ISPRS Journal of Photogrammetry and Remote Sensing最新文献_第7页

Generative networks for spatio-temporal gap filling of Sentinel-2 reflectances

IF 10.6 1区地球科学 Q1 GEOGRAPHY, PHYSICAL

ISPRS Journal of Photogrammetry and Remote Sensing

Pub Date : 2025-02-01 DOI: 10.1016/j.isprsjprs.2025.01.016

Maria Gonzalez-Calabuig, Miguel-Ángel Fernández-Torres, Gustau Camps-Valls

Earth observation from satellite sensors offers the possibility to monitor natural ecosystems by deriving spatially explicit and temporally resolved biogeophysical parameters. Optical remote sensing, however, suffers from missing data mainly due to the presence of clouds, sensor malfunctioning, and atmospheric conditions. This study proposes a novel deep learning architecture to address gap filling of satellite reflectances, more precisely the visible and near-infrared bands, and illustrates its performance at high-resolution Sentinel-2 data. We introduce GANFilling, a generative adversarial network capable of sequence-to-sequence translation, which comprises convolutional long short-term memory layers to effectively exploit complete dependencies in space–time series data. We focus on Europe and evaluate the method’s performance quantitatively (through distortion and perceptual metrics) and qualitatively (via visual inspection and visual quality metrics). Quantitatively, our model offers the best trade-off between denoising corrupted data and preserving noise-free information, underscoring the importance of considering multiple metrics jointly when assessing gap filling tasks. Qualitatively, it successfully deals with various noise sources, such as clouds and missing data, constituting a robust solution to multiple scenarios and settings. We also illustrate and quantify the quality of the generated product in the relevant downstream application of vegetation greenness forecasting, where using GANFilling enhances forecasting in approximately 70% of the considered regions in Europe. This research contributes to underlining the utility of deep learning for Earth observation data, which allows for improved spatially and temporally resolved monitoring of the Earth surface.

{"title":"Generative networks for spatio-temporal gap filling of Sentinel-2 reflectances","authors":"Maria Gonzalez-Calabuig, Miguel-Ángel Fernández-Torres, Gustau Camps-Valls","doi":"10.1016/j.isprsjprs.2025.01.016","DOIUrl":"10.1016/j.isprsjprs.2025.01.016","url":null,"abstract":"<div><div>Earth observation from satellite sensors offers the possibility to monitor natural ecosystems by deriving spatially explicit and temporally resolved biogeophysical parameters. Optical remote sensing, however, suffers from missing data mainly due to the presence of clouds, sensor malfunctioning, and atmospheric conditions. This study proposes a novel deep learning architecture to address gap filling of satellite reflectances, more precisely the visible and near-infrared bands, and illustrates its performance at high-resolution Sentinel-2 data. We introduce GANFilling, a generative adversarial network capable of sequence-to-sequence translation, which comprises convolutional long short-term memory layers to effectively exploit complete dependencies in space–time series data. We focus on Europe and evaluate the method’s performance <em>quantitatively</em> (through distortion and perceptual metrics) and <em>qualitatively</em> (via visual inspection and visual quality metrics). Quantitatively, our model offers the best trade-off between denoising corrupted data and preserving noise-free information, underscoring the importance of considering multiple metrics jointly when assessing gap filling tasks. Qualitatively, it successfully deals with various noise sources, such as clouds and missing data, constituting a robust solution to multiple scenarios and settings. We also illustrate and quantify the quality of the generated product in the relevant downstream application of vegetation greenness forecasting, where using GANFilling enhances forecasting in approximately 70% of the considered regions in Europe. This research contributes to underlining the utility of deep learning for Earth observation data, which allows for improved spatially and temporally resolved monitoring of the Earth surface.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"220 ","pages":"Pages 637-648"},"PeriodicalIF":10.6,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143035306","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Nothing Stands Still: A spatiotemporal benchmark on 3D point cloud registration under large geometric and temporal change

IF 10.6 1区地球科学 Q1 GEOGRAPHY, PHYSICAL

ISPRS Journal of Photogrammetry and Remote Sensing

Pub Date : 2025-02-01 DOI: 10.1016/j.isprsjprs.2025.01.010

Tao Sun , Yan Hao , Shengyu Huang , Silvio Savarese , Konrad Schindler , Marc Pollefeys , Iro Armeni

Building 3D geometric maps of man-made spaces is a well-established and active field that is fundamental to numerous computer vision and robotics applications. However, considering the continuously evolving nature of built environments, it is essential to question the capabilities of current mapping efforts in handling temporal changes. In addition to the above, the ability to create spatiotemporal maps holds significant potential for achieving sustainability and circularity goals. Existing mapping approaches focus on small changes, such as object relocation within common living spaces or self-driving car operation in outdoor spaces; all cases where the main structure of the scene remains fixed. Consequently, these approaches fail to address more radical change in the structure of the built environment, such as on the geometry and topology of it. To promote advancements on this front, we introduce the Nothing Stands Still (NSS) benchmark, which focuses on the spatiotemporal registration of 3D scenes undergoing large spatial and temporal change, ultimately creating one coherent spatiotemporal map. Specifically, the benchmark involves registering within the same coordinate system two or more partial 3D point clouds (fragments) originating from the same scene but captured from different spatiotemporal views. In addition to the standard task of pairwise registration, we assess multi-way registration of multiple fragments that belong to the same indoor environment and any temporal stage. As part of NSS, we introduce a dataset of 3D point clouds recurrently captured in large-scale building indoor environments that are under construction or renovation. The NSS benchmark presents three scenarios of increasing difficulty, with the goal to quantify the generalization ability of point cloud registration methods over space (within one building and across buildings) and time. We conduct extensive evaluations of state-of-the-art methods on NSS over all tasks and scenarios. The results demonstrate the necessity for novel methods specifically designed to handle large spatiotemporal changes. The homepage of our benchmark is at http://nothing-stands-still.com.

{"title":"Nothing Stands Still: A spatiotemporal benchmark on 3D point cloud registration under large geometric and temporal change","authors":"Tao Sun , Yan Hao , Shengyu Huang , Silvio Savarese , Konrad Schindler , Marc Pollefeys , Iro Armeni","doi":"10.1016/j.isprsjprs.2025.01.010","DOIUrl":"10.1016/j.isprsjprs.2025.01.010","url":null,"abstract":"<div><div>Building 3D geometric maps of man-made spaces is a well-established and active field that is fundamental to numerous computer vision and robotics applications. However, considering the continuously evolving nature of built environments, it is essential to question the capabilities of current mapping efforts in handling temporal changes. In addition to the above, the ability to create spatiotemporal maps holds significant potential for achieving sustainability and circularity goals. Existing mapping approaches focus on small changes, such as object relocation within common living spaces or self-driving car operation in outdoor spaces; all cases where the main structure of the scene remains fixed. Consequently, these approaches fail to address more radical change in the structure of the built environment, such as on the geometry and topology of it. To promote advancements on this front, we introduce the <strong><strong>Nothing Stands Still</strong> (<strong>NSS</strong>)</strong> benchmark, which focuses on the spatiotemporal registration of 3D scenes undergoing large spatial and temporal change, ultimately creating one coherent spatiotemporal map. Specifically, the benchmark involves registering within the same coordinate system two or more partial 3D point clouds (fragments) originating from the same scene but captured from different spatiotemporal views. In addition to the standard task of <em>pairwise</em> registration, we assess <em>multi-way</em> registration of multiple fragments that belong to the same indoor environment and any temporal stage. As part of <strong>NSS</strong>, we introduce a dataset of 3D point clouds recurrently captured in large-scale building indoor environments that are under construction or renovation. The <strong>NSS</strong> benchmark presents three scenarios of increasing difficulty, with the goal to quantify the generalization ability of point cloud registration methods over space (within one building and across buildings) and time. We conduct extensive evaluations of state-of-the-art methods on <strong>NSS</strong> over all tasks and scenarios. The results demonstrate the necessity for novel methods specifically designed to handle large spatiotemporal changes. The homepage of our benchmark is at <span><span>http://nothing-stands-still.com</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"220 ","pages":"Pages 799-823"},"PeriodicalIF":10.6,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143072521","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Near-surface air temperature estimation for areas with sparse observations based on transfer learning

IF 10.6 1区地球科学 Q1 GEOGRAPHY, PHYSICAL

ISPRS Journal of Photogrammetry and Remote Sensing

Pub Date : 2025-02-01 DOI: 10.1016/j.isprsjprs.2025.01.021

Wei Wang , Stefan Brönnimann , Ji Zhou , Shaopeng Li , Ziwei Wang

Near-surface air temperature (NSAT) data is essential for climate analysis and applied research in areas with sparse ground-based observations. In recent years, machine learning (ML) techniques have been increasingly used to estimate NSAT, delivering promising results. However, in regions with limited observational samples, machine learning-based NSAT estimations may encounter challenges, potentially resulting in reduced accuracy. Therefore, this study introduces a novel model – TranSAT. TranSAT utilizes a transfer learning (TL) framework, deep neural network (DNN) and U-shape convolutional network (U-Net) to enhance the accuracy of NSAT estimations in regions with sparse observational data. Considering the scarcity of observation stations in certain regions, the Tibetan Plateau within the China's landmass (CNTP) is selected as the study region. The majority of observational stations are concentrated in the eastern and southeastern parts of CNTP, with a significant lack of stations in the northern and western regions. The scarce observations in the CNTP affect NSAT estimation accuracy in recent studies, thus limiting practical applications. The estimated NSAT (i.e., TranSAT NSAT) by TranSAT is evaluated by measurements of 10 independent meteorological stations from the Meteorological network in China's cold region (MSC). Evaluation results indicate an average coefficient of determination (R²) of 0.92 and a root mean squared error (RMSE) of 2.29 °C. The TranSAT NSAT exhibits an overall decrease of at least 7 % on RMSE compared to existing NSAT datasets, with a more significant enhancement of over 40 % in regions with sparse ground observations. These results highlight the good and consistent performance of TranSAT NSAT, further confirming that the proposed TranSAT model effectively improves NSAT estimation in areas with limited observational data.

{"title":"Near-surface air temperature estimation for areas with sparse observations based on transfer learning","authors":"Wei Wang , Stefan Brönnimann , Ji Zhou , Shaopeng Li , Ziwei Wang","doi":"10.1016/j.isprsjprs.2025.01.021","DOIUrl":"10.1016/j.isprsjprs.2025.01.021","url":null,"abstract":"<div><div>Near-surface air temperature (NSAT) data is essential for climate analysis and applied research in areas with sparse ground-based observations. In recent years, machine learning (ML) techniques have been increasingly used to estimate NSAT, delivering promising results. However, in regions with limited observational samples, machine learning-based NSAT estimations may encounter challenges, potentially resulting in reduced accuracy. Therefore, this study introduces a novel model – TranSAT. TranSAT utilizes a transfer learning (TL) framework, deep neural network (DNN) and U-shape convolutional network (U-Net) to enhance the accuracy of NSAT estimations in regions with sparse observational data. Considering the scarcity of observation stations in certain regions, the Tibetan Plateau within the China's landmass (CNTP) is selected as the study region. The majority of observational stations are concentrated in the eastern and southeastern parts of CNTP, with a significant lack of stations in the northern and western regions. The scarce observations in the CNTP affect NSAT estimation accuracy in recent studies, thus limiting practical applications. The estimated NSAT (i.e., TranSAT NSAT) by TranSAT is evaluated by measurements of 10 independent meteorological stations from the Meteorological network in China's cold region (MSC). Evaluation results indicate an average coefficient of determination (<em>R</em><sup>2</sup>) of 0.92 and a root mean squared error (RMSE) of 2.29 °C. The TranSAT NSAT exhibits an overall decrease of at least 7 % on RMSE compared to existing NSAT datasets, with a more significant enhancement of over 40 % in regions with sparse ground observations. These results highlight the good and consistent performance of TranSAT NSAT, further confirming that the proposed TranSAT model effectively improves NSAT estimation in areas with limited observational data.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"220 ","pages":"Pages 712-727"},"PeriodicalIF":10.6,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143035287","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Cross-view geolocalization and disaster mapping with street-view and VHR satellite imagery: A case study of Hurricane IAN

IF 10.6 1区地球科学 Q1 GEOGRAPHY, PHYSICAL

ISPRS Journal of Photogrammetry and Remote Sensing

Pub Date : 2025-02-01 DOI: 10.1016/j.isprsjprs.2025.01.003

Hao Li , Fabian Deuser , Wenping Yin , Xuanshu Luo , Paul Walther , Gengchen Mai , Wei Huang , Martin Werner

Nature disasters play a key role in shaping human-urban infrastructure interactions. Effective and efficient response to natural disasters is essential for building resilience and sustainable urban environment. Two types of information are usually the most necessary and difficult to gather in disaster response. The first information is about the disaster damage perception, which shows how badly people think that urban infrastructure has been damaged. The second information is geolocation awareness, which means how people’s whereabouts are made available. In this paper, we proposed a novel disaster mapping framework, namely CVDisaster, aiming at simultaneously addressing geolocalization and damage perception estimation using cross-view Street-View Imagery (SVI) and Very High-Resolution satellite imagery. CVDisaster consists of two cross-view models, where CVDisaster-Geoloc refers to a cross-view geolocalization model based on a contrastive learning objective with a Siamese ConvNeXt image encoder and CVDisaster-Est is a cross-view classification model based on a Coupled Global Context Vision Transformer (CGCViT). Taking Hurricane IAN as a case study, we evaluate the CVDisaster framework by creating a novel cross-view dataset (CVIAN) and conducting extensive experiments. As a result, we show that CVDisaster can achieve highly competitive performance (over 80% for geolocalization and 75% for damage perception estimation) with even limited fine-tuning efforts, which largely motivates future cross-view models and applications within a broader GeoAI research community. The data and code are publicly available at: https://github.com/tum-bgd/CVDisaster.

{"title":"Cross-view geolocalization and disaster mapping with street-view and VHR satellite imagery: A case study of Hurricane IAN","authors":"Hao Li , Fabian Deuser , Wenping Yin , Xuanshu Luo , Paul Walther , Gengchen Mai , Wei Huang , Martin Werner","doi":"10.1016/j.isprsjprs.2025.01.003","DOIUrl":"10.1016/j.isprsjprs.2025.01.003","url":null,"abstract":"<div><div>Nature disasters play a key role in shaping human-urban infrastructure interactions. Effective and efficient response to natural disasters is essential for building resilience and sustainable urban environment. Two types of information are usually the most necessary and difficult to gather in disaster response. The first information is about the disaster damage perception, which shows how badly people think that urban infrastructure has been damaged. The second information is geolocation awareness, which means how people’s whereabouts are made available. In this paper, we proposed a novel disaster mapping framework, namely CVDisaster, aiming at simultaneously addressing geolocalization and damage perception estimation using cross-view Street-View Imagery (SVI) and Very High-Resolution satellite imagery. CVDisaster consists of two cross-view models, where CVDisaster-Geoloc refers to a cross-view geolocalization model based on a contrastive learning objective with a Siamese ConvNeXt image encoder and CVDisaster-Est is a cross-view classification model based on a Coupled Global Context Vision Transformer (CGCViT). Taking Hurricane IAN as a case study, we evaluate the CVDisaster framework by creating a novel cross-view dataset (CVIAN) and conducting extensive experiments. As a result, we show that CVDisaster can achieve highly competitive performance (over 80% for geolocalization and 75% for damage perception estimation) with even limited fine-tuning efforts, which largely motivates future cross-view models and applications within a broader GeoAI research community. The data and code are publicly available at: <span><span>https://github.com/tum-bgd/CVDisaster</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"220 ","pages":"Pages 841-854"},"PeriodicalIF":10.6,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143072522","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

RF-DET: Refocusing on the small-scale objects using aggregated context for accurate power transmitting components detection on UAV oblique imagery

IF 10.6 1区地球科学 Q1 GEOGRAPHY, PHYSICAL

ISPRS Journal of Photogrammetry and Remote Sensing

Pub Date : 2025-02-01 DOI: 10.1016/j.isprsjprs.2025.01.005

Zhengfei Yan , Chi Chen , Shaolong Wu , Zhiye Wang , Liuchun Li , Shangzhe Sun , Bisheng Yang , Jing Fu

In transmission lines, regular inspections are crucial for maintaining their safe operation. Automatic and accurate detection of power transmission facility components (power components) in inspection imagery is an effective way to monitor the status of electrical assets within the Right of Ways (RoWs). However, the multitude of small-scale objects (e.g. grading rings, vibration dampers) in inspection imagery poses enormous challenges. To address these challenges, we propose a coarse-to-fine object detector named RF-DET. It adopts a Refocus Framework to refine the detection accuracy of small objects within the Regions of Interest of the Power Components (P-RoIs) generated through explicit context. On the basis above, an Implicit Context Aggregation Attention Module (ICAM) is proposed. ICAM utilizes a multi-branch structure to capture and aggregate multi-directional positional and global information, enabling in-depth mining of the implicit context among small objects. To verify the performance of this detector, a benchmark dataset named DOPI-UAV is constructed, comprising 4,438 UAV oblique images and 54,591 instances, encompassing six common categories of power components and one category of defect. Experimental results show that RF-DET achieves mAP of 62.7%, 55.7%, 84.6%, and 52.8% on the DOPI-UAV, Tower, CPLID, and InsD datasets, respectively. Compared to the state-of-the-art method, such as YOLOv9, RF-DET attains significant performance improvements, with increases of 5.2% in mAP and 6.4% in mAP₅₀, respectively. Especially, the AP_S shows an improvement of 8.3%. The datasets and codes are available at https://github.com/DCSI2022/RF-DET.

{"title":"RF-DET: Refocusing on the small-scale objects using aggregated context for accurate power transmitting components detection on UAV oblique imagery","authors":"Zhengfei Yan , Chi Chen , Shaolong Wu , Zhiye Wang , Liuchun Li , Shangzhe Sun , Bisheng Yang , Jing Fu","doi":"10.1016/j.isprsjprs.2025.01.005","DOIUrl":"10.1016/j.isprsjprs.2025.01.005","url":null,"abstract":"<div><div>In transmission lines, regular inspections are crucial for maintaining their safe operation. Automatic and accurate detection of power transmission facility components (power components) in inspection imagery is an effective way to monitor the status of electrical assets within the Right of Ways (RoWs). However, the multitude of small-scale objects (e.g. grading rings, vibration dampers) in inspection imagery poses enormous challenges. To address these challenges, we propose a coarse-to-fine object detector named RF-DET. It adopts a Refocus Framework to refine the detection accuracy of small objects within the Regions of Interest of the Power Components (P-RoIs) generated through explicit context. On the basis above, an Implicit Context Aggregation Attention Module (ICAM) is proposed. ICAM utilizes a multi-branch structure to capture and aggregate multi-directional positional and global information, enabling in-depth mining of the implicit context among small objects. To verify the performance of this detector, a benchmark dataset named DOPI-UAV is constructed, comprising 4,438 UAV oblique images and 54,591 instances, encompassing six common categories of power components and one category of defect. Experimental results show that RF-DET achieves mAP of 62.7%, 55.7%, 84.6%, and 52.8% on the DOPI-UAV, Tower, CPLID, and InsD datasets, respectively. Compared to the state-of-the-art method, such as YOLOv9, RF-DET attains significant performance improvements, with increases of 5.2% in mAP and 6.4% in mAP<sub>50</sub>, respectively. Especially, the AP<sub>S</sub> shows an improvement of 8.3%. The datasets and codes are available at <span><span>https://github.com/DCSI2022/RF-DET</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"220 ","pages":"Pages 692-711"},"PeriodicalIF":10.6,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143161509","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

3D automatic detection and correction for phase unwrapping errors in time series SAR interferometry 时间序列SAR干涉中相位展开误差的三维自动检测与校正

IF 10.6 1区地球科学 Q1 GEOGRAPHY, PHYSICAL

ISPRS Journal of Photogrammetry and Remote Sensing

Pub Date : 2025-02-01 DOI: 10.1016/j.isprsjprs.2024.12.013

Ying Liu , Hong’an Wu , Yonghong Zhang , Zhong Lu , Yonghui Kang , Jujie Wei

Phase unwrapping (PhU) is one of the most critical steps in synthetic aperture radar interferometry (InSAR) technology. However, the current phase unwrapping methods cannot completely avoid the PhU errors, particularly in complex environments with low coherence. Here, we show that the PhU errors can be corrected well with the time series interferograms. We propose a three-dimensional automatic detection and correction (3D-ADAC) method based on phase closure for time-series InSAR PhU errors to improve the quality of the interferograms, especially for the regions with the same errors in different interferograms which cancel each other out in phase closure. The 3D-ADAC algorithm was evaluated with 26 Sentinel-1 SAR images and 72 phase closure loops over the Tianjin region, China, and compared with the popular MintPy and CorPhU methods. Our results demonstrate that the number of new arcs with model coherence coefficient greater than 0.7 achieved by the proposed method is 2.36 times that by the method used in the MintPy software and 3.07 times that by the CorPhU method. The corrected and improved interferograms will be helpful for accurately mapping the ground deformations or Earth topographies via InSAR technology. Codes and data are available at https://github.com/Lylionaurora/code3d-ADCD.

相位展开（PhU）是合成孔径雷达干涉测量（InSAR）技术的关键步骤之一。然而，目前的相位展开方法并不能完全避免PhU误差，特别是在低相干性的复杂环境中。在这里，我们证明了时间序列干涉图可以很好地纠正PhU误差。为了提高干涉图的质量，特别是对不同干涉图中具有相同误差且相位封闭相互抵消的区域，提出了一种基于相位封闭的时间序列InSAR PhU误差三维自动检测与校正（3D-ADAC）方法。利用中国天津地区的26幅Sentinel-1 SAR图像和72个相位闭合环对3D-ADAC算法进行了评估，并与流行的MintPy和CorPhU方法进行了比较。结果表明，该方法获得的模型相干系数大于0.7的新弧数是MintPy方法的2.36倍，是CorPhU方法的3.07倍。修正和改进后的干涉图将有助于InSAR技术精确测绘地面变形或地球地形。代码和数据可在https://github.com/Lylionaurora/code3d-ADCD上获得。

{"title":"3D automatic detection and correction for phase unwrapping errors in time series SAR interferometry","authors":"Ying Liu , Hong’an Wu , Yonghong Zhang , Zhong Lu , Yonghui Kang , Jujie Wei","doi":"10.1016/j.isprsjprs.2024.12.013","DOIUrl":"10.1016/j.isprsjprs.2024.12.013","url":null,"abstract":"<div><div>Phase unwrapping (PhU) is one of the most critical steps in synthetic aperture radar interferometry (InSAR) technology. However, the current phase unwrapping methods cannot completely avoid the PhU errors, particularly in complex environments with low coherence. Here, we show that the PhU errors can be corrected well with the time series interferograms. We propose a three-dimensional automatic detection and correction (3D-ADAC) method based on phase closure for time-series InSAR PhU errors to improve the quality of the interferograms, especially for the regions with the same errors in different interferograms which cancel each other out in phase closure. The 3D-ADAC algorithm was evaluated with 26 Sentinel-1 SAR images and 72 phase closure loops over the Tianjin region, China, and compared with the popular MintPy and CorPhU methods. Our results demonstrate that the number of new arcs with model coherence coefficient greater than 0.7 achieved by the proposed method is 2.36 times that by the method used in the MintPy software and 3.07 times that by the CorPhU method. The corrected and improved interferograms will be helpful for accurately mapping the ground deformations or Earth topographies via InSAR technology. Codes and data are available at https://github.com/Lylionaurora/code3d-ADCD.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"220 ","pages":"Pages 232-245"},"PeriodicalIF":10.6,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142874572","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Improving 30-meter global impervious surface area (GISA) mapping: New method and dataset 改进30米全球不透水面（GISA）制图：新方法和数据集

IF 10.6 1区地球科学 Q1 GEOGRAPHY, PHYSICAL

ISPRS Journal of Photogrammetry and Remote Sensing

Pub Date : 2025-02-01 DOI: 10.1016/j.isprsjprs.2024.12.023

Huiqun Ren , Xin Huang , Jie Yang , Guoqing Zhou

Timely and accurate monitoring of impervious surface areas (ISA) is crucial for effective urban planning and sustainable development. Recent advances in remote sensing technologies have enabled global ISA mapping at fine spatial resolution (<30 m) over long time spans (>30 years), offering the opportunity to track global ISA dynamics. However, existing 30 m global long-term ISA datasets suffer from omission and commission issues, affecting their accuracy in practical applications. To address these challenges, we proposed a novel global long-term ISA mapping method and generated a new 30 m global ISA dataset from 1985 to 2021, namely GISA-new. Specifically, to reduce ISA omissions, a multi-temporal Continuous Change Detection and Classification (CCDC) algorithm that accounts for newly added ISA regions (NA-CCDC) was proposed to enhance the diversity and representativeness of the training samples. Meanwhile, a multi-scale iterative (MIA) method was proposed to automatically remove global commissions of various sizes and types. Finally, we collected two independent test datasets with over 100,000 test samples globally for accuracy assessment. Results showed that GISA-new outperformed other existing global ISA datasets, such as GISA, WSF-evo, GAIA, and GAUD, achieving the highest overall accuracy (93.12 %), the lowest omission errors (10.50 %), and the lowest commission errors (3.52 %). Furthermore, the spatial distribution of global ISA omissions and commissions was analyzed, revealing more mapping uncertainties in the Northern Hemisphere. In general, the proposed method in this study effectively addressed global ISA omissions and removed commissions at different scales. The generated high-quality GISA-new can serve as a fundamental parameter for a more comprehensive understanding of global urbanization.

及时、准确地监测不透水地表面积对有效的城市规划和可持续发展至关重要。遥感技术的最新进展使长时间跨度（30年）的精细空间分辨率（30米）的全球ISA制图成为可能，为跟踪全球ISA动态提供了机会。然而，现有的30 m全球长期ISA数据集存在遗漏和委托问题，影响了其在实际应用中的准确性。为了解决这些挑战，我们提出了一种新的全球长期ISA映射方法，并生成了1985 - 2021年新的30 m全球ISA数据集，即GISA-new。具体而言，为了减少ISA遗漏，提出了一种考虑ISA新区域的多时相连续变化检测与分类（NA-CCDC）算法，以增强训练样本的多样性和代表性。同时，提出了一种多尺度迭代（MIA）方法来自动去除各种规模和类型的全局佣金。最后，我们收集了两个独立的测试数据集，其中包括全球超过100,000个测试样本，用于准确性评估。结果表明，GISA-new优于GISA、WSF-evo、GAIA和GAUD等现有全球ISA数据集，总体准确率最高（93.12%），遗漏误差最低（10.50%），委托误差最低（3.52%）。此外，还分析了全球ISA遗漏和佣金的空间分布，揭示了北半球制图的更多不确定性。总的来说，本研究中提出的方法有效地解决了全球的国际公务员制度遗漏问题，并取消了不同比额表的佣金。生成的高质量GISA-new可以作为更全面了解全球城市化的基本参数。

{"title":"Improving 30-meter global impervious surface area (GISA) mapping: New method and dataset","authors":"Huiqun Ren , Xin Huang , Jie Yang , Guoqing Zhou","doi":"10.1016/j.isprsjprs.2024.12.023","DOIUrl":"10.1016/j.isprsjprs.2024.12.023","url":null,"abstract":"<div><div>Timely and accurate monitoring of impervious surface areas (ISA) is crucial for effective urban planning and sustainable development. Recent advances in remote sensing technologies have enabled global ISA mapping at fine spatial resolution (<30 m) over long time spans (>30 years), offering the opportunity to track global ISA dynamics. However, existing 30 m global long-term ISA datasets suffer from omission and commission issues, affecting their accuracy in practical applications. To address these challenges, we proposed a novel global long-term ISA mapping method and generated a new 30 m global ISA dataset from 1985 to 2021, namely GISA-new. Specifically, to reduce ISA omissions, a multi-temporal Continuous Change Detection and Classification (CCDC) algorithm that accounts for newly added ISA regions (NA-CCDC) was proposed to enhance the diversity and representativeness of the training samples. Meanwhile, a multi-scale iterative (MIA) method was proposed to automatically remove global commissions of various sizes and types. Finally, we collected two independent test datasets with over 100,000 test samples globally for accuracy assessment. Results showed that GISA-new outperformed other existing global ISA datasets, such as GISA, WSF-evo, GAIA, and GAUD, achieving the highest overall accuracy (93.12 %), the lowest omission errors (10.50 %), and the lowest commission errors (3.52 %). Furthermore, the spatial distribution of global ISA omissions and commissions was analyzed, revealing more mapping uncertainties in the Northern Hemisphere. In general, the proposed method in this study effectively addressed global ISA omissions and removed commissions at different scales. The generated high-quality GISA-new can serve as a fundamental parameter for a more comprehensive understanding of global urbanization.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"220 ","pages":"Pages 354-376"},"PeriodicalIF":10.6,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142925284","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A universal method to recognize global big rivers estuarine turbidity maximum from remote sensing 遥感识别全球大河河口浊度最大值的通用方法

IF 10.6 1区地球科学 Q1 GEOGRAPHY, PHYSICAL

ISPRS Journal of Photogrammetry and Remote Sensing

Pub Date : 2025-02-01 DOI: 10.1016/j.isprsjprs.2025.01.002

Chongyang Wang , Chenghu Zhou , Xia Zhou , Mingjie Duan , Yingwei Yan , Jiaxue Wang , Li Wang , Kai Jia , Yishan Sun , Danni Wang , Yangxiaoyue Liu , Dan Li , Jinyue Chen , Hao Jiang , Shuisen Chen

The study of estuarine turbidity maximum (ETM) has a long history. However, the algorithms and criteria for ETM identification vary significantly across estuaries and hydrological regimes. Moreover, almost all of these methods depend on derived water parameters, such as suspended sediment concentration and turbidity, which inevitably result in inherent errors in the ETM results. To overcome these disadvantages and develop a standard ETM recognition method that has good applicability in most estuaries, this study analyzed the spectral characteristics of 23 big river estuaries worldwide using Landsat and Sentinel sensor images. Based on the difference in band reflectance between the ETM and normal water bodies, we first proposed a universal method, defined as the product of the ratio of blue, green and red bands to their average value over the entire estuary, namely, Red Green Blue Turbidity (RGBT). Combined with the corresponding remote sensing images, the ETM distributions in the 23 estuaries were extracted and analyzed. It was found that the ETM recognition results for the Pearl River Estuary on different dates (2004, 2015) were consistent with those of previous studies. The validation accuracies (Q) reached 0.8335 and 0.8800, respectively, illustrating the effectiveness of the RGBT method in the Pearl River Estuary. For the other 22 estuaries, the RGBT-based ETM recognition results were evaluated using the corresponding visual interpretation. Comparisons and details of the ETM boundaries indicate that the method works well for all types of estuaries. It also included accurately identifying slightly turbid plumes from maritime wind turbines and bridge piers. The validation accuracy exceeded 0.9 (0.9025–0.9733) in seven estuaries, and surpassed 0.7898 in the remaining 15 estuaries. The RGBT method generally achieved higher accuracy for estuaries in Asia and Europe, followed by estuaries in America and Oceania, with a relatively lower accuracy for estuaries in Africa. But the variation in the accuracy in different regions was small. The average validation accuracy of all estuaries and different seasons was as high as 0.9027. This demonstrates that the unified method with same criterion can directly and effectively recognize ETM distributions from multi-source remote sensing data in different estuaries worldwide.

河口浊度最大值（ETM）的研究历史悠久。然而，在不同的河口和水文条件下，ETM识别的算法和标准差异很大。此外，几乎所有这些方法都依赖于导出的水参数，如悬沙浓度和浊度，这不可避免地导致ETM结果的固有误差。为了克服这些缺点，开发一种适用于大多数河口的标准ETM识别方法，本研究利用Landsat和Sentinel传感器图像对全球23个大河河口的光谱特征进行了分析。基于ETM与正常水体波段反射率的差异，我们首先提出了一种通用的方法，将其定义为整个河口内蓝、绿、红波段的比值与其平均值的乘积，即红绿蓝浊度（RGBT）。结合相应的遥感影像，提取并分析了23个河口的ETM分布。发现珠江口不同日期（2004年、2015年）的ETM识别结果与前人研究结果一致。验证精度(Q)分别达到0.8335和0.8800，说明了RGBT方法在珠江口的有效性。对其余22个河口，采用相应的视觉解译对基于rgbt的ETM识别结果进行评价。结果表明，该方法适用于所有类型的河口。它还包括准确识别海上风力涡轮机和桥墩上的微浑浊羽流。7个河口的验证精度超过0.9(0.9025 ~ 0.9733)，其余15个河口的验证精度超过0.7898。RGBT方法对亚洲和欧洲河口的精度普遍较高，其次是美洲和大洋洲河口，非洲河口精度相对较低。但不同地区的准确度差异很小。各河口和不同季节的平均验证精度高达0.9027。这表明，采用同一准则的统一方法可以直接有效地识别全球不同河口多源遥感数据的ETM分布。

{"title":"A universal method to recognize global big rivers estuarine turbidity maximum from remote sensing","authors":"Chongyang Wang , Chenghu Zhou , Xia Zhou , Mingjie Duan , Yingwei Yan , Jiaxue Wang , Li Wang , Kai Jia , Yishan Sun , Danni Wang , Yangxiaoyue Liu , Dan Li , Jinyue Chen , Hao Jiang , Shuisen Chen","doi":"10.1016/j.isprsjprs.2025.01.002","DOIUrl":"10.1016/j.isprsjprs.2025.01.002","url":null,"abstract":"<div><div>The study of estuarine turbidity maximum (ETM) has a long history. However, the algorithms and criteria for ETM identification vary significantly across estuaries and hydrological regimes. Moreover, almost all of these methods depend on derived water parameters, such as suspended sediment concentration and turbidity, which inevitably result in inherent errors in the ETM results. To overcome these disadvantages and develop a standard ETM recognition method that has good applicability in most estuaries, this study analyzed the spectral characteristics of 23 big river estuaries worldwide using Landsat and Sentinel sensor images. Based on the difference in band reflectance between the ETM and normal water bodies, we first proposed a universal method, defined as the product of the ratio of blue, green and red bands to their average value over the entire estuary, namely, Red Green Blue Turbidity (RGBT). Combined with the corresponding remote sensing images, the ETM distributions in the 23 estuaries were extracted and analyzed. It was found that the ETM recognition results for the Pearl River Estuary on different dates (2004, 2015) were consistent with those of previous studies. The validation accuracies (Q) reached 0.8335 and 0.8800, respectively, illustrating the effectiveness of the RGBT method in the Pearl River Estuary. For the other 22 estuaries, the RGBT-based ETM recognition results were evaluated using the corresponding visual interpretation. Comparisons and details of the ETM boundaries indicate that the method works well for all types of estuaries. It also included accurately identifying slightly turbid plumes from maritime wind turbines and bridge piers. The validation accuracy exceeded 0.9 (0.9025–0.9733) in seven estuaries, and surpassed 0.7898 in the remaining 15 estuaries. The RGBT method generally achieved higher accuracy for estuaries in Asia and Europe, followed by estuaries in America and Oceania, with a relatively lower accuracy for estuaries in Africa. But the variation in the accuracy in different regions was small. The average validation accuracy of all estuaries and different seasons was as high as 0.9027. This demonstrates that the unified method with same criterion can directly and effectively recognize ETM distributions from multi-source remote sensing data in different estuaries worldwide.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"220 ","pages":"Pages 509-523"},"PeriodicalIF":10.6,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142967835","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A sensitive geometric self-calibration method and stability analysis for multiview spaceborne SAR images based on the range-Doppler model 基于距离-多普勒模型的多视点星载SAR图像几何自标定方法及稳定性分析

IF 10.6 1区地球科学 Q1 GEOGRAPHY, PHYSICAL

ISPRS Journal of Photogrammetry and Remote Sensing

Pub Date : 2025-02-01 DOI: 10.1016/j.isprsjprs.2025.01.009

Lina Yin , Mingjun Deng , Yin Yang , Yunqing Huang , Qili Tang

Synthetic aperture radar (SAR) image positioning technology is extensively used in many scientific fields, including land surveying and mapping. Geometric self-calibration can be performed if images are captured in three directions. However, when the number of images is too small, self-calibration of the SAR images based on the range-Doppler (RD) model appears to be inaccurate. Hence, a robust geometric calibration method has an important impact on calibration results. The effectiveness of such a method depends on the validity of the SAR images. This implies that the calibration can algorithmically optimize the images involved in self-calibration such that the calibration results are close to the true unknown parameters. To overcome these inaccuracies in geometric calibration, this study proposes a flexible calibration approach. The determinant and accuracy stabilization factor (ASF) are utilized to filter the images, allowing the evaluation of singular solutions and determining the validity of the SAR images. Experimental results demonstrate that the robustness of the proposed approach. In addition, the slant range equation is suggested as the dominant equation for analyzing image calibration error sources and image capture. It is found that satellite position is the main source of image calibration errors. Therefore, the impact of the satellite position and the associated incidence angle on the calibration is analyzed. The analysis reveals that it is desirable for satellites to capture ipsilateral images with incidence angles greater than 8

°

. This finding justifies the acquisition of SAR images.

合成孔径雷达（SAR）图像定位技术广泛应用于包括土地测绘在内的许多科学领域。如果在三个方向上捕获图像，则可以进行几何自校准。然而，当图像数量过少时，基于距离-多普勒（RD）模型的SAR图像自定标会出现不准确的情况。因此，鲁棒几何标定方法对标定结果有重要影响。这种方法的有效性取决于SAR图像的有效性。这意味着校准可以通过算法优化自校准所涉及的图像，使校准结果接近真实的未知参数。为了克服几何标定中的这些误差，本研究提出了一种灵活的标定方法。利用行列式和精度稳定因子（ASF）对图像进行过滤，允许奇异解的评估并确定SAR图像的有效性。实验结果证明了该方法的鲁棒性。此外，建议将倾斜距离方程作为分析图像校准误差源和图像捕获的主导方程。研究发现，卫星位置是图像标定误差的主要来源。因此，分析了卫星位置和相关入射角对标定的影响。分析表明，卫星捕获入射角大于8°的同侧图像是理想的。这一发现证明了获取SAR图像的合理性。

{"title":"A sensitive geometric self-calibration method and stability analysis for multiview spaceborne SAR images based on the range-Doppler model","authors":"Lina Yin , Mingjun Deng , Yin Yang , Yunqing Huang , Qili Tang","doi":"10.1016/j.isprsjprs.2025.01.009","DOIUrl":"10.1016/j.isprsjprs.2025.01.009","url":null,"abstract":"<div><div>Synthetic aperture radar (SAR) image positioning technology is extensively used in many scientific fields, including land surveying and mapping. Geometric self-calibration can be performed if images are captured in three directions. However, when the number of images is too small, self-calibration of the SAR images based on the range-Doppler (RD) model appears to be inaccurate. Hence, a robust geometric calibration method has an important impact on calibration results. The effectiveness of such a method depends on the validity of the SAR images. This implies that the calibration can algorithmically optimize the images involved in self-calibration such that the calibration results are close to the true unknown parameters. To overcome these inaccuracies in geometric calibration, this study proposes a flexible calibration approach. The determinant and accuracy stabilization factor (ASF) are utilized to filter the images, allowing the evaluation of singular solutions and determining the validity of the SAR images. Experimental results demonstrate that the robustness of the proposed approach. In addition, the slant range equation is suggested as the dominant equation for analyzing image calibration error sources and image capture. It is found that satellite position is the main source of image calibration errors. Therefore, the impact of the satellite position and the associated incidence angle on the calibration is analyzed. The analysis reveals that it is desirable for satellites to capture ipsilateral images with incidence angles greater than 8<span><math><mo>°</mo></math></span>. This finding justifies the acquisition of SAR images.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"220 ","pages":"Pages 550-562"},"PeriodicalIF":10.6,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142989649","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Global high categorical resolution land cover mapping via weak supervision 基于弱监督的全球高分类分辨率土地覆盖制图

IF 10.6 1区地球科学 Q1 GEOGRAPHY, PHYSICAL

ISPRS Journal of Photogrammetry and Remote Sensing

Pub Date : 2025-02-01 DOI: 10.1016/j.isprsjprs.2024.12.017

Xin-Yi Tong , Runmin Dong , Xiao Xiang Zhu

Land cover information is indispensable for advancing the United Nations’ sustainable development goals, and land cover mapping under a more detailed category system would significantly contribute to economic livelihood tracking and environmental degradation measurement. However, the substantial difficulty in acquiring fine-grained training data makes the implementation of this task particularly challenging. Here, we propose to combine fully labeled source domain and weakly labeled target domain for weakly supervised domain adaptation (WSDA). This is beneficial as the utilization of sparse and coarse weak labels can considerably alleviate the labor required for precise and detailed land cover annotation. Specifically, we introduce the Prototype-based pseudo-label Rectification and Expansion (PRE) approach, which leverages the prototypes (i.e., the class-wise feature centroids) as the bridge to connect sparse labels and global feature distributions. According to the feature distances to the prototypes, the confidence of pseudo-labels predicted in the unlabeled regions of the target domain is assessed. This confidence is then utilized to guide the dynamic expansion and rectification of pseudo-labels. Based on PRE, we carry out high categorical resolution land cover mapping for 10 cities in different regions around the world, severally using PlanetScope, Gaofen-1, and Sentinel-2 satellite images. In the study areas, we achieve cross-sensor, cross-category, and cross-continent WSDA, with the overall accuracy exceeding 80%. The promising results indicate that PRE is capable of reducing the dependency of land cover classification on high-quality annotations, thereby improving label efficiency. We expect our work to enable global fine-grained land cover mapping, which in turn promote Earth observation to provide more precise and thorough information for environmental monitoring. Our data and code will be available publicly at https://zhu-xlab.github.io/PRE-land-cover.html.

土地覆盖信息对于推进联合国的可持续发展目标是不可或缺的，在更详细的类别系统下绘制土地覆盖地图将对经济生计跟踪和环境退化测量作出重大贡献。然而，获取细粒度训练数据的巨大困难使得这项任务的实现特别具有挑战性。在此，我们提出将完全标记的源域和弱标记的目标域结合起来进行弱监督域自适应。这是有益的，因为使用稀疏和粗糙的弱标签可以大大减轻精确和详细的土地覆盖标注所需的劳动。具体来说，我们引入了基于原型的伪标签纠偏和扩展（PRE）方法，该方法利用原型（即类特征质心）作为连接稀疏标签和全局特征分布的桥梁。根据特征到原型的距离，评估在目标域的未标记区域预测的伪标签的置信度。然后利用这种置信度来指导伪标签的动态扩展和整改。基于PRE，我们利用PlanetScope、高分一号和哨兵二号卫星影像，对全球不同地区的10个城市进行了高分类分辨率的土地覆盖制图。在研究区域，我们实现了跨传感器、跨品类、跨大陆的WSDA，总体准确率超过80%。结果表明，PRE能够减少土地覆盖分类对高质量标注的依赖，从而提高标注效率。我们希望我们的工作能够实现全球细粒度的土地覆盖测绘，从而促进地球观测，为环境监测提供更精确和全面的信息。我们的数据和代码将在https://zhu-xlab.github.io/PRE-land-cover.html上公开。

{"title":"Global high categorical resolution land cover mapping via weak supervision","authors":"Xin-Yi Tong , Runmin Dong , Xiao Xiang Zhu","doi":"10.1016/j.isprsjprs.2024.12.017","DOIUrl":"10.1016/j.isprsjprs.2024.12.017","url":null,"abstract":"<div><div>Land cover information is indispensable for advancing the United Nations’ sustainable development goals, and land cover mapping under a more detailed category system would significantly contribute to economic livelihood tracking and environmental degradation measurement. However, the substantial difficulty in acquiring fine-grained training data makes the implementation of this task particularly challenging. Here, we propose to combine fully labeled source domain and weakly labeled target domain for weakly supervised domain adaptation (WSDA). This is beneficial as the utilization of sparse and coarse weak labels can considerably alleviate the labor required for precise and detailed land cover annotation. Specifically, we introduce the Prototype-based pseudo-label Rectification and Expansion (<em>PRE</em>) approach, which leverages the prototypes (i.e., the class-wise feature centroids) as the bridge to connect sparse labels and global feature distributions. According to the feature distances to the prototypes, the confidence of pseudo-labels predicted in the unlabeled regions of the target domain is assessed. This confidence is then utilized to guide the dynamic expansion and rectification of pseudo-labels. Based on PRE, we carry out high categorical resolution land cover mapping for 10 cities in different regions around the world, severally using PlanetScope, Gaofen-1, and Sentinel-2 satellite images. In the study areas, we achieve cross-sensor, cross-category, and cross-continent WSDA, with the overall accuracy exceeding 80%. The promising results indicate that PRE is capable of reducing the dependency of land cover classification on high-quality annotations, thereby improving label efficiency. We expect our work to enable global fine-grained land cover mapping, which in turn promote Earth observation to provide more precise and thorough information for environmental monitoring. Our data and code will be available publicly at <span><span>https://zhu-xlab.github.io/PRE-land-cover.html</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50269,"journal":{"name":"ISPRS Journal of Photogrammetry and Remote Sensing","volume":"220 ","pages":"Pages 535-549"},"PeriodicalIF":10.6,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142989650","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0