IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing最新文献

{"title":"A Recurrent Feedback Hyperspectral Image Super-Resolution Reconstruction Method by Using Self-Attention-Based Pixel Awareness","authors":"Ruyi Feng;Zhongyu Guo;Xiaofeng Wang","doi":"10.1109/JSTARS.2024.3471899","DOIUrl":"https://doi.org/10.1109/JSTARS.2024.3471899","url":null,"abstract":"Hyperspectral images (HSIs) contain abundant spectral information, while the spatial resolution is usually limited. To obtain high-spatial-resolution HSIs, various HSI super-resolution (SR) methods are proposed. Currently, deep-learning-based SR reconstruction methods are studied in depth, which take different measures to make full use of the spatial and spectral information of HSIs, and optimize the network with lots of trainings. Although they have achieved satisfying spatial resolution, the spectral consistency before and after reconstruction is difficult to guarantee. In this article, we proposed a self-attention-based recurrent feedback network for hyperspectral SR reconstruction, utilizing pixel-aware weights and pseudo three-dimensional convolution to enhance the spatial and spectral consistency during the reconstruction process. In addition, group reconstruction is used to reduce the redundancy of information. Spectral consistency regularization is proposed to ensure the spectral consistency before and after reconstruction. The effectiveness of the proposed method is tested on one set of natural images and three hyperspectral remote sensing image datasets.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"17 ","pages":"18502-18516"},"PeriodicalIF":4.7,"publicationDate":"2024-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10711264","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142517960","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Foliage-Concealed Target Change Detection Scheme Based on Convolutional Neural Network in Low-Frequency Ultrawideband SAR Images","authors":"Hongtu Xie;Yuanjie Zhang;Jinfeng He;Shiliang Yi;Lin Zhang;Nannan Zhu","doi":"10.1109/JSTARS.2024.3477514","DOIUrl":"https://doi.org/10.1109/JSTARS.2024.3477514","url":null,"abstract":"The low-frequency ultrawideband synthetic aperture radar (UWB SAR) has the ability of the foliage-penetrating and high-resolution imaging, which can detect the foliage-concealed target. However, due to low-frequency UWB SAR characteristics and forest detection environments, there are usually some nontarget strong scattering points in the low-frequency UWB SAR images, which may increase the difficulty of the foliage-concealed target change detection. To solve the problem of the weak antijamming ability of the foliage-concealed target change detection, a foliage-concealed target change detection scheme based on the convolutional neural network in the low-frequency UWB SAR images is proposed, which combines the traditional image difference method and deep-learning method. First, a relatively low inspection threshold is set for the target change detection based on the image difference method, which can obtain a lot of the position information of the detection point. Moreover, for the target characteristics in the foliage-concealed scenarios, the corresponding data extraction and enhancement techniques are used to effectively extract the detection point samples from the detection image and reference image, which can prevent the overfitting of the model training caused by the sample scarcity. Finally, the samples of the detection points are input to the target classification network with the double input and single output for the classification training and testing. The experimental results tested on the CARABAS-II SAR dataset demonstrate the correctness and effectiveness of the proposed scheme, which has the better change detection performance and anti-interference capability.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"17 ","pages":"19302-19316"},"PeriodicalIF":4.7,"publicationDate":"2024-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10712645","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142550507","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Finding Optimal Spatial Window: The Influence of Size on Remote-Sensing-Based Chl-a Prediction in Small Reservoirs","authors":"Cáceres-Merino José;Cuartero Aurora;Torrecilla-Pinero Jesús A.","doi":"10.1109/JSTARS.2024.3476970","DOIUrl":"https://doi.org/10.1109/JSTARS.2024.3476970","url":null,"abstract":"This study investigates the optimal spatial window size for estimating chlorophyll-a (Chl-a) concentrations using Sentinel-2 imagery in small reservoirs of Extremadura, Spain. While remote-sensing techniques have proven valuable for water quality monitoring, the influence of pixel window size on estimation accuracy remains understudied, particularly for smaller water bodies. We analyzed 94 atmospherically corrected Sentinel-2 images using the C2RCC processor, corresponding to 32 reservoirs, and compared the results with in situ measurements collected between 2017 and 2022. Our methodology explored window sizes ranging from 1×1 pixels to 20×20 pixels, employing various statistical estimators. Performance was assessed using root-mean-square relative error, mean absolute percentage error, and Spearman's correlation coefficient (ρ). Results show that window sizes between 5×5 and 9×9 pixels yielded optimal Chl-a estimation accuracy. The Cmax estimator consistently outperformed other methods across different window sizes, particularly for mesotrophic and eutrophic waters. Notably, larger window sizes improved correlation with in situ data but showed diminishing returns beyond 9×9 pixels. This study contributes to refining remote-sensing methodologies for inland water quality monitoring, particularly for small- to medium-sized reservoirs. Our findings suggest that careful consideration of spatial window size and statistical estimators can enhance the accuracy of Chl-a concentration predictions, potentially improving water resource management in regions with diverse aquatic ecosystems.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"17 ","pages":"18769-18783"},"PeriodicalIF":4.7,"publicationDate":"2024-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10710322","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142517771","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"MFFCI–YOLOv8: A Lightweight Remote Sensing Object Detection Network Based on Multiscale Features Fusion and Context Information","authors":"Sheng Xu;Lin Song;Junru Yin;Qiqiang Chen;Tianming Zhan;Wei Huang","doi":"10.1109/JSTARS.2024.3474689","DOIUrl":"https://doi.org/10.1109/JSTARS.2024.3474689","url":null,"abstract":"Most current researches primarily focus on improving experimental accuracy using large models, often neglecting the deployment challenges. There is a growing need for lightweight algorithms in certain remote sensing devices. Moreover, remote sensing images (RSIs) often contain numerous small, densely distributed targets, which pose significant detection challenges. To address these issues, we have improved the YOLOv8s network and developed a lightweight remote sensing object detection (RSOD) network based on multiscale features fusion and context information (MFFCI–YOLOv8). This network combines multiscale feature fusion and contextual information to accurately detect objects in RSIs. First, we introduce the lightweight CSP bottleneck with attention module, which utilizes partial convolution calculation and SimAM attention mechanisms to decrease the number of parameters and computational complexity while enhancing feature extraction capabilities. Second, we design the gate spatial pyramid pooling fast module to enhance the model's perception of scale and contextual information, thus improving the detection of small objects. Last, we employ the multiscale fusion lightweight neck module for more efficient multiscale feature fusion, preventing the loss of small objects. Compared to YOLOv8s, our overall model reduces the number of parameters by 7.7% and FLOPs by 11.9%. We validated the accuracy of MFFCI–YOLOv8 on two remote sensing datasets, NWPU VHR-10 and VisDrone. The experimental results demonstrate that our model offers a low computational cost and high detection accuracy compared to other RSOD models and other YOLO models.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"17 ","pages":"19743-19755"},"PeriodicalIF":4.7,"publicationDate":"2024-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10713206","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142595812","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Mapping and Monitoring of Water Hyacinth in Lake Victoria Using Polarimetric Radar Data","authors":"Isundwa Kasiti Felix;Marino Armando;Morgan David Simpson;Akbari Vahid;Thiago S. F. Silva;Aviraj Datta;Prabhu G. Nagendra;Gogumalla Pranuthi;Rupavatharam Srikanth","doi":"10.1109/JSTARS.2024.3476938","DOIUrl":"https://doi.org/10.1109/JSTARS.2024.3476938","url":null,"abstract":"Water hyacinth, an invasive species originating from South America, has become a significant concern since its introduction in Lake Victoria (Kenya), particularly in the Winam Gulf, where large annual blooms are observed. Monitoring the occurrence and location using in situ methods is expensive and challenging due to the lake's vastness. Remote sensing monitoring methods offer an alternate option due to the ability to cover vast areas. This study explores the potential of polarimetric synthetic aperture radar (PolSAR), specifically utilising Sentinel-1 VV-VH data to map and monitor water hyacinth cover. The change detection method based on optimization of power difference and minimum eigenvalue selection achieves a remarkable accuracy of 98.89% in separating clear and water hyacinth-infested water. Using polarimetric data offered better separability, enabling spatial and temporal monitoring. The analysis reveals that in 2018 water hyacinth cover peaked, spanning over 200 km\u0000<inline-formula><tex-math>$^{2}$</tex-math></inline-formula>\u0000. Temporal variability showcases a seasonal rise and peak from September to December. This research demonstrates the capability of using PolSAR data to accurately map and monitor water hyacinth's spatial and temporal dynamics, offering valuable insights for effective management strategies.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"17 ","pages":"19900-19910"},"PeriodicalIF":4.7,"publicationDate":"2024-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10711204","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142645539","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"RSID-CR: Remote Sensing Image Denoising Based on Contrastive Learning","authors":"Zhibao Wang;Xiaoqing He;Bin Xiao;Liangfu Chen;Xiuli Bi","doi":"10.1109/JSTARS.2024.3476566","DOIUrl":"https://doi.org/10.1109/JSTARS.2024.3476566","url":null,"abstract":"In the field of remote sensing image denoising, the current mainstream methods usually only consider using clean or noisy images to guide the network in the training phase. Most of them only apply to specific types of noise, and the denoising effect is not satisfactory enough, with problems such as artifacts and noise residues. In this article, we endeavor to deal with a wide range of noise types, preserving as much detailed information in the image as possible and aiming to address the relevant limitations. Inspired by contrastive learning, we propose a remote sensing image denoising framework based on contrastive learning, named RSID-CR, which constructs positive and negative sample pairs between clean, noisy, and denoised images. Then, we construct a joint loss function consisting of reconstruction loss and contrastive regularization as a guide signal to train the denoising network, such that the denoised image is pushed closer to the clean image and farther away from the noisy image in the feature space. We conduct extensive experiments on two public datasets for five types of noise often present in remote sensing images. In addition, we validate our method using two real noisy remote sensing datasets. The experimental results indicate that our proposed method achieves satisfactory outcomes.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"17 ","pages":"18784-18799"},"PeriodicalIF":4.7,"publicationDate":"2024-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10711275","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142524155","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Expeditious Hyperspectral Image Classification With Inner and Outer Layered Transformer Using Feature Enhancement","authors":"Qianhui Sun;Xiaohua Zhang;Hongyun Meng;Shuxiang Xia;Licheng Jiao","doi":"10.1109/JSTARS.2024.3476333","DOIUrl":"https://doi.org/10.1109/JSTARS.2024.3476333","url":null,"abstract":"Hyperspectral image classification (HSI) is the process of segmenting an image into distinct land cover types by analyzing the rich spectral information of each pixel, with the key lying in feature extraction. Benefiting from the superior ability to exploit long-range dependencies, transformer-based methods have garnered significant attention in the field. However, the limited local sensitivity, high computation burden, influence from heterogeneous spectrum random, and initialization of class token without prior knowledge may restrict the performance of transformer-based methods. To effectively address the aforementioned issues, this study introduces the Dual-Layer Spectral-Spatial Transformer architecture, adept at comprehensively extracting and modeling features. First, to address the issue of limited local sensitivity, we propose a dual-layer transformer architecture, where the inner Pixel-Transformer ensures adequate extraction of local features, and the outer Patch-Transformer is engineered to capture joint spectral-spatial features, thereby strengthening global context modeling. This dual-layer cascading approach not only provides balanced enhancement in feature extraction and modeling, but also alleviates the computational burden associated with self-attention operations. Meanwhile, we have also incorporated a feature selector to mitigate the influence of the heterogeneous spectrum. In addition, the inner Pixel-Transformer enhances feature representation by integrating the spectral vector of the target pixel as a class token, thereby solving the issue of random initialization of the class token without prior knowledge. Experimental results on four public HSI benchmark datasets demonstrate that our model outperforms state-of-the-art methods, with an improvement ranging from 0.86% to a maximum of 3.9%, and has achieved excellent classification results at the boundaries between different land cover types.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"17 ","pages":"19361-19379"},"PeriodicalIF":4.7,"publicationDate":"2024-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10707201","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142579178","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Mitigation of Land Contamination in SMOS L1C Brightness Temperature Data Based on Convolutional Neural Networks","authors":"Ke Chen;Qian Yang;Yuanyuan Tian;Qingxia Li;Rong Jin","doi":"10.1109/JSTARS.2024.3476470","DOIUrl":"https://doi.org/10.1109/JSTARS.2024.3476470","url":null,"abstract":"Due to the Gibbs oscillation effect of microwave aperture synthesis radiometers (ASRs) occurring near land/ocean transitions, soil moisture and ocean salinity (SMOS) brightness temperature (TB) measurements are subject to land contamination in ocean regions (within a few hundred kilometers of the shore). In this article, the magnitude of land contamination in the SMOS L1C TB is demonstrated by comparison with the results of collocated forward modeling. Then, a land contamination correction algorithm for microwave SARs based on a convolutional neural network is presented. The basic process of the algorithm is to design a land contamination mitigation network (LCMN) to learn the land contamination features from the simulated TB dataset of the microwave ASRs and then to use the well-trained network to remap the actual observed TB images to mitigate the land contamination error. Land contamination error correction experiments based on LCMN remapping were executed on SMOS L1C TB data, and the performance of the algorithm was verified by comparison with forward modeling and salinity retrieval. The experimental results show that the proposed LCMN algorithm can effectively mitigate land contamination at the SMOS L1C TB.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"17 ","pages":"18666-18682"},"PeriodicalIF":4.7,"publicationDate":"2024-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10709663","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142517957","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"L2-Norm Quasi 3-D Phase Unwrapping Assisted Multitemporal InSAR Deformation Dynamic Monitoring for the Cross-Sea Bridge","authors":"Baohang Wang;Wenhong Li;Chaoying Zhao;Qin Zhang;Guangrong Li;Xiaojie Liu;Bojie Yan;Xiaohe Cai;Jianxia Zhang;Shouzhu Zheng","doi":"10.1109/JSTARS.2024.3476172","DOIUrl":"https://doi.org/10.1109/JSTARS.2024.3476172","url":null,"abstract":"Interferometric fringes containing noise with complex distributions significantly contribute to phase unwrapping (PhU) failures in synthetic aperture radar interferometry (InSAR) technology. The study proposes an \u0000<italic>L</i>\u0000²\u0000-Norm Quasi 3-D PhU-assisted multitemporal InSAR strategy. Initially, the \u0000<italic>L</i>\u0000²\u0000-norm quasi 3-D PhU (first spatial 2-D and then temporal 1-D PhU) is employed to reduce the phase gradient of interferograms with optimized networks. The advantage of this methodology is that the wrapped residual phase satisfies the phase triangle, thereby making it suitable for existing widely-used 2-D or 3-D PhU techniques. Subsequently, a popular PhU method is applied to the residual phase, which is smooth and continuous, thereby improving the accuracy of subsequent spatial PhU. The deformation rate, time series and number of PhU triplet closures demonstrate the reliability of the proposed method for the Pingtan Straits Rail-cum-Road Bridge and the Hong Kong–Zhuhai–Macao Bridge in China using the sentinel-1A SAR dataset. The deformation results demonstrate that the bridge deformation is temperature-dependent, with the location of deformation being contingent upon the structural configuration of the bridge.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"17 ","pages":"18926-18938"},"PeriodicalIF":4.7,"publicationDate":"2024-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10707274","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142524185","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Logarithmic Kernel Relaxed Collaborative Representation With Scaled MST Dictionary Construction for Hyperspectral Anomaly Detection","authors":"Yang Zhao;Hongjun Su;Zhaoyue Wu;Zhaohui Xue;Qian Du","doi":"10.1109/JSTARS.2024.3476319","DOIUrl":"https://doi.org/10.1109/JSTARS.2024.3476319","url":null,"abstract":"Representation-based anomaly detection methods are one of the most popular methods in hyperspectral anomaly detection. Nevertheless, linear models of have difficulties in adequately describing complex data and generating a decision boundary for anomaly-background separation. To relax such a limitation, a novel kernel relaxed collaboration representation anomaly detection method is proposed. A new logarithmic kernel function is used to map the raw data into a high-dimensional feature space where anomalies and background are more separable. Meanwhile, the scaled minimum spanning tree method is adopted to cluster the data and select representative pixels to construct a pure dictionary. Then, the distance from a testing pixel to each dictionary atom is calculated using the KNN method, and atoms with the closest distance are selected to construct a nonglobal dictionary for the testing pixel. The proposed method becomes more robust due to the contamination of anomalies from the dictionary is removed. The experiments on four real datasets demonstrate that the proposed method has significant advantages over currently existing methods.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"17 ","pages":"18652-18665"},"PeriodicalIF":4.7,"publicationDate":"2024-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10707290","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142517914","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}