Pub Date : 2024-11-04DOI: 10.1109/JSTARS.2024.3490584
Zhenhao Yang;Fukun Bi;Xinghai Hou;Dehao Zhou;Yanping Wang
Semantic segmentation is crucial for interpreting remote sensing images. The segmentation performance has been significantly improved recently with the development of deep learning. However, complex background samples and small objects greatly increase the challenge of the semantic segmentation task for remote sensing images. To address these challenges, we propose a dual-domain refinement network (DDRNet) for accurate segmentation. Specifically, we first propose a spatial and frequency feature reconstruction module, which separately utilizes the characteristics of the frequency and spatial domains to refine the global salient features and the fine-grained spatial features of objects. This process enhances the foreground saliency and adaptively suppresses background noise. Subsequently, we propose a feature alignment module that selectively couples the features refined from both domains via cross-attention, achieving semantic alignment between frequency and spatial domains. In addition, a meticulously designed detail-aware attention module is introduced to compensate for the loss of small objects during feature propagation. This module leverages cross-correlation matrices between high-level features and the original image to quantify the similarities among objects belonging to the same category, thereby transmitting rich semantic information from high-level features to small objects. The results on multiple datasets validate that our method outperforms the existing methods and achieves a good compromise between computational overhead and accuracy.
{"title":"DDRNet: Dual-Domain Refinement Network for Remote Sensing Image Semantic Segmentation","authors":"Zhenhao Yang;Fukun Bi;Xinghai Hou;Dehao Zhou;Yanping Wang","doi":"10.1109/JSTARS.2024.3490584","DOIUrl":"https://doi.org/10.1109/JSTARS.2024.3490584","url":null,"abstract":"Semantic segmentation is crucial for interpreting remote sensing images. The segmentation performance has been significantly improved recently with the development of deep learning. However, complex background samples and small objects greatly increase the challenge of the semantic segmentation task for remote sensing images. To address these challenges, we propose a dual-domain refinement network (DDRNet) for accurate segmentation. Specifically, we first propose a spatial and frequency feature reconstruction module, which separately utilizes the characteristics of the frequency and spatial domains to refine the global salient features and the fine-grained spatial features of objects. This process enhances the foreground saliency and adaptively suppresses background noise. Subsequently, we propose a feature alignment module that selectively couples the features refined from both domains via cross-attention, achieving semantic alignment between frequency and spatial domains. In addition, a meticulously designed detail-aware attention module is introduced to compensate for the loss of small objects during feature propagation. This module leverages cross-correlation matrices between high-level features and the original image to quantify the similarities among objects belonging to the same category, thereby transmitting rich semantic information from high-level features to small objects. The results on multiple datasets validate that our method outperforms the existing methods and achieves a good compromise between computational overhead and accuracy.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"17 ","pages":"20177-20189"},"PeriodicalIF":4.7,"publicationDate":"2024-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10741324","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142713773","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 : 2024-11-04DOI: 10.1109/JSTARS.2024.3491216
Xinran Li;Tao Chen;Gang Liu;Jie Dou;Ruiqing Niu;Antonio Plaza
Landslide recognition (LR) is a fundamental task for disaster prevention and control. Convolutional neural networks (CNNs) and transformer architectures have been widely used for extracting landslide information. However, CNNs cannot accurately characterize long-distance dependencies and global information, while the transformer may not be as effective as CNNs in capturing local features and spatial information. To address these limitations, we construct a new LR network based on grid-based attention and multilevel feature fusion (GAMTNet). We complement CNNs by adding a transformer-based structure in a layer-by-layer fashion and improving methods for sequence generation and attention weight calculation. As a result, GAMTNet effectively learns global and local information about landslides across various spatial scales. We evaluated our model using landslide data collected from the southwest region of Jiuzhaigou County, Aba Tibetan, and Qiang Autonomous Prefecture, Sichuan Province, China. The results demonstrate that the proposed GAMTNet model achieves an F 1-score of 0.8951, a Kappa coefficient of 0.8807, and an MIoU of 0.8908, indicating its capability for the accurate landslide identification and its potential application in LR tasks.
滑坡识别（LR）是灾害预防和控制的一项基本任务。卷积神经网络（CNN）和变换器架构已被广泛用于提取滑坡信息。然而，卷积神经网络无法准确描述长距离依赖关系和全局信息，而变换器在捕捉局部特征和空间信息方面可能不如卷积神经网络有效。为了解决这些局限性，我们构建了一种基于网格关注和多级特征融合的新型 LR 网络（GAMTNet）。我们通过逐层添加基于变换器的结构，并改进序列生成和注意力权重计算方法，对 CNN 进行了补充。因此，GAMTNet 可有效学习不同空间尺度上滑坡的全局和局部信息。我们使用从中国四川省阿坝藏族羌族自治州九寨沟县西南地区收集到的滑坡数据对我们的模型进行了评估。结果表明，所提出的 GAMTNet 模型的 F1 分数为 0.8951，Kappa 系数为 0.8807，MIoU 为 0.8908，这表明该模型具有准确识别滑坡的能力，并有望应用于 LR 任务中。
{"title":"Joint Grid-Based Attention and Multilevel Feature Fusion for Landslide Recognition","authors":"Xinran Li;Tao Chen;Gang Liu;Jie Dou;Ruiqing Niu;Antonio Plaza","doi":"10.1109/JSTARS.2024.3491216","DOIUrl":"https://doi.org/10.1109/JSTARS.2024.3491216","url":null,"abstract":"Landslide recognition (LR) is a fundamental task for disaster prevention and control. Convolutional neural networks (CNNs) and transformer architectures have been widely used for extracting landslide information. However, CNNs cannot accurately characterize long-distance dependencies and global information, while the transformer may not be as effective as CNNs in capturing local features and spatial information. To address these limitations, we construct a new LR network based on grid-based attention and multilevel feature fusion (GAMTNet). We complement CNNs by adding a transformer-based structure in a layer-by-layer fashion and improving methods for sequence generation and attention weight calculation. As a result, GAMTNet effectively learns global and local information about landslides across various spatial scales. We evaluated our model using landslide data collected from the southwest region of Jiuzhaigou County, Aba Tibetan, and Qiang Autonomous Prefecture, Sichuan Province, China. The results demonstrate that the proposed GAMTNet model achieves an \u0000<italic>F</i>\u00001-score of 0.8951, a Kappa coefficient of 0.8807, and an MIoU of 0.8908, indicating its capability for the accurate landslide identification and its potential application in LR tasks.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"17 ","pages":"19911-19922"},"PeriodicalIF":4.7,"publicationDate":"2024-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10742385","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142713775","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 : 2024-11-04DOI: 10.1109/JSTARS.2024.3491221
Deyong Lu;Wei An;Haibo Wang;Qiang Ling;Dong Cao;Miao Li;Zaiping Lin
Infrared moving small target detection is an important and challenging task in infrared search and track system, especially in the case of low signal-to-clutter ratio (SCR) and complex scenes. The spatial–temporal information has not been fully utilized, and there is a serious imbalance in their exploitation, especially the lack of long-term temporal characteristics. In this article, a novel method based on the spatial–temporal feature fusion tensor model is proposed to solve these problems. By directly stacking raw infrared images, the sequence can be transformed into a third-order tensor, where the spatial–temporal features are not reduced or destroyed. Its horizontal and lateral slices can be viewed as 2-D images, showing the change of gray values of horizontal/vertical fixed spatial pixels over time. Then, a new tensor composed of several serial slices are decomposed into low-rank background components and sparse target components, which can make full use of the temporal similarity and spatial correlation of background. The partial tubal nuclear norm is introduced to constrain the low-rank background, and the tensor robust principal component analysis problem is solved quickly by the alternating direction method of multipliers. By superimposing all the decomposed sparse components into the target tensor, small target can be segmented from the reconstructed target image. Experimental results of synthetic and real data demonstrate that the proposed method is superior to other state-of-the-art methods in visual and numerical results for targets with different sizes, velocities, and SCR values under different complex backgrounds.
{"title":"Infrared Moving Small Target Detection Based on Spatial–Temporal Feature Fusion Tensor Model","authors":"Deyong Lu;Wei An;Haibo Wang;Qiang Ling;Dong Cao;Miao Li;Zaiping Lin","doi":"10.1109/JSTARS.2024.3491221","DOIUrl":"https://doi.org/10.1109/JSTARS.2024.3491221","url":null,"abstract":"Infrared moving small target detection is an important and challenging task in infrared search and track system, especially in the case of low signal-to-clutter ratio (SCR) and complex scenes. The spatial–temporal information has not been fully utilized, and there is a serious imbalance in their exploitation, especially the lack of long-term temporal characteristics. In this article, a novel method based on the spatial–temporal feature fusion tensor model is proposed to solve these problems. By directly stacking raw infrared images, the sequence can be transformed into a third-order tensor, where the spatial–temporal features are not reduced or destroyed. Its horizontal and lateral slices can be viewed as 2-D images, showing the change of gray values of horizontal/vertical fixed spatial pixels over time. Then, a new tensor composed of several serial slices are decomposed into low-rank background components and sparse target components, which can make full use of the temporal similarity and spatial correlation of background. The partial tubal nuclear norm is introduced to constrain the low-rank background, and the tensor robust principal component analysis problem is solved quickly by the alternating direction method of multipliers. By superimposing all the decomposed sparse components into the target tensor, small target can be segmented from the reconstructed target image. Experimental results of synthetic and real data demonstrate that the proposed method is superior to other state-of-the-art methods in visual and numerical results for targets with different sizes, velocities, and SCR values under different complex backgrounds.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"78-99"},"PeriodicalIF":4.7,"publicationDate":"2024-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10742415","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142713828","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 : 2024-11-01DOI: 10.1109/JSTARS.2024.3481444
Yan Zhou;Christopher Grassotti;Quanhua Liu;Shuyan Liu;Yong-Keun Lee
Total precipitable water (TPW) is defined as the vertically integrated column water vapor from the earth's surface to the top of the atmosphere. TPW is a key element of the hydrological cycle and is responsive to changes in global climate related to greenhouse-gas-induced warming. In this research, we focus on trend analysis using the TPW retrieval product from the recently reprocessed Microwave Integrated Retrieval System (MiRS) Suomi National Polar-Orbiting Partnership (SNPP) Advanced Technology Microwave Sounder (ATMS) data and compare it with ERA5 reanalysis. The primary results show that the global TPW trend during 2012–2021 from reprocessed SNPP ATMS is 0.46 mm/decade, in relatively good agreement with the trend from ERA5 of 0.39 mm/decade. Trends for tropical and mid-latitude subregions are also in good agreement, with essentially the same trend of 0.43 mm/decade seen in both datasets in the mid-latitudes. Both the datasets show a large positive anomaly associated with the strong El Nino event in 2015–2016, which increased TPW amounts in the tropics. We also found that the TPW trend is not uniformly distributed spatially, with significant regional variations in both sign and amplitude. Nevertheless, the spatial patterns from MiRS SNPP ATMS retrievals and ERA5 analyses are in very good agreement. Both the datasets show that positive TPW trends in terms of relative percentage in the polar regions were on par with those seen in lower latitudes. The results suggest that water vapor observations from a single polar-orbiting microwave instrument with only two local observation times daily may be sufficient to characterize trends in TPW.
{"title":"Evaluation of Total Precipitable Water Trends From Reprocessed MiRS SNPP ATMS Observations, 2012–2021","authors":"Yan Zhou;Christopher Grassotti;Quanhua Liu;Shuyan Liu;Yong-Keun Lee","doi":"10.1109/JSTARS.2024.3481444","DOIUrl":"https://doi.org/10.1109/JSTARS.2024.3481444","url":null,"abstract":"Total precipitable water (TPW) is defined as the vertically integrated column water vapor from the earth's surface to the top of the atmosphere. TPW is a key element of the hydrological cycle and is responsive to changes in global climate related to greenhouse-gas-induced warming. In this research, we focus on trend analysis using the TPW retrieval product from the recently reprocessed Microwave Integrated Retrieval System (MiRS) Suomi National Polar-Orbiting Partnership (SNPP) Advanced Technology Microwave Sounder (ATMS) data and compare it with ERA5 reanalysis. The primary results show that the global TPW trend during 2012–2021 from reprocessed SNPP ATMS is 0.46 mm/decade, in relatively good agreement with the trend from ERA5 of 0.39 mm/decade. Trends for tropical and mid-latitude subregions are also in good agreement, with essentially the same trend of 0.43 mm/decade seen in both datasets in the mid-latitudes. Both the datasets show a large positive anomaly associated with the strong El Nino event in 2015–2016, which increased TPW amounts in the tropics. We also found that the TPW trend is not uniformly distributed spatially, with significant regional variations in both sign and amplitude. Nevertheless, the spatial patterns from MiRS SNPP ATMS retrievals and ERA5 analyses are in very good agreement. Both the datasets show that positive TPW trends in terms of relative percentage in the polar regions were on par with those seen in lower latitudes. The results suggest that water vapor observations from a single polar-orbiting microwave instrument with only two local observation times daily may be sufficient to characterize trends in TPW.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"17 ","pages":"19798-19804"},"PeriodicalIF":4.7,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10740803","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142636568","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}
Extreme precipitation events greatly threaten people's daily lives and safety, making accurate and timely precipitation estimation especially critical. However, common methods like radar and satellite remote sensing have limitations due to coverage and environmental factors. Existing deep learning models struggle with complex scenarios and multisource data correlations. These make the precipitation estimation tasks challenging. This article proposes a Multiscale Dual Cross-Attention UNet (MS-DCA-UNet) model for near-real-time precipitation estimation. It integrates Doppler weather radar and FY-4A satellite data to overcome single-source data limitations. To narrow the semantic gap among the encoder feature maps, the MS-DCA-UNet model introduces a dual-cross attention (DCA) module at the skip connections of the backbone network U-Net. The DCA module mainly employs a channel cross-attention and a spatial cross-attention to capture remote dependencies and enable multiscale feature fusion. A multiscale convolution module is designed to reduce the risk of the model falling into local optima. It is a multibranch upsampling strategy that runs parallel to the decoder. Experimental results show that the Critical Success Index (CSI), Root Mean Square Error (RMSE), and Pearson's Correlation Coefficient (CC) of MS-DCA-UNet are 0.6033, 0.5949 mm/h, and 0.8460, respectively, with the hourly CMPAS precipitation as the benchmark. These outperform the other comparisons, such as FY-4A QPE, GPM IMERG, U-Net, Attention-UNet, and DCA-UNet on the CSI, RMSE, and CC metrics. MS-DCA-UNet reduces the RMSE of Attention-UNet, UNet, and DCA-UNet by a margin of 34.68% (0.5949 mm/h versus 0.9107 mm/h), 10.24% (0.5949 mm/h versus 0.6628 mm/h), 6.96% (0.5949 mm/h versus 0.6394 mm/h), respectively.
{"title":"Multiscale Attention-UNet-Based Near-Real-Time Precipitation Estimation From FY-4A/AGRI and Doppler Radar Observations","authors":"Dongling Wang;Shanmin Yang;Xiaojie Li;Jing Peng;Hongjiang Ma;Xi Wu","doi":"10.1109/JSTARS.2024.3488854","DOIUrl":"https://doi.org/10.1109/JSTARS.2024.3488854","url":null,"abstract":"Extreme precipitation events greatly threaten people's daily lives and safety, making accurate and timely precipitation estimation especially critical. However, common methods like radar and satellite remote sensing have limitations due to coverage and environmental factors. Existing deep learning models struggle with complex scenarios and multisource data correlations. These make the precipitation estimation tasks challenging. This article proposes a Multiscale Dual Cross-Attention UNet (MS-DCA-UNet) model for near-real-time precipitation estimation. It integrates Doppler weather radar and FY-4A satellite data to overcome single-source data limitations. To narrow the semantic gap among the encoder feature maps, the MS-DCA-UNet model introduces a dual-cross attention (DCA) module at the skip connections of the backbone network U-Net. The DCA module mainly employs a channel cross-attention and a spatial cross-attention to capture remote dependencies and enable multiscale feature fusion. A multiscale convolution module is designed to reduce the risk of the model falling into local optima. It is a multibranch upsampling strategy that runs parallel to the decoder. Experimental results show that the Critical Success Index (CSI), Root Mean Square Error (RMSE), and Pearson's Correlation Coefficient (CC) of MS-DCA-UNet are 0.6033, 0.5949 mm/h, and 0.8460, respectively, with the hourly CMPAS precipitation as the benchmark. These outperform the other comparisons, such as FY-4A QPE, GPM IMERG, U-Net, Attention-UNet, and DCA-UNet on the CSI, RMSE, and CC metrics. MS-DCA-UNet reduces the RMSE of Attention-UNet, UNet, and DCA-UNet by a margin of 34.68% (0.5949 mm/h versus 0.9107 mm/h), 10.24% (0.5949 mm/h versus 0.6628 mm/h), 6.96% (0.5949 mm/h versus 0.6394 mm/h), respectively.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"17 ","pages":"19998-20011"},"PeriodicalIF":4.7,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10740264","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142672121","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 : 2024-11-01DOI: 10.1109/JSTARS.2024.3490738
Jiayang Cao;Litao Li;Yonghua Jiang;Xin Shen;Deren Li;Meilin Tan
Image sharpness assesses detail visibility in remote-sensing images and measures sensors' details resolution capability. Sensor aging and environmental changes can degrade image sharpness and quality. The Gaofen (GF) satellites provide diverse remote-sensing imagery, but evaluations of their sharpness are limited. In this study, for the GF1/2/6/7 optical remote-sensing satellites in the space-based system of the China High-Resolution Earth Observation System (CHEOS) major special project, we evaluated the relative edge response (RER), full width at half maximum (FWHM), and modulation transfer function (MTF) of the images, using nearly ten years of ground target image data. This measures image sharpness and models how it changes over time with different sensors. Within ten years of on-orbit operation, the RER and MTF (@Nyquist frequency) of GF1/2 are 0.51 and 0.50, and 0.15 and 0.11, respectively. This indicated good image edge and high-frequency detail responsiveness, with FWHM of 1.16 and 1.17, respectively, showing a slight image sharpening. For GF6, the RER, MTF (@Nyquist frequency), and FWHM were 0.42, 0.09, and 1.39, indicating improved sharpening compared with GF1/2 but decreased edge and high-frequency detail response. The RER, MTF (@Nyquist frequency), and FWHM of the panchromatic images of GF7 were 0.32, 0.04, and 1.91, which indicate image blur. Meanwhile, the corresponding indicators for the multispectral images were 0.45, 0.14, and 1.40, better than the panchromatic images. Long-term data showed periodic sharpness variations in satellite images, with GF6s stability and minimal track differences being superior. The dynamic change pattern corresponds to a fourth-order polynomial model.
{"title":"Evaluation and Modeling of Image Sharpness of Chinese Gaofen-1/2/6/7 Optical Remote-Sensing Satellites Over Time","authors":"Jiayang Cao;Litao Li;Yonghua Jiang;Xin Shen;Deren Li;Meilin Tan","doi":"10.1109/JSTARS.2024.3490738","DOIUrl":"https://doi.org/10.1109/JSTARS.2024.3490738","url":null,"abstract":"Image sharpness assesses detail visibility in remote-sensing images and measures sensors' details resolution capability. Sensor aging and environmental changes can degrade image sharpness and quality. The Gaofen (GF) satellites provide diverse remote-sensing imagery, but evaluations of their sharpness are limited. In this study, for the GF1/2/6/7 optical remote-sensing satellites in the space-based system of the China High-Resolution Earth Observation System (CHEOS) major special project, we evaluated the relative edge response (RER), full width at half maximum (FWHM), and modulation transfer function (MTF) of the images, using nearly ten years of ground target image data. This measures image sharpness and models how it changes over time with different sensors. Within ten years of on-orbit operation, the RER and MTF (@Nyquist frequency) of GF1/2 are 0.51 and 0.50, and 0.15 and 0.11, respectively. This indicated good image edge and high-frequency detail responsiveness, with FWHM of 1.16 and 1.17, respectively, showing a slight image sharpening. For GF6, the RER, MTF (@Nyquist frequency), and FWHM were 0.42, 0.09, and 1.39, indicating improved sharpening compared with GF1/2 but decreased edge and high-frequency detail response. The RER, MTF (@Nyquist frequency), and FWHM of the panchromatic images of GF7 were 0.32, 0.04, and 1.91, which indicate image blur. Meanwhile, the corresponding indicators for the multispectral images were 0.45, 0.14, and 1.40, better than the panchromatic images. Long-term data showed periodic sharpness variations in satellite images, with GF6s stability and minimal track differences being superior. The dynamic change pattern corresponds to a fourth-order polynomial model.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"17 ","pages":"20150-20163"},"PeriodicalIF":4.7,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10741340","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142713776","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 : 2024-11-01DOI: 10.1109/JSTARS.2024.3490756
Chen Zuo;Haowei Zhang;Xin Ma;Wei Gong
On June 6, 2023, the Kakhovka Dam in Ukraine was damaged, causing a flood that could have had a significant impact on society. A single satellite may not provide sufficient data for timely disaster response. To overcome this, a combination of optical images, a new generation of hydrological monitoring satellite data, and nighttime light data were employed to analyze the disaster. Sentinel-3 provides useful hydrological information for quickly identifying and locating disaster areas, while surface water and ocean topography are able to detect changes in water surface elevation, providing a direct view of the flood's impact on the water area and surface elevation. The datasets both provide information about the extent of the flood area, which is more detailed than that provided by a single source. Furthermore, the NPP-VIIRS data not only reflects the indirect impact of the disaster on the lives and production of the local population, but also provides an intuitive assessment of the damage to the Zaporizhzhya nuclear power plant's power supply. The data showed that the disaster affected an area of about 8 km on either side of the river downstream of the dam. This enables the prediction of the damage and the postdisaster reconstruction strategy from a humanistic perspective. The combination of these three data types enables the specific impact of the disaster to be gauged in terms of its scope, extent, impact on human life, and the postdisaster recovery situation. This provides a scientific reference for the timely formulation and implementation of disaster relief and postdisaster reconstruction measures.
{"title":"Impact Assessment of Flood Events Based on Multisource Satellite Remote Sensing: The Case of Kahovka Dam","authors":"Chen Zuo;Haowei Zhang;Xin Ma;Wei Gong","doi":"10.1109/JSTARS.2024.3490756","DOIUrl":"https://doi.org/10.1109/JSTARS.2024.3490756","url":null,"abstract":"On June 6, 2023, the Kakhovka Dam in Ukraine was damaged, causing a flood that could have had a significant impact on society. A single satellite may not provide sufficient data for timely disaster response. To overcome this, a combination of optical images, a new generation of hydrological monitoring satellite data, and nighttime light data were employed to analyze the disaster. Sentinel-3 provides useful hydrological information for quickly identifying and locating disaster areas, while surface water and ocean topography are able to detect changes in water surface elevation, providing a direct view of the flood's impact on the water area and surface elevation. The datasets both provide information about the extent of the flood area, which is more detailed than that provided by a single source. Furthermore, the NPP-VIIRS data not only reflects the indirect impact of the disaster on the lives and production of the local population, but also provides an intuitive assessment of the damage to the Zaporizhzhya nuclear power plant's power supply. The data showed that the disaster affected an area of about 8 km on either side of the river downstream of the dam. This enables the prediction of the damage and the postdisaster reconstruction strategy from a humanistic perspective. The combination of these three data types enables the specific impact of the disaster to be gauged in terms of its scope, extent, impact on human life, and the postdisaster recovery situation. This provides a scientific reference for the timely formulation and implementation of disaster relief and postdisaster reconstruction measures.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"17 ","pages":"20164-20176"},"PeriodicalIF":4.7,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10741335","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142713777","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 : 2024-11-01DOI: 10.1109/JSTARS.2024.3490755
Zhiqi Zhang;Chuang Liu;Lu Wei;Shao Xiang
Pansharpening is the process of integrating two heterogeneous remote sensing images to obtain high-resolution multispectral images, which is crucial for downstream tasks. Existing methods utilizing advanced deep-learning techniques are able to achieve good sharpening results. However, the heterogeneity between diverse source images is not sufficiently considered, which in turn results in distortions in the sharpening results. Addressing this gap, we have developed a multibranch pyramid structure, which can build bridges between diverse source images at various scales. It contains three distinct branches, including the PAN branch, the MS branch, and the fusion branch, which efficiently and seamlessly integrates the data flow in distinct branches by means of the pyramid structure. Furthermore, in order to retain more advantageous information, we have developed a specialized adaptive extraction and integration module (AEIM) for each branch, namely, the texture shrinkage adaptive module for the PAN branch, the spectral information consistency module for the MS branch, and the adaptive fusion module for the fusion branch. These AEIMs are specifically designed to cater to diverse sources and distinct stages of the pansharpening process. The adaptive weights they generate can be used to extract and fuse more advantageous information. Ultimately, high-fidelity sharpening outcomes are obtained by minimizing the reconstruction errors at various scales in distinct branches. Extensive experiments show that our methodology surpasses that of representative advanced methods, while maintaining a high level of efficiency. All implementations will be published at MMAPP.
全景锐化是将两幅异质遥感图像整合以获得高分辨率多光谱图像的过程，这对下游任务至关重要。利用先进的深度学习技术的现有方法能够实现良好的锐化效果。然而，不同源图像之间的异质性没有得到充分考虑，这反过来又导致锐化结果失真。针对这一缺陷，我们开发了一种多分支金字塔结构，它可以在不同尺度的不同源图像之间建立桥梁。它包含三个不同的分支，包括 PAN 分支、MS 分支和融合分支，通过金字塔结构有效、无缝地整合了不同分支中的数据流。此外，为了保留更多有利信息，我们还为每个分支开发了专门的自适应提取和整合模块（AEIM），即 PAN 分支的纹理收缩自适应模块、MS 分支的光谱信息一致性模块和融合分支的自适应融合模块。这些 AEIM 专为满足不同来源和不同阶段的平差处理而设计。它们生成的自适应权重可用于提取和融合更有利的信息。最终，通过最小化不同分支中不同尺度的重建误差，获得高保真的锐化结果。广泛的实验表明，我们的方法超越了具有代表性的先进方法，同时保持了较高的效率。所有实施方案都将在 MMAPP 上发布。
{"title":"MMAPP: Multibranch and Multiscale Adaptive Progressive Pyramid Network for Multispectral Image Pansharpening","authors":"Zhiqi Zhang;Chuang Liu;Lu Wei;Shao Xiang","doi":"10.1109/JSTARS.2024.3490755","DOIUrl":"https://doi.org/10.1109/JSTARS.2024.3490755","url":null,"abstract":"Pansharpening is the process of integrating two heterogeneous remote sensing images to obtain high-resolution multispectral images, which is crucial for downstream tasks. Existing methods utilizing advanced deep-learning techniques are able to achieve good sharpening results. However, the heterogeneity between diverse source images is not sufficiently considered, which in turn results in distortions in the sharpening results. Addressing this gap, we have developed a multibranch pyramid structure, which can build bridges between diverse source images at various scales. It contains three distinct branches, including the PAN branch, the MS branch, and the fusion branch, which efficiently and seamlessly integrates the data flow in distinct branches by means of the pyramid structure. Furthermore, in order to retain more advantageous information, we have developed a specialized adaptive extraction and integration module (AEIM) for each branch, namely, the texture shrinkage adaptive module for the PAN branch, the spectral information consistency module for the MS branch, and the adaptive fusion module for the fusion branch. These AEIMs are specifically designed to cater to diverse sources and distinct stages of the pansharpening process. The adaptive weights they generate can be used to extract and fuse more advantageous information. Ultimately, high-fidelity sharpening outcomes are obtained by minimizing the reconstruction errors at various scales in distinct branches. Extensive experiments show that our methodology surpasses that of representative advanced methods, while maintaining a high level of efficiency. All implementations will be published at MMAPP.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"17 ","pages":"20129-20149"},"PeriodicalIF":4.7,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10741347","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142713774","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 : 2024-10-31DOI: 10.1109/JSTARS.2024.3483992
Caixia Liu;Huabing Huang;John M. Melack;Ye Tian;Jinxiong Jiang;Xiao Fu;Zhiguo Cao;Shaohua Wang
The grassland ecosystems of Xilingol, China, characteristically part of the vast Eurasian steppe, are currently facing two challenges: natural variations and anthropogenic stress, which are leading to significant degradation. This article harnesses a sequence of high-resolution (30 m) land cover and greenness trend maps derived from multiyear Landsat imagery to describe these ecologically critical shifts over a landscape spanning more than 200 000 km 2 . By leveraging random forest models complemented with phenological patterns, we streamlined the generation of land cover maps, securing overall accuracies upwards of 94% across eight categorical classifications, as substantiated by rigorous validation. Between 1985 and 2000, there were significant changes in the landscape, such as an increase in farmland of about 4.0 × 10 3 km 2 , mostly at the expense of natural grasslands and wetlands. Throughout the study period, an ongoing trend is the noticeable shrinkage of water bodies with the biggest reduction of wetlands reported between 1995 and 2015. Open-pit mining regions began to increase with the start of the 21st century, and from 1985 to the present, urbanization drove the growth of impervious surfaces. These maps offer powerful visual representations of major land use changes, capturing the expansion of surface mining, the retreat of wetland areas, and the growth of urban areas. Therefore, our findings compose an essential part in the documentation and comprehension of the details of wetland reduction, cropland intensification, surface water decline, and rapid urban growth, providing crucial information to conservationists and policymakers working toward sustainable ecosystem management.
{"title":"Assessing Land Degradation and Restoration in Eastern China Grasslands from 1985 to 2018 Using Multitemporal Landsat Data","authors":"Caixia Liu;Huabing Huang;John M. Melack;Ye Tian;Jinxiong Jiang;Xiao Fu;Zhiguo Cao;Shaohua Wang","doi":"10.1109/JSTARS.2024.3483992","DOIUrl":"https://doi.org/10.1109/JSTARS.2024.3483992","url":null,"abstract":"The grassland ecosystems of Xilingol, China, characteristically part of the vast Eurasian steppe, are currently facing two challenges: natural variations and anthropogenic stress, which are leading to significant degradation. This article harnesses a sequence of high-resolution (30 m) land cover and greenness trend maps derived from multiyear Landsat imagery to describe these ecologically critical shifts over a landscape spanning more than 200 000 km\u0000<sup>2</sup>\u0000. By leveraging random forest models complemented with phenological patterns, we streamlined the generation of land cover maps, securing overall accuracies upwards of 94% across eight categorical classifications, as substantiated by rigorous validation. Between 1985 and 2000, there were significant changes in the landscape, such as an increase in farmland of about 4.0 × 10\u0000<sup>3</sup>\u0000 km\u0000<sup>2</sup>\u0000, mostly at the expense of natural grasslands and wetlands. Throughout the study period, an ongoing trend is the noticeable shrinkage of water bodies with the biggest reduction of wetlands reported between 1995 and 2015. Open-pit mining regions began to increase with the start of the 21st century, and from 1985 to the present, urbanization drove the growth of impervious surfaces. These maps offer powerful visual representations of major land use changes, capturing the expansion of surface mining, the retreat of wetland areas, and the growth of urban areas. Therefore, our findings compose an essential part in the documentation and comprehension of the details of wetland reduction, cropland intensification, surface water decline, and rapid urban growth, providing crucial information to conservationists and policymakers working toward sustainable ecosystem management.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"17 ","pages":"19328-19342"},"PeriodicalIF":4.7,"publicationDate":"2024-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10740496","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142579179","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 : 2024-10-30DOI: 10.1109/JSTARS.2024.3488034
Wei Zhang;Miaoxin Cai;Tong Zhang;Guoqiang Lei;Yin Zhuang;Xuerui Mao
Ship detection needs to identify ship locations from remote sensing scenes. Due to different imaging payloads, various appearances of ships, and complicated background interference from the bird's eye view, it is difficult to setup a unified paradigm for achieving multisource ship detection. To address this challenge, in this article, leveraging the large language models powerful generalization ability, a unified visual-language model called Popeye is proposed for multisource ship detection from RS imagery. Specifically, to bridge the interpretation gap across the multisource images for ship detection, a novel unified labeling paradigm is designed to integrate different visual modalities and the various ship detection ways, i.e., horizontal bounding box and oriented bounding box. Subsequently, the hybrid experts encoder is designed to refine multiscale visual features, thereby enhancing visual perception. Then, a visual-language alignment method is developed for Popeye to enhance interactive comprehension ability between visual and language content. Furthermore, an instruction adaption mechanism is proposed for transferring the pretrained visual-language knowledge from the nature scene into the RS domain for multisource ship detection. In addition, the segment anything model is also seamlessly integrated into the proposed Popeye to achieve pixel-level ship segmentation without additional training costs. Finally, extensive experiments are conducted on the newly constructed ship instruction dataset named MMShip, and the results indicate that the proposed Popeye outperforms current specialist, open-vocabulary, and other visual-language models in zero-shot multisource various ship detection tasks.
{"title":"Popeye: A Unified Visual-Language Model for Multisource Ship Detection From Remote Sensing Imagery","authors":"Wei Zhang;Miaoxin Cai;Tong Zhang;Guoqiang Lei;Yin Zhuang;Xuerui Mao","doi":"10.1109/JSTARS.2024.3488034","DOIUrl":"https://doi.org/10.1109/JSTARS.2024.3488034","url":null,"abstract":"Ship detection needs to identify ship locations from remote sensing scenes. Due to different imaging payloads, various appearances of ships, and complicated background interference from the bird's eye view, it is difficult to setup a unified paradigm for achieving multisource ship detection. To address this challenge, in this article, leveraging the large language models powerful generalization ability, a unified visual-language model called Popeye is proposed for multisource ship detection from RS imagery. Specifically, to bridge the interpretation gap across the multisource images for ship detection, a novel unified labeling paradigm is designed to integrate different visual modalities and the various ship detection ways, i.e., horizontal bounding box and oriented bounding box. Subsequently, the hybrid experts encoder is designed to refine multiscale visual features, thereby enhancing visual perception. Then, a visual-language alignment method is developed for Popeye to enhance interactive comprehension ability between visual and language content. Furthermore, an instruction adaption mechanism is proposed for transferring the pretrained visual-language knowledge from the nature scene into the RS domain for multisource ship detection. In addition, the segment anything model is also seamlessly integrated into the proposed Popeye to achieve pixel-level ship segmentation without additional training costs. Finally, extensive experiments are conducted on the newly constructed ship instruction dataset named MMShip, and the results indicate that the proposed Popeye outperforms current specialist, open-vocabulary, and other visual-language models in zero-shot multisource various ship detection tasks.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"17 ","pages":"20050-20063"},"PeriodicalIF":4.7,"publicationDate":"2024-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10738390","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142645478","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：