOI: 10.1109/JSTARS.2024.3485890
Ninghui Li;Lei Guan;Jonathon S. Wright
Sea surface temperature (SST) is a vital oceanic parameter that significantly influences air–sea heat flux and momentum exchange. SST datasets are crucial for identifying and describing both short-term and long-term climate perturbations in the ocean. This article focuses on cloud detection and SST retrievals in the Western Pacific Ocean, using observations obtained by the Chinese Ocean Color and Temperature Scanner (COCTS) onboard the Haiyang-1C satellite. To distinguish between clear-sky and overcast regions, reflectance after sun glint correction and brightness temperature are used as inputs for an alternative decision tree (ADTree). The accuracy of cloud detection is 93.85% for daytime and 91.98% for nighttime, respectively. Application of the cloud detection algorithm improves the accuracy and data availability (spatiotemporal coverage) of SST retrievals. We implement a nonlinear algorithm to retrieve the SST and validate these retrieved values against buoy measurements of SST. Comparisons are conducted for measurements within ±1 h and 0.01° × 0.01° of the retrieval. During the day, the bias and standard deviation (SD) are −0.01 °C and 0.63 °C, respectively, while at night, they stand at −0.08 °C and 0.71 °C, respectively. Furthermore, the intercomparison between the SST products derived from the moderate-resolution imaging spectroradiometer (MODIS) onboard Terra and the results are conducted. During the day, the bias and SD are 0.03 °C and 0.42 °C, respectively, whereas at night, they are 0.25 °C and 0.76 °C, respectively. This article improves the accuracy and applicability of the SST retrieved from the COCTS thermal infrared channels.
{"title":"Cloud Detection and Sea Surface Temperature Retrieval by HY-1C COCTS Observations","authors":"Ninghui Li;Lei Guan;Jonathon S. Wright","doi":"10.1109/JSTARS.2024.3485890","DOIUrl":"https://doi.org/10.1109/JSTARS.2024.3485890","url":null,"abstract":"Sea surface temperature (SST) is a vital oceanic parameter that significantly influences air–sea heat flux and momentum exchange. SST datasets are crucial for identifying and describing both short-term and long-term climate perturbations in the ocean. This article focuses on cloud detection and SST retrievals in the Western Pacific Ocean, using observations obtained by the Chinese Ocean Color and Temperature Scanner (COCTS) onboard the Haiyang-1C satellite. To distinguish between clear-sky and overcast regions, reflectance after sun glint correction and brightness temperature are used as inputs for an alternative decision tree (ADTree). The accuracy of cloud detection is 93.85% for daytime and 91.98% for nighttime, respectively. Application of the cloud detection algorithm improves the accuracy and data availability (spatiotemporal coverage) of SST retrievals. We implement a nonlinear algorithm to retrieve the SST and validate these retrieved values against buoy measurements of SST. Comparisons are conducted for measurements within ±1 h and 0.01° × 0.01° of the retrieval. During the day, the bias and standard deviation (SD) are −0.01 °C and 0.63 °C, respectively, while at night, they stand at −0.08 °C and 0.71 °C, respectively. Furthermore, the intercomparison between the SST products derived from the moderate-resolution imaging spectroradiometer (MODIS) onboard Terra and the results are conducted. During the day, the bias and SD are 0.03 °C and 0.42 °C, respectively, whereas at night, they are 0.25 °C and 0.76 °C, respectively. This article improves the accuracy and applicability of the SST retrieved from the COCTS thermal infrared channels.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"17 ","pages":"19853-19863"},"PeriodicalIF":4.7,"publicationDate":"2024-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10734229","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142636326","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}
Pub Date : 2024-10-24DOI: 10.1109/JSTARS.2024.3485734
Ming Tong;Shenghua Fan;Jiu Jiang;Chu He
Ship detection achieves great significance in remote sensing of synthetic aperture radar (SAR) and many efforts have been done in recent years. However, distinguishing ship targets precisely from the interference of multiplicative non-Gaussian coherent speckle is still a challenging task due to the discreteness, variability, and nonlinearity of ship scattering features. A detection framework based on hierarchical sampling representation is introduced to alleviate the phenomenon in this article. First, ships in SAR images exhibit multiplicative non-Gaussian coherent speckle, which introduces nonlinear characteristics under the imaging mechanism of SAR. Therefore, a statistical feature learning module is proposed with a learnable design to describe the nonlinear representations and expand the feature space. Second, our method designs a convex-hull representation to fit the irregular contours of ships represented by strong scattering points. Third, in order to supervise and optimize the regression of convex-hull representation, a sparse low-rank reassignment module is employed to evaluate the positive samples with SAR mechanism and reassign ones of high quality, which produces better results. Furthermore, experimental results on three authoritative SAR-oriented datasets for ship detection application present the comprehensive performance of our method.
船舶探测在合成孔径雷达（SAR）遥感中具有重要意义，近年来人们已经做了很多努力。然而，由于船舶散射特征的离散性、可变性和非线性，从乘法非高斯相干斑点的干扰中精确区分船舶目标仍然是一项具有挑战性的任务。本文介绍了一种基于分层采样表示的检测框架来缓解这一现象。首先，合成孔径雷达图像中的船舶表现出乘法非高斯相干斑点，这在合成孔径雷达成像机制下引入了非线性特征。因此，本文提出了一个统计特征学习模块，通过可学习设计来描述非线性表征并扩展特征空间。其次，我们的方法设计了一种凸船体表示法，以拟合由强散射点表示的不规则船舶轮廓。第三，为了监督和优化凸船体表示的回归，我们采用了稀疏低秩重配模块，利用 SAR 机制评估正样本，并重配高质量样本，从而获得更好的结果。此外，在三个面向合成孔径雷达的权威数据集上进行的船舶检测应用实验结果表明了我们方法的综合性能。
{"title":"Hierarchical Sampling Representation Detector for Ship Detection in SAR Images","authors":"Ming Tong;Shenghua Fan;Jiu Jiang;Chu He","doi":"10.1109/JSTARS.2024.3485734","DOIUrl":"https://doi.org/10.1109/JSTARS.2024.3485734","url":null,"abstract":"Ship detection achieves great significance in remote sensing of synthetic aperture radar (SAR) and many efforts have been done in recent years. However, distinguishing ship targets precisely from the interference of multiplicative non-Gaussian coherent speckle is still a challenging task due to the discreteness, variability, and nonlinearity of ship scattering features. A detection framework based on hierarchical sampling representation is introduced to alleviate the phenomenon in this article. First, ships in SAR images exhibit multiplicative non-Gaussian coherent speckle, which introduces nonlinear characteristics under the imaging mechanism of SAR. Therefore, a statistical feature learning module is proposed with a learnable design to describe the nonlinear representations and expand the feature space. Second, our method designs a convex-hull representation to fit the irregular contours of ships represented by strong scattering points. Third, in order to supervise and optimize the regression of convex-hull representation, a sparse low-rank reassignment module is employed to evaluate the positive samples with SAR mechanism and reassign ones of high quality, which produces better results. Furthermore, experimental results on three authoritative SAR-oriented datasets for ship detection application present the comprehensive performance of our method.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"17 ","pages":"19530-19547"},"PeriodicalIF":4.7,"publicationDate":"2024-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10733998","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142600182","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}
Pub Date : 2024-10-24DOI: 10.1109/JSTARS.2024.3486210
Ying Liu;Jin Liu;Xingye Li;Lai Wei;Zhongdai Wu;Bing Han;Wenjuan Dai
Fine-grained remote sensing ship detection is crucial in a variety of fields, such as ship safety, marine environmental protection, and maritime traffic management. Despite recent progress, current research suffers from the following three major challenges: insufficient features representation, conflicts in shared features, and inappropriate anchor labeling strategy, which significantly impede accurate fine-grained ship detection. To address these issues, we propose FineShipNet as a solution. Specifically, we first propose a novel blend synchronization module, which aims to facilitate the coutilization of semantic information from top-level and bottom-level features and minimize information redundancy. Subsequently, the blend feature maps are fed into a novel polarized feature focusing module, which decouples the features used in classification and regression to create task-specific discriminating features maps. Meanwhile, we adopt the adaptive harmony anchor labeling and propose a novel metric, harmony score, to choose high-quality anchors that can effectively capture the discriminating features of the target. Extensive experiments on four fine-grained remote sensing ship datasets (HRSC2016, DOSR, FGSD2021, and ShipRSImageNet) demonstrate that our FineShipNet outperforms current state-of-the-art object detection methods, achieving superior performance with mean average precision scores of 81.3%, 68.5%, 85.7%, and 63.9%, respectively.
{"title":"Exploiting Discriminating Features for Fine-Grained Ship Detection in Optical Remote Sensing Images","authors":"Ying Liu;Jin Liu;Xingye Li;Lai Wei;Zhongdai Wu;Bing Han;Wenjuan Dai","doi":"10.1109/JSTARS.2024.3486210","DOIUrl":"https://doi.org/10.1109/JSTARS.2024.3486210","url":null,"abstract":"Fine-grained remote sensing ship detection is crucial in a variety of fields, such as ship safety, marine environmental protection, and maritime traffic management. Despite recent progress, current research suffers from the following three major challenges: insufficient features representation, conflicts in shared features, and inappropriate anchor labeling strategy, which significantly impede accurate fine-grained ship detection. To address these issues, we propose FineShipNet as a solution. Specifically, we first propose a novel blend synchronization module, which aims to facilitate the coutilization of semantic information from top-level and bottom-level features and minimize information redundancy. Subsequently, the blend feature maps are fed into a novel polarized feature focusing module, which decouples the features used in classification and regression to create task-specific discriminating features maps. Meanwhile, we adopt the adaptive harmony anchor labeling and propose a novel metric, harmony score, to choose high-quality anchors that can effectively capture the discriminating features of the target. Extensive experiments on four fine-grained remote sensing ship datasets (HRSC2016, DOSR, FGSD2021, and ShipRSImageNet) demonstrate that our FineShipNet outperforms current state-of-the-art object detection methods, achieving superior performance with mean average precision scores of 81.3%, 68.5%, 85.7%, and 63.9%, respectively.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"17 ","pages":"20098-20115"},"PeriodicalIF":4.7,"publicationDate":"2024-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10733997","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142645451","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}
Pub Date : 2024-10-24DOI: 10.1109/JSTARS.2024.3486187
Haoqi Gu;Lianchong Zhang;Mengjiao Qin;Sensen Wu;Zhenhong Du
With the accelerating impact of global warming, the changes of Arctic sea ice has become a focal point of research. Due to the spatial heterogeneity and the complexity of its evolution, long-term prediction of Arctic sea ice remains a challenge. In this article, a spatial attention U-Net (SAU-Net) method integrated with a gated spatial attention mechanism is proposed. Extracting and enhancing the spatial features from the historical atmospheric and SIC data, this method improves the accuracy of Arctic sea ice prediction. During the test periods (2018–2020), our method can skillfully predict the Arctic sea ice up to 12 months, outperforming the naive U-Net, linear trend models, and dynamical models, especially in extreme sea ice scenarios. The importance of different atmospheric factors affecting sea ice prediction are also analyzed for further exploration.
随着全球变暖影响的加速，北极海冰的变化已成为研究的焦点。由于北极海冰的空间异质性及其演变的复杂性，对其进行长期预测仍是一项挑战。本文提出了一种集成了门控空间注意力机制的空间注意力 U-Net （SAU-Net）方法。该方法从历史大气和 SIC 数据中提取并增强空间特征，提高了北极海冰预测的准确性。在测试期间（2018-2020 年），我们的方法可以熟练预测长达 12 个月的北极海冰，优于天真 U-Net、线性趋势模型和动力学模型，尤其是在极端海冰情况下。此外，还分析了不同大气因素对海冰预测的重要影响，以供进一步探讨。
{"title":"Arctic Sea Ice Concentration Prediction Using Spatial Attention Deep Learning","authors":"Haoqi Gu;Lianchong Zhang;Mengjiao Qin;Sensen Wu;Zhenhong Du","doi":"10.1109/JSTARS.2024.3486187","DOIUrl":"https://doi.org/10.1109/JSTARS.2024.3486187","url":null,"abstract":"With the accelerating impact of global warming, the changes of Arctic sea ice has become a focal point of research. Due to the spatial heterogeneity and the complexity of its evolution, long-term prediction of Arctic sea ice remains a challenge. In this article, a spatial attention U-Net (SAU-Net) method integrated with a gated spatial attention mechanism is proposed. Extracting and enhancing the spatial features from the historical atmospheric and SIC data, this method improves the accuracy of Arctic sea ice prediction. During the test periods (2018–2020), our method can skillfully predict the Arctic sea ice up to 12 months, outperforming the naive U-Net, linear trend models, and dynamical models, especially in extreme sea ice scenarios. The importance of different atmospheric factors affecting sea ice prediction are also analyzed for further exploration.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"17 ","pages":"19565-19574"},"PeriodicalIF":4.7,"publicationDate":"2024-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10734000","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142636472","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}
Red–green–blue (RGB) images (or videos) captured by consumer-level uncrewedaerial vehicle (UAV) cameras are widely used in high-resolution remote observations. However, digital number (DN) values of these RGB images usually have a nonlinear relationship with the incident radiance, which reduces the accuracy of quantitative remote sensing of macroalgae. To solve this problem, we proposed an improved processing procedure for UAV RGB images (or videos) based on camera response functions (CRFs). The CRF was utilized to convert the DN values into energy values ( E values), which demonstrate a linear relationship with the incident radiance. When the DN values were replaced by their corresponding E values to calculate the reflectance of green macroalgae under different illumination intensities, the errors in reflectance were reduced by ∼21%; for the corresponding green macroalgae indices, such as the red–green band virtual baseline floating green algae height (RG-FAH), the E -value-based RG-FAH demonstrates more resistance to the impacts of sun glints; and the E values were further applied to estimate the coverage portion of macroalgae (POM, %) in RGB videos; the illumination-induced deviations of the POM were effectively reduced by up to 33.06%, showing an advantage in quantitative estimation of macroalgae biomass. The results of applications to UAV RGB images show that the E values have significant suitability in estimating POM across diverse green macroalgae species and various algae indices, suggesting promising potentials of the proposed processing procedure with E -based photo and/or video RGB images in monitoring aquatic plants and environment.
{"title":"An Improved UAV RGB Image Processing Method for Quantitative Remote Sensing of Marine Green Macroalgae","authors":"Jinghu Li;Qianguo Xing;Liqiao Tian;Yingzhuo Hou;Xiangyang Zheng;Maham Arif;Lin Li;Shanshan Jiang;Jiannan Cai;Jun Chen;Yingcheng Lu;Dingfeng Yu;Jindong Xu","doi":"10.1109/JSTARS.2024.3486045","DOIUrl":"https://doi.org/10.1109/JSTARS.2024.3486045","url":null,"abstract":"Red–green–blue (RGB) images (or videos) captured by consumer-level uncrewedaerial vehicle (UAV) cameras are widely used in high-resolution remote observations. However, digital number (DN) values of these RGB images usually have a nonlinear relationship with the incident radiance, which reduces the accuracy of quantitative remote sensing of macroalgae. To solve this problem, we proposed an improved processing procedure for UAV RGB images (or videos) based on camera response functions (CRFs). The CRF was utilized to convert the DN values into energy values (\u0000<italic>E</i>\u0000 values), which demonstrate a linear relationship with the incident radiance. When the DN values were replaced by their corresponding \u0000<italic>E</i>\u0000 values to calculate the reflectance of green macroalgae under different illumination intensities, the errors in reflectance were reduced by ∼21%; for the corresponding green macroalgae indices, such as the red–green band virtual baseline floating green algae height (RG-FAH), the \u0000<italic>E</i>\u0000-value-based RG-FAH demonstrates more resistance to the impacts of sun glints; and the \u0000<italic>E</i>\u0000 values were further applied to estimate the coverage portion of macroalgae (POM, %) in RGB videos; the illumination-induced deviations of the POM were effectively reduced by up to 33.06%, showing an advantage in quantitative estimation of macroalgae biomass. The results of applications to UAV RGB images show that the \u0000<italic>E</i>\u0000 values have significant suitability in estimating POM across diverse green macroalgae species and various algae indices, suggesting promising potentials of the proposed processing procedure with \u0000<italic>E</i>\u0000-based photo and/or video RGB images in monitoring aquatic plants and environment.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"17 ","pages":"19864-19883"},"PeriodicalIF":4.7,"publicationDate":"2024-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10734187","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142636471","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}
Pub Date : 2024-10-23DOI: 10.1109/JSTARS.2024.3485528
Anan Yaghmour;Saurabh Prasad;Melba M. Crawford
In geospatial image analysis, domain shifts caused by differences between datasets often undermine the performance of deep learning models due to their limited generalization ability. This issue is particularly pronounced in hyperspectral imagery, given the high dimensionality of the per-pixel reflectance vectors and the complexity of the resulting deep learning models. We introduce a semisupervised domain adaptation technique that improves on the adversarial discriminative framework, incorporating a novel multiclass discriminator to address low discriminability and negative transfer issues from which current approaches suffer. Significantly, our method addresses mode collapse by incorporating limited labeled data from the target domain for targeted guidance during adaptation. In addition, we integrate an attention mechanism that focuses on challenging spatial regions for the target mode. We tested our approach on three unique hyperspectral remote sensing datasets to demonstrate its efficacy in diverse conditions (e.g., cloud shadows, atmospheric variability, and terrain). This strategy improves discrimination and reduces negative transfer in domain adaptation for geospatial image analysis.
{"title":"Attention Guided Semisupervised Generative Transfer Learning for Hyperspectral Image Analysis","authors":"Anan Yaghmour;Saurabh Prasad;Melba M. Crawford","doi":"10.1109/JSTARS.2024.3485528","DOIUrl":"https://doi.org/10.1109/JSTARS.2024.3485528","url":null,"abstract":"In geospatial image analysis, domain shifts caused by differences between datasets often undermine the performance of deep learning models due to their limited generalization ability. This issue is particularly pronounced in hyperspectral imagery, given the high dimensionality of the per-pixel reflectance vectors and the complexity of the resulting deep learning models. We introduce a semisupervised domain adaptation technique that improves on the adversarial discriminative framework, incorporating a novel multiclass discriminator to address low discriminability and negative transfer issues from which current approaches suffer. Significantly, our method addresses mode collapse by incorporating limited labeled data from the target domain for targeted guidance during adaptation. In addition, we integrate an attention mechanism that focuses on challenging spatial regions for the target mode. We tested our approach on three unique hyperspectral remote sensing datasets to demonstrate its efficacy in diverse conditions (e.g., cloud shadows, atmospheric variability, and terrain). This strategy improves discrimination and reduces negative transfer in domain adaptation for geospatial image analysis.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"17 ","pages":"19884-19899"},"PeriodicalIF":4.7,"publicationDate":"2024-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10731899","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142636328","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}
Pub Date : 2024-10-23DOI: 10.1109/JSTARS.2024.3485091
Jiawei Luo;Yulin Huang;Ruitao Li;Deqing Mao;Yongchao Zhang;Yin Zhang;Jianyu Yang
Recently, a sparse super-resolution method based on $L_{1}$ iterative reweighted norm (IRN) has been proposed to improve the azimuth resolution of forward-looking radar. However, this method suffers from poor adaptability and high computational complexity due to its noise-sensitive user-parameter and the necessity for high-dimensional matrix inversion. To this end, a fast adaptive $L_{1}$ -IRN sparse super-resolution method is derived in this article, allowing for the user-parameter-free and efficient sparse imaging of forward-looking radar. First, we establish the super-resolution model of forward-looking radar and analyze the user parameter selection problem in the conventional $L_{1}$ -IRN method. Second, based on Bayesian theory, adaptive iterative weights of different azimuths are derived by transforming the sparse estimation problem into a maximum posterior (MAP) estimation problem. Finally, by using QR decomposition and Sherman–Morrison formula, the dimensionality of the echo and antenna pattern involved in the iteration is reduced to further diminish the computational complexity. Compared to the existing $L_{1}$ -IRN method, the proposed method eliminates the need for any user parameters, and the computational complexity has been reduced from ${O}({JN}^{3})$ to ${O}({JN}^{2}{a})$ . Simulation and measured data demonstrate the superiority of the proposed method.
{"title":"Fast Adaptive Sparse Iterative Reweighted Super-Resolution Method for Forward-Looking Radar Imaging","authors":"Jiawei Luo;Yulin Huang;Ruitao Li;Deqing Mao;Yongchao Zhang;Yin Zhang;Jianyu Yang","doi":"10.1109/JSTARS.2024.3485091","DOIUrl":"https://doi.org/10.1109/JSTARS.2024.3485091","url":null,"abstract":"Recently, a sparse super-resolution method based on \u0000<inline-formula><tex-math>$L_{1}$</tex-math></inline-formula>\u0000 iterative reweighted norm (IRN) has been proposed to improve the azimuth resolution of forward-looking radar. However, this method suffers from poor adaptability and high computational complexity due to its noise-sensitive user-parameter and the necessity for high-dimensional matrix inversion. To this end, a fast adaptive \u0000<inline-formula><tex-math>$L_{1}$</tex-math></inline-formula>\u0000-IRN sparse super-resolution method is derived in this article, allowing for the user-parameter-free and efficient sparse imaging of forward-looking radar. First, we establish the super-resolution model of forward-looking radar and analyze the user parameter selection problem in the conventional \u0000<inline-formula><tex-math>$L_{1}$</tex-math></inline-formula>\u0000-IRN method. Second, based on Bayesian theory, adaptive iterative weights of different azimuths are derived by transforming the sparse estimation problem into a maximum posterior (MAP) estimation problem. Finally, by using QR decomposition and Sherman–Morrison formula, the dimensionality of the echo and antenna pattern involved in the iteration is reduced to further diminish the computational complexity. Compared to the existing \u0000<inline-formula><tex-math>$L_{1}$</tex-math></inline-formula>\u0000-IRN method, the proposed method eliminates the need for any user parameters, and the computational complexity has been reduced from \u0000<inline-formula><tex-math>${O}({JN}^{3})$</tex-math></inline-formula>\u0000 to \u0000<inline-formula><tex-math>${O}({JN}^{2}{a})$</tex-math></inline-formula>\u0000. Simulation and measured data demonstrate the superiority of the proposed method.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"17 ","pages":"19503-19517"},"PeriodicalIF":4.7,"publicationDate":"2024-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10729867","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142600371","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}
Pub Date : 2024-10-23DOI: 10.1109/JSTARS.2024.3485168
Sijia Chen;Changjun Zhao;Mi Jiang;Hanwen Yu
In the field of multitemporal interferometric synthetic aperture radar (MT-InSAR), the selection of persistent scatterer (PS) is crucial for acquiring ground deformation product. To obtain precise ground deformation, pixels with as high signal-to-noise ratio (SNR) as possible should be selected, while pixels with low SNR should be avoided. To this end, we propose a novel framework, referred to as the PS feature-fusion network (PSFNet), for efficient PS selection. Specifically, we propose a data-driven two-branch network consisting of a ResUNet with spatial and channel attention, as well as a TANet with 3-D convolutional layers and a time-step attention block (T-Attention block), which can use not only spatial features of SAR image but also time-series phase features when selecting PS pixels. In particular, a time-step attention mechanism is proposed for accommodating to interferometric pairs with different SNRs to enhance the feature representation ability of the network. The proposed method was tested using the Sentinel-1 images, showing that it can select more PSs with higher quality compared with StaMPS. In addition, the prediction time of PSFNet requires only 0.26% of the running time of StaMPS, which greatly improves the efficiency of PSFNet for practical applications.
{"title":"PSFNet: A Feature-Fusion Framework for Persistent Scatterer Selection in Multitemporal InSAR","authors":"Sijia Chen;Changjun Zhao;Mi Jiang;Hanwen Yu","doi":"10.1109/JSTARS.2024.3485168","DOIUrl":"https://doi.org/10.1109/JSTARS.2024.3485168","url":null,"abstract":"In the field of multitemporal interferometric synthetic aperture radar (MT-InSAR), the selection of persistent scatterer (PS) is crucial for acquiring ground deformation product. To obtain precise ground deformation, pixels with as high signal-to-noise ratio (SNR) as possible should be selected, while pixels with low SNR should be avoided. To this end, we propose a novel framework, referred to as the PS feature-fusion network (PSFNet), for efficient PS selection. Specifically, we propose a data-driven two-branch network consisting of a ResUNet with spatial and channel attention, as well as a TANet with 3-D convolutional layers and a time-step attention block (T-Attention block), which can use not only spatial features of SAR image but also time-series phase features when selecting PS pixels. In particular, a time-step attention mechanism is proposed for accommodating to interferometric pairs with different SNRs to enhance the feature representation ability of the network. The proposed method was tested using the Sentinel-1 images, showing that it can select more PSs with higher quality compared with StaMPS. In addition, the prediction time of PSFNet requires only 0.26% of the running time of StaMPS, which greatly improves the efficiency of PSFNet for practical applications.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"17 ","pages":"19972-19985"},"PeriodicalIF":4.7,"publicationDate":"2024-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10729861","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142691821","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}
Utilizing massive spatio-temporal sequence data and real-time synthetic aperture radar (SAR) ship target monitoring technology, it is possible to effectively predict the future trajectories and intents of ships. While real-time monitoring technology validates and adjusts spatio-temporal sequence prediction models, it still faces challenges, such as manual anchor box sizing and slow inference speeds due to large computational parameters. To address this challenge, a SAR ship target real-time detection method based on CenterNet is introduced in this article. The proposed method comprises the following steps. First, to improve the feature extraction capability of the original CenterNet network, we introduce a feature pyramid fusion structure and replace upsampled deconvolution with Deformable Convolution Networks (DCNets), which enable richer feature map outputs. Then, to identify nearshore and small target ships better, BiFormer attention mechanism and spatial pyramid pooling module are incorporated to enlarge the receptive field of network. Finally, to improve accuracy and convergence speed, we optimize the Focal loss of the heatmap and utilize Smooth L1 loss for width, height, and center point offsets, which enhance detection accuracy and generalization. Performance evaluations on two SAR image ship datasets, HRSID and SSDD, validate the method's effectiveness, achieving Average Precision (AP) values of 82.87% and 94.25%, representing improvements of 5.26% and 4.04% in AP compared to the original models, with detection speeds of 49 FPS on both datasets. These results underscore the superiority of the improved CenterNet method over other representative methods for SAR ship detection in overall performance.
{"title":"A Real-Time SAR Ship Detection Method Based on Improved CenterNet for Navigational Intent Prediction","authors":"Xiao Tang;Jiufeng Zhang;Yunzhi Xia;Enkun Cui;Weining Zhao;Qiong Chen","doi":"10.1109/JSTARS.2024.3485222","DOIUrl":"https://doi.org/10.1109/JSTARS.2024.3485222","url":null,"abstract":"Utilizing massive spatio-temporal sequence data and real-time synthetic aperture radar (SAR) ship target monitoring technology, it is possible to effectively predict the future trajectories and intents of ships. While real-time monitoring technology validates and adjusts spatio-temporal sequence prediction models, it still faces challenges, such as manual anchor box sizing and slow inference speeds due to large computational parameters. To address this challenge, a SAR ship target real-time detection method based on CenterNet is introduced in this article. The proposed method comprises the following steps. First, to improve the feature extraction capability of the original CenterNet network, we introduce a feature pyramid fusion structure and replace upsampled deconvolution with Deformable Convolution Networks (DCNets), which enable richer feature map outputs. Then, to identify nearshore and small target ships better, BiFormer attention mechanism and spatial pyramid pooling module are incorporated to enlarge the receptive field of network. Finally, to improve accuracy and convergence speed, we optimize the Focal loss of the heatmap and utilize Smooth L1 loss for width, height, and center point offsets, which enhance detection accuracy and generalization. Performance evaluations on two SAR image ship datasets, HRSID and SSDD, validate the method's effectiveness, achieving Average Precision (AP) values of 82.87% and 94.25%, representing improvements of 5.26% and 4.04% in AP compared to the original models, with detection speeds of 49 FPS on both datasets. These results underscore the superiority of the improved CenterNet method over other representative methods for SAR ship detection in overall performance.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"17 ","pages":"19467-19477"},"PeriodicalIF":4.7,"publicationDate":"2024-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10729880","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142600228","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}
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：