Pub Date : 2024-10-17DOI: 10.1109/JSTARS.2024.3483279
Yukio Kurihara;Misako Kachi
We developed a cross-calibration method to improve sea surface temperature (SST) retrieval from remotely sensed thermal infrared data from space. The cross-calibration method is based on a physical SST method that determines SST by solving the infrared radiative transfer equation. We calibrated the thermal infrared data from Himawari-9, a Japanese geostationary meteorological satellite, using the developed method and the reference observation obtained with the Second-generation Global Imager (SGLI) onboard the Global Change Observation Mission-Climate (GCOM-C) satellite. As a result, the bias and the standard deviation of Himawari-9 SST were improved from $-$ 0.63 to $-$ 0.028 K and from 1.2 to 0.73 K, respectively, compared to the buoy data. Consistency between the Himawari-9 SST and SGLI SST was also improved after this calibration. Meanwhile, negative bias remained in the Himawari-9 SST, which was determined using 3.9 $mu$ m data if the observation zenith angle was larger than 50°. This article discusses the cross-calibration method and the validation results of SST retrieved from the calibrated Himawari-9 data.
{"title":"Cross-Calibration of the Himawari-9 Thermal Infrared Data by Applying a Physical Sea Surface Temperature Method","authors":"Yukio Kurihara;Misako Kachi","doi":"10.1109/JSTARS.2024.3483279","DOIUrl":"https://doi.org/10.1109/JSTARS.2024.3483279","url":null,"abstract":"We developed a cross-calibration method to improve sea surface temperature (SST) retrieval from remotely sensed thermal infrared data from space. The cross-calibration method is based on a physical SST method that determines SST by solving the infrared radiative transfer equation. We calibrated the thermal infrared data from Himawari-9, a Japanese geostationary meteorological satellite, using the developed method and the reference observation obtained with the Second-generation Global Imager (SGLI) onboard the Global Change Observation Mission-Climate (GCOM-C) satellite. As a result, the bias and the standard deviation of Himawari-9 SST were improved from \u0000<inline-formula><tex-math>$-$</tex-math></inline-formula>\u00000.63 to \u0000<inline-formula><tex-math>$-$</tex-math></inline-formula>\u00000.028 K and from 1.2 to 0.73 K, respectively, compared to the buoy data. Consistency between the Himawari-9 SST and SGLI SST was also improved after this calibration. Meanwhile, negative bias remained in the Himawari-9 SST, which was determined using 3.9 \u0000<inline-formula><tex-math>$mu$</tex-math></inline-formula>\u0000m data if the observation zenith angle was larger than 50°. This article discusses the cross-calibration method and the validation results of SST retrieved from the calibrated Himawari-9 data.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"17 ","pages":"19730-19742"},"PeriodicalIF":4.7,"publicationDate":"2024-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10721364","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142595811","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 : 2024-10-17DOI: 10.1109/JSTARS.2024.3482577
Ilaria Petracca;Daniele Latini;Marco Di Giacomo;Fabrizio Niro;Stefania Bonafoni;Fabio Del Frate
In this work, we address the bidirectional reflectance distribution function (BRDF) characterization of homogeneous surfaces by means of multiangular datasets acquired with an unmanned aerial system (UAS) carrying a multispectral sensor (MAIA) replicating the spectral characteristics of the multispectral instrument onboard Copernicus Sentinel-2 satellite. The UAS field campaign was performed in clear-sky conditions over two different test sites, a vegetation cover and an asphalted area, exhibiting different behaviors in terms of surface reflectance anisotropy. A dual angular approach for the processing of the reflectance measurements is examined: a conical configuration considering a cone angle of 10° (hemispherical conical-reflectance distribution) and a directional configuration (hemispherical directional-reflectance distribution) considering a cone angle of 3°. Afterward, the retrieval of the parameters of the Ross–Li–Maignan BRDF model was implemented by a least-squared fitting of the UAS reflectance measurements for each MAIA band. The accuracy of the modeled reflectances was evaluated and the overall relative root-mean-square error between the measured and modeled reflectances was less than 10% for both test sites. The outcomes of the present study go toward the definition of a standard approach for UAS-based measurements with high angular resolution features for BRDF modeling, avoiding the well-known issues related to the use of ground-based and satellite-based instruments, and proving the UAS effectiveness in supporting calibration and validation activities of satellite missions.
{"title":"Toward a Standard Approach for UAS-Based Multiangular Dataset Collection for BRDF Analysis","authors":"Ilaria Petracca;Daniele Latini;Marco Di Giacomo;Fabrizio Niro;Stefania Bonafoni;Fabio Del Frate","doi":"10.1109/JSTARS.2024.3482577","DOIUrl":"https://doi.org/10.1109/JSTARS.2024.3482577","url":null,"abstract":"In this work, we address the bidirectional reflectance distribution function (BRDF) characterization of homogeneous surfaces by means of multiangular datasets acquired with an unmanned aerial system (UAS) carrying a multispectral sensor (MAIA) replicating the spectral characteristics of the multispectral instrument onboard Copernicus Sentinel-2 satellite. The UAS field campaign was performed in clear-sky conditions over two different test sites, a vegetation cover and an asphalted area, exhibiting different behaviors in terms of surface reflectance anisotropy. A dual angular approach for the processing of the reflectance measurements is examined: a conical configuration considering a cone angle of 10° (hemispherical conical-reflectance distribution) and a directional configuration (hemispherical directional-reflectance distribution) considering a cone angle of 3°. Afterward, the retrieval of the parameters of the Ross–Li–Maignan BRDF model was implemented by a least-squared fitting of the UAS reflectance measurements for each MAIA band. The accuracy of the modeled reflectances was evaluated and the overall relative root-mean-square error between the measured and modeled reflectances was less than 10% for both test sites. The outcomes of the present study go toward the definition of a standard approach for UAS-based measurements with high angular resolution features for BRDF modeling, avoiding the well-known issues related to the use of ground-based and satellite-based instruments, and proving the UAS effectiveness in supporting calibration and validation activities of satellite missions.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"17 ","pages":"19487-19502"},"PeriodicalIF":4.7,"publicationDate":"2024-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10720872","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142594968","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 : 2024-10-17DOI: 10.1109/JSTARS.2024.3482553
Xiaoxing Hu;Yupei Wang;Liang Chen
Semantic segmentation models experience a significant performance degradation due to domain shifts between the source and target domains. This issue is particularly prevalent in remote sensing imagery, where a semantic segmentation model trained on images from one satellite is tested on images from another. Previous research has often overlooked the role of data augmentation in enhancing a model's adaptability to target domains. In contrast, this article proposes a novel self-training framework that incorporates data augmentation at both the input and feature levels, yielding excellent results. Specifically, we introduce a regularized online self-training framework that effectively addresses the challenges of overconfidence and class imbalance inherent in self-training. Based on this framework, we implement two robust data augmentation strategies at the input and feature levels to facilitate the learning of cross-domain invariant knowledge. At the input level, we employ a large-scale domain mixing strategy, termed multidomain mixing, to enhance the model's generalization capability. At the feature level, we introduce masked feature augmentation, a masking-based perturbation technique applied to the semantic features of the target domain. This approach enhances the consistency of teacher–student network predictions in the target domain feature space, thereby improving the robustness of the model's recognition of target domain features. The integration of the proposed self-training framework with dual-level data augmentation culminates in our innovative self-training-based dual-level data augmentation (STDA) method. Extensive experimental results on the ISPRS semantic segmentation benchmark demonstrate that STDA outperforms existing state-of-the-art methods, showcasing its effectiveness.
{"title":"Domain Adaptive Semantic Segmentation of Remote Sensing Images via Self-Training-Based Dual-Level Data Augmentation","authors":"Xiaoxing Hu;Yupei Wang;Liang Chen","doi":"10.1109/JSTARS.2024.3482553","DOIUrl":"https://doi.org/10.1109/JSTARS.2024.3482553","url":null,"abstract":"Semantic segmentation models experience a significant performance degradation due to domain shifts between the source and target domains. This issue is particularly prevalent in remote sensing imagery, where a semantic segmentation model trained on images from one satellite is tested on images from another. Previous research has often overlooked the role of data augmentation in enhancing a model's adaptability to target domains. In contrast, this article proposes a novel self-training framework that incorporates data augmentation at both the input and feature levels, yielding excellent results. Specifically, we introduce a regularized online self-training framework that effectively addresses the challenges of overconfidence and class imbalance inherent in self-training. Based on this framework, we implement two robust data augmentation strategies at the input and feature levels to facilitate the learning of cross-domain invariant knowledge. At the input level, we employ a large-scale domain mixing strategy, termed multidomain mixing, to enhance the model's generalization capability. At the feature level, we introduce masked feature augmentation, a masking-based perturbation technique applied to the semantic features of the target domain. This approach enhances the consistency of teacher–student network predictions in the target domain feature space, thereby improving the robustness of the model's recognition of target domain features. The integration of the proposed self-training framework with dual-level data augmentation culminates in our innovative self-training-based dual-level data augmentation (STDA) method. Extensive experimental results on the ISPRS semantic segmentation benchmark demonstrate that STDA outperforms existing state-of-the-art methods, showcasing its effectiveness.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"17 ","pages":"19713-19729"},"PeriodicalIF":4.7,"publicationDate":"2024-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10720895","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142595809","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 : 2024-10-16DOI: 10.1109/JSTARS.2024.3481368
Wei Liu;Lifan Zhou;Shan Zhong;Shengrong Gong
The unique challenge in SAR object detection is the strong speckle noise inherent in SAR imagery. Existing learning-based works mainly focus on architectural enhancements, and fail to consider the valuable semantic information that can mitigate the effects of speckle noise. Large pretrained segment anything model (SAM) is a powerful foundational model with general semantic knowledge. However, SAM is not fully exploited for SAR object detection. This study paves the way for applying SAM for SAR object detection. Rather than fine-tuning the SAM network, we propose three mask-guided learning strategies by simply utilizing the semantic masks generated by SAM. Built upon the advanced RealTime DEtection TRansformer (RT-DETR) framework, the Semantic Assisted DETR, deemed as SA-DETR, integrates prior semantics from SAM into the SAR detection task. To be specific, first, we propose the mask-guided feature denoising module in the encoder stage, to enhance the network's discrimination of positives and negatives. Second, we propose the mask-guided query selection for initial query generation, which is beneficial for the decoder refinement. Finally, the mask-guided instance segmentation is proposed to achieve more accurate localization. To validate the superiority of the proposed SA-DETR, extensive experiments are conducted on two benchmark datasets, i.e., the SAR ship detection dataset (SSDD) and the recently published COCO-level large-scale multiclass SAR object detection dataset (SARDet-100K). Experimental results on both datasets outperform previous advanced detectors, achieving a new state-of-the-art with 99.0 $AP_{50}$ and 88.4 $mAP_{50}$ on SSDD and SARDet-100 K, respectively.
SAR 物体检测的独特挑战在于 SAR 图像固有的强斑点噪声。现有的基于学习的工作主要集中在结构上的增强，而没有考虑到有价值的语义信息可以减轻斑点噪声的影响。大型预训练分段模型（SAM）是一种具有一般语义知识的强大基础模型。然而，SAM 在合成孔径雷达目标检测中并未得到充分利用。本研究为将 SAM 应用于 SAR 物体检测铺平了道路。我们没有对 SAM 网络进行微调，而是通过简单利用 SAM 生成的语义掩码，提出了三种掩码引导学习策略。语义辅助 DETR（Semantic Assisted DETR，简称 SA-DETR）以先进的实时检测转换器（RealTime DEtection TRansformer，RT-DETR）框架为基础，将 SAM 的先验语义整合到合成孔径雷达检测任务中。具体来说，首先，我们在编码器阶段提出了掩码引导特征去噪模块，以增强网络对正负信号的辨别能力。其次，我们提出了用于初始查询生成的掩码引导查询选择，这有利于解码器的完善。最后，我们提出了掩码引导的实例分割，以实现更精确的定位。为了验证所提出的 SA-DETR 的优越性，我们在两个基准数据集上进行了大量实验，即 SAR 船舶检测数据集（SSDD）和最近发布的 COCO 级大规模多类 SAR 物体检测数据集（SARDet-100K）。在这两个数据集上的实验结果都优于以前的高级探测器，在 SSDD 和 SARDet-100 K 上分别达到了 99.0 $AP_{50}$ 和 88.4 $mAP_{50}$，达到了新的先进水平。
{"title":"Semantic Assistance in SAR Object Detection: A Mask-Guided Approach","authors":"Wei Liu;Lifan Zhou;Shan Zhong;Shengrong Gong","doi":"10.1109/JSTARS.2024.3481368","DOIUrl":"https://doi.org/10.1109/JSTARS.2024.3481368","url":null,"abstract":"The unique challenge in SAR object detection is the strong speckle noise inherent in SAR imagery. Existing learning-based works mainly focus on architectural enhancements, and fail to consider the valuable semantic information that can mitigate the effects of speckle noise. Large pretrained segment anything model (SAM) is a powerful foundational model with general semantic knowledge. However, SAM is not fully exploited for SAR object detection. This study paves the way for applying SAM for SAR object detection. Rather than fine-tuning the SAM network, we propose three mask-guided learning strategies by simply utilizing the semantic masks generated by SAM. Built upon the advanced RealTime DEtection TRansformer (RT-DETR) framework, the Semantic Assisted DETR, deemed as SA-DETR, integrates prior semantics from SAM into the SAR detection task. To be specific, first, we propose the mask-guided feature denoising module in the encoder stage, to enhance the network's discrimination of positives and negatives. Second, we propose the mask-guided query selection for initial query generation, which is beneficial for the decoder refinement. Finally, the mask-guided instance segmentation is proposed to achieve more accurate localization. To validate the superiority of the proposed SA-DETR, extensive experiments are conducted on two benchmark datasets, i.e., the SAR ship detection dataset (SSDD) and the recently published COCO-level large-scale multiclass SAR object detection dataset (SARDet-100K). Experimental results on both datasets outperform previous advanced detectors, achieving a new state-of-the-art with 99.0 \u0000<inline-formula><tex-math>$AP_{50}$</tex-math></inline-formula>\u0000 and 88.4 \u0000<inline-formula><tex-math>$mAP_{50}$</tex-math></inline-formula>\u0000 on SSDD and SARDet-100 K, respectively.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"17 ","pages":"19395-19407"},"PeriodicalIF":4.7,"publicationDate":"2024-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10720452","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142579244","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 : 2024-10-16DOI: 10.1109/JSTARS.2024.3481460
Thitimar Chongtaku;Attaphongse Taparugssanagorn;Hiroyuki Miyazaki;Takuji W. Tsusaka
Facing the escalating global challenge of frequent and severe heatwaves, this study meticulously assesses heatwave dynamics across urban and nonurban areas in central Thailand. It introduces a novel workflow integrating ground-based observations with satellite-derived land surface temperature data over 39 years (1981–2019). Our findings reveal a significant increase in daytime heatwaves in urban and peri-urban areas, with notable rises in the number, frequency, duration, and amplitude of heatwaves. Conversely, nighttime heatwaves intensify mainly in rural areas. Land surface temperature data show distinct patterns: peri-urban regions experience significant daytime increases in heatwave magnitude, amplitude, and frequency, contrasting with varied trends in urban and rural settings. The annual pattern of heatwave characteristics across specific regions reveals that daytime occurrences are more frequent and intense in peri-urban zones such as Pathum Thani and eastern Bangkok, with annual episodes ranging from 2 to 9 and durations of 10 to 39 days. In contrast, urban areas such as downtown Bangkok are more prone to nighttime heatwaves, with a wider occurrence range of 3 to 12 events and longer durations, lasting from 13 to 62 days annually. Overall, this research advances traditional methods by offering a nuanced view of heatwave dynamics and highlighting the potential of remote sensing to identify risk areas. The study demonstrates how this precise technique can identify extreme weather events and support sustainable climate practices, government policy, and decision-making, all of which are crucial for enhancing resilience and addressing the growing threat of heat-related health risks.
{"title":"Enhanced Spatiotemporal Heatwave Analysis in Urban and Nonurban Thai Environments Through Integration of In-Situ and Remote Sensing Data","authors":"Thitimar Chongtaku;Attaphongse Taparugssanagorn;Hiroyuki Miyazaki;Takuji W. Tsusaka","doi":"10.1109/JSTARS.2024.3481460","DOIUrl":"https://doi.org/10.1109/JSTARS.2024.3481460","url":null,"abstract":"Facing the escalating global challenge of frequent and severe heatwaves, this study meticulously assesses heatwave dynamics across urban and nonurban areas in central Thailand. It introduces a novel workflow integrating ground-based observations with satellite-derived land surface temperature data over 39 years (1981–2019). Our findings reveal a significant increase in daytime heatwaves in urban and peri-urban areas, with notable rises in the number, frequency, duration, and amplitude of heatwaves. Conversely, nighttime heatwaves intensify mainly in rural areas. Land surface temperature data show distinct patterns: peri-urban regions experience significant daytime increases in heatwave magnitude, amplitude, and frequency, contrasting with varied trends in urban and rural settings. The annual pattern of heatwave characteristics across specific regions reveals that daytime occurrences are more frequent and intense in peri-urban zones such as Pathum Thani and eastern Bangkok, with annual episodes ranging from 2 to 9 and durations of 10 to 39 days. In contrast, urban areas such as downtown Bangkok are more prone to nighttime heatwaves, with a wider occurrence range of 3 to 12 events and longer durations, lasting from 13 to 62 days annually. Overall, this research advances traditional methods by offering a nuanced view of heatwave dynamics and highlighting the potential of remote sensing to identify risk areas. The study demonstrates how this precise technique can identify extreme weather events and support sustainable climate practices, government policy, and decision-making, all of which are crucial for enhancing resilience and addressing the growing threat of heat-related health risks.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"17 ","pages":"19174-19193"},"PeriodicalIF":4.7,"publicationDate":"2024-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10720433","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142555113","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 : 2024-10-16DOI: 10.1109/JSTARS.2024.3482348
Yang Chu;Minchao Ye;Yuntao Qian
Fine-grained image recognition (FGIR), unlike traditional coarse-grained recognition, is centered on distinguishing fine-level subclasses within broader semantic categories. It holds significant scientific research value, particularly in remote sensing, where the precise identification of specific objects—such as ships, buildings, and land use categories—is critical for tasks like boundary security, environmental monitoring, and urban planning. Recent advancements in FGIR have notably improved feature representation and generalization, especially under the diverse imaging conditions typical of remote sensing. However, challenges remain, including the heavy reliance on high-quality large-scale fine-grained image data and difficulties in extracting subtle image features. Efficiently utilizing limited data and enhancing feature extraction capabilities have thus become key focus areas in current FGIR research. This article systematically reviews the advancements in FGIR, covering its foundational principles, key methodologies, and the latest research developments, while providing a comprehensive comparative analysis of their performance in remote sensing image applications. In addition, it addresses the specific challenges posed by fine-grained recognition in remote sensing imagery and explores potential directions for future research in this field.
{"title":"Fine-Grained Image Recognition Methods and Their Applications in Remote Sensing Images: A Review","authors":"Yang Chu;Minchao Ye;Yuntao Qian","doi":"10.1109/JSTARS.2024.3482348","DOIUrl":"https://doi.org/10.1109/JSTARS.2024.3482348","url":null,"abstract":"Fine-grained image recognition (FGIR), unlike traditional coarse-grained recognition, is centered on distinguishing fine-level subclasses within broader semantic categories. It holds significant scientific research value, particularly in remote sensing, where the precise identification of specific objects—such as ships, buildings, and land use categories—is critical for tasks like boundary security, environmental monitoring, and urban planning. Recent advancements in FGIR have notably improved feature representation and generalization, especially under the diverse imaging conditions typical of remote sensing. However, challenges remain, including the heavy reliance on high-quality large-scale fine-grained image data and difficulties in extracting subtle image features. Efficiently utilizing limited data and enhancing feature extraction capabilities have thus become key focus areas in current FGIR research. This article systematically reviews the advancements in FGIR, covering its foundational principles, key methodologies, and the latest research developments, while providing a comprehensive comparative analysis of their performance in remote sensing image applications. In addition, it addresses the specific challenges posed by fine-grained recognition in remote sensing imagery and explores potential directions for future research in this field.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"17 ","pages":"19640-19667"},"PeriodicalIF":4.7,"publicationDate":"2024-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10720642","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142595788","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 : 2024-10-16DOI: 10.1109/JSTARS.2024.3481874
Peiling Li;Zhiwei Li;Wenxiang Mao;Qiang Shi;Qiwei Lin
With the help of interferometric synthetic aperture radar (InSAR) and global navigation satellite system (GNSS) technology, high spatial and temporal resolution surface deformation results can be generated, which can help to better understand the mechanism of surface deformation. The spatio-temporal Kalman-based InSAR and GNSS fusion method fully considers the spatio-temporal correlation of deformation and characterizes the potential spatio-temporal process of deformation through spatial modeling and Kalman filter or smooth. However, when focusing on deformation with typical subsidence spatial characteristics, existing studies did not fully consider the spatial distribution of deformations, resulting in the loss of spatial detail information. This article proposes an adaptive spatial modeling optimization method that takes into account the spatial distribution of deformation, which can capture the optimal spatial basis layout scheme under a limited number of spatial bases, establish a more accurate spatial model, and improve the accuracy of deformation fusion. The effectiveness and reliability of this method are verified through simulation experiments and the deformation monitoring results in Datong City, China. The results of the two experiments show that the proposed method can improve the accuracy of InSAR interpolation results by 27.7% and 11.5% on average, respectively.
{"title":"Fusion of InSAR and GNSS Based on Adaptive Spatio-Temporal Kalman Model for Reconstructing High Spatio-Temporal Resolution Deformation","authors":"Peiling Li;Zhiwei Li;Wenxiang Mao;Qiang Shi;Qiwei Lin","doi":"10.1109/JSTARS.2024.3481874","DOIUrl":"https://doi.org/10.1109/JSTARS.2024.3481874","url":null,"abstract":"With the help of interferometric synthetic aperture radar (InSAR) and global navigation satellite system (GNSS) technology, high spatial and temporal resolution surface deformation results can be generated, which can help to better understand the mechanism of surface deformation. The spatio-temporal Kalman-based InSAR and GNSS fusion method fully considers the spatio-temporal correlation of deformation and characterizes the potential spatio-temporal process of deformation through spatial modeling and Kalman filter or smooth. However, when focusing on deformation with typical subsidence spatial characteristics, existing studies did not fully consider the spatial distribution of deformations, resulting in the loss of spatial detail information. This article proposes an adaptive spatial modeling optimization method that takes into account the spatial distribution of deformation, which can capture the optimal spatial basis layout scheme under a limited number of spatial bases, establish a more accurate spatial model, and improve the accuracy of deformation fusion. The effectiveness and reliability of this method are verified through simulation experiments and the deformation monitoring results in Datong City, China. The results of the two experiments show that the proposed method can improve the accuracy of InSAR interpolation results by 27.7% and 11.5% on average, respectively.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"17 ","pages":"19616-19626"},"PeriodicalIF":4.7,"publicationDate":"2024-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10720337","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142595776","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}
Earth observation utilizes multisource satellite data to enhance photogrammetry mapping. This study introduces a novel method to improve the geometric positioning accuracy of large-scale optical satellite imagery by combined adjustment with NASA's Ice, Cloud, and Land Elevation Satellite-2 (ICESat-2) laser altimetry data. Although ICESat-2 is known for its high vertical accuracy, its potential to improve horizontal accuracy has been limited due to the difficulty in matching caused by temporal inconsistencies across large survey areas. To address this, our method employs a robust terrain profile elevation sequence similarity matching technique, refined with two-dimensional Gaussian fitting to achieve enhanced position extraction. We also propose a weighted adjustment strategy that uses matching confidence to enhance the precision of the combined adjustments. Large-scale tests across various terrains showed that our approach has significantly reduced horizontal and vertical positioning errors to 4.3 and 1.7 m, respectively, outperforming existing methods.
{"title":"Large-Scale Combined Adjustment of Optical Satellite Imagery and ICESat-2 Data Through Terrain Profile Elevation Sequence Similarity Matching","authors":"Shaodong Wei;Yonghua Jiang;Bin Du;MeiLin Tan;Miaozhong Xu;Weiqi Lian;Guo Zhang","doi":"10.1109/JSTARS.2024.3481449","DOIUrl":"https://doi.org/10.1109/JSTARS.2024.3481449","url":null,"abstract":"Earth observation utilizes multisource satellite data to enhance photogrammetry mapping. This study introduces a novel method to improve the geometric positioning accuracy of large-scale optical satellite imagery by combined adjustment with NASA's Ice, Cloud, and Land Elevation Satellite-2 (ICESat-2) laser altimetry data. Although ICESat-2 is known for its high vertical accuracy, its potential to improve horizontal accuracy has been limited due to the difficulty in matching caused by temporal inconsistencies across large survey areas. To address this, our method employs a robust terrain profile elevation sequence similarity matching technique, refined with two-dimensional Gaussian fitting to achieve enhanced position extraction. We also propose a weighted adjustment strategy that uses matching confidence to enhance the precision of the combined adjustments. Large-scale tests across various terrains showed that our approach has significantly reduced horizontal and vertical positioning errors to 4.3 and 1.7 m, respectively, outperforming existing methods.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"17 ","pages":"19771-19785"},"PeriodicalIF":4.7,"publicationDate":"2024-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10720096","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142595893","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 : 2024-10-15DOI: 10.1109/JSTARS.2024.3481246
Shiliang Shao;Guangjie Han;Hairui Jia;Xianyu Shi;Ting Wang;Chunhe Song;Chenghao Hu
Geospatial data is essential for urban planning and environmental sustainability. Utilizing multiple robots, each equipped with 3-D LiDAR for remote sensing, to collaboratively construct environmental maps can significantly enhance the efficiency of geospatial data collection. However, efficiently identifying overlapping areas between robots and accurately merging the maps constructed by different robots remains a pressing challenge. This study proposes a multirobot collaborative simultaneous localization and mapping (SLAM) method based on a novel environmental feature descriptor to address this problem. In this method, a distributed multirobot collaborative SLAM system is first constructed. Then, an SLAM algorithm that integrates intensity features and ground constraint is proposed for the robots in the multirobot SLAM system. Additionally, a multilayer hybrid context descriptor is introduced to detect overlapping areas between different robots. To validate the effectiveness and advantages of our method, we conducted benchmark comparisons with other approaches. Our multirobot collaborative SLAM method demonstrated favorable experimental results.
地理空间数据对于城市规划和环境可持续性至关重要。利用多个机器人（每个机器人都配备了用于遥感的三维激光雷达）合作绘制环境地图，可以大大提高地理空间数据收集的效率。然而，如何有效识别机器人之间的重叠区域，并准确合并不同机器人绘制的地图，仍然是一个亟待解决的难题。本研究提出了一种基于新型环境特征描述符的多机器人协同同步定位和绘图（SLAM）方法来解决这一问题。在该方法中，首先构建了一个分布式多机器人协作 SLAM 系统。然后，为多机器人 SLAM 系统中的机器人提出了一种集成了强度特征和地面约束的 SLAM 算法。此外，还引入了多层混合上下文描述符来检测不同机器人之间的重叠区域。为了验证我们方法的有效性和优势，我们与其他方法进行了基准比较。我们的多机器人协作 SLAM 方法取得了良好的实验结果。
{"title":"Multirobot Collaborative SLAM Based on Novel Descriptor With LiDAR Remote Sensing","authors":"Shiliang Shao;Guangjie Han;Hairui Jia;Xianyu Shi;Ting Wang;Chunhe Song;Chenghao Hu","doi":"10.1109/JSTARS.2024.3481246","DOIUrl":"https://doi.org/10.1109/JSTARS.2024.3481246","url":null,"abstract":"Geospatial data is essential for urban planning and environmental sustainability. Utilizing multiple robots, each equipped with 3-D LiDAR for remote sensing, to collaboratively construct environmental maps can significantly enhance the efficiency of geospatial data collection. However, efficiently identifying overlapping areas between robots and accurately merging the maps constructed by different robots remains a pressing challenge. This study proposes a multirobot collaborative simultaneous localization and mapping (SLAM) method based on a novel environmental feature descriptor to address this problem. In this method, a distributed multirobot collaborative SLAM system is first constructed. Then, an SLAM algorithm that integrates intensity features and ground constraint is proposed for the robots in the multirobot SLAM system. Additionally, a multilayer hybrid context descriptor is introduced to detect overlapping areas between different robots. To validate the effectiveness and advantages of our method, we conducted benchmark comparisons with other approaches. Our multirobot collaborative SLAM method demonstrated favorable experimental results.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"17 ","pages":"19317-19327"},"PeriodicalIF":4.7,"publicationDate":"2024-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10716780","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142579141","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 : 2024-10-15DOI: 10.1109/JSTARS.2024.3480520
Cesar Aybar;Gonzalo Mateo-García;Giacomo Acciarini;Vít Růžička;Gabriele Meoni;Nicolas Longépé;Luis Gómez-Chova
Nano and microsatellites have expanded the acquisition of satellite images with higher spatial, temporal, and spectral resolutions. Nevertheless, downlinking all this data to the ground for processing becomes challenging as the amount of remote sensing data rises. Custom onboard algorithms are designed to make real-time decisions and to prioritize and reduce the amount of data transmitted to the ground. However, these onboard algorithms frequently require cloud-free bottom-of-atmosphere surface reflectance (SR) estimations as inputs to operate. In this context, this article presents the data transformations and autocalibration for Sentinel-2 (S-2) network (DTACSNet), an onboard cloud detection and atmospheric correction processor based on lightweight convolutional neural networks. DTACSNet provides cloud and cloud shadow masks and SR estimates 10× faster than the operational S-2 L2A processor in dedicated space-tested hardware: 7 mins versus 1 h for a 10 980 × 10 980 scene. The DTACSNet cloud masking, based on a lightweight neural network, obtains the highest F2-score (0.81), followed by the state-of-the-art KappaMask (0.74), Fmask (0.72), and Sen2Cor v.2.8 (0.51) algorithms. In addition, validation results on independent datasets show that DTACSNet can efficiently replicate Sen2Cor SR estimates, reporting a competitive accuracy with differences below 2%.
{"title":"Onboard Cloud Detection and Atmospheric Correction With Efficient Deep Learning Models","authors":"Cesar Aybar;Gonzalo Mateo-García;Giacomo Acciarini;Vít Růžička;Gabriele Meoni;Nicolas Longépé;Luis Gómez-Chova","doi":"10.1109/JSTARS.2024.3480520","DOIUrl":"https://doi.org/10.1109/JSTARS.2024.3480520","url":null,"abstract":"Nano and microsatellites have expanded the acquisition of satellite images with higher spatial, temporal, and spectral resolutions. Nevertheless, downlinking all this data to the ground for processing becomes challenging as the amount of remote sensing data rises. Custom onboard algorithms are designed to make real-time decisions and to prioritize and reduce the amount of data transmitted to the ground. However, these onboard algorithms frequently require cloud-free bottom-of-atmosphere surface reflectance (SR) estimations as inputs to operate. In this context, this article presents the data transformations and autocalibration for Sentinel-2 (S-2) network (DTACSNet), an onboard cloud detection and atmospheric correction processor based on lightweight convolutional neural networks. DTACSNet provides cloud and cloud shadow masks and SR estimates 10× faster than the operational S-2 L2A processor in dedicated space-tested hardware: 7 mins versus 1 h for a 10 980 × 10 980 scene. The DTACSNet cloud masking, based on a lightweight neural network, obtains the highest F2-score (0.81), followed by the state-of-the-art KappaMask (0.74), Fmask (0.72), and Sen2Cor v.2.8 (0.51) algorithms. In addition, validation results on independent datasets show that DTACSNet can efficiently replicate Sen2Cor SR estimates, reporting a competitive accuracy with differences below 2%.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"17 ","pages":"19518-19529"},"PeriodicalIF":4.7,"publicationDate":"2024-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10716772","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142594969","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：