Seismic exploration risk can be decreased by high-precision migration techniques. Imaging anisotropic multicomponent seismic data in areas with developed cracks and sedimentation is challenging. We introduce an efficient anisotropic wave separation elastic reverse time migration (RTM) to image anisotropic multicomponent seismic data in this letter. The elastic waves are decomposed into P- and S-waves for subsequent anisotropic wave separation elastic RTM (AWSERTM) to reduce crosstalk noise and improve imaging accuracy. In this new method, the pseudo-decoupled wave equations of transverse isotropic (TI) media with a vertical symmetry axis vertical transversely isotropic (VTI) are derived based on the decomposition of the anisotropic elastic stiffness parameters into anisotropic P- and S-wave stiffness parameters. Forward and backward anisotropic P- and S-waves can then be efficiently obtained by numerical solution of the pseudo-decoupled wave equations using the finite difference (FD) method. Combining the vector imaging condition, the high-quality AWSERTM’s results can be obtained. Synthetic examples from the modified HESS VTI model demonstrate the correctness and progressiveness of the proposed method.
高精度迁移技术可降低地震勘探风险。在裂缝发育和沉积地区对各向异性多分量地震数据进行成像具有挑战性。我们在这封信中介绍了一种高效的各向异性波分离弹性反向时间迁移（RTM）技术，用于对各向异性多分量地震数据成像。弹性波被分解成 P 波和 S 波，用于随后的各向异性波分离弹性反演（AWSERTM），以减少串扰噪声，提高成像精度。在这种新方法中，根据将各向异性弹性刚度参数分解为各向异性 P 波和 S 波刚度参数，推导出了具有垂直对称轴垂直横向各向同性（VTI）的横向各向同性（TI）介质的伪解耦波方程。然后，通过使用有限差分（FD）方法对伪解耦（pseudo-decoupled）波方程进行数值求解，可以有效地获得正向和反向各向异性 P 波和 S 波。结合矢量成像条件，可以获得高质量的 AWSERTM 结果。修改后的 HESS VTI 模型的合成示例证明了所提方法的正确性和渐进性。
{"title":"Anisotropic Wave Separation Elastic Reverse Time Migration Based on the Pseudo-Decoupled Wave Equations in VTI Media","authors":"Yu Zhong;Qinghui Mao;Yangting Liu;Mei He;Kun Zou;Kai Xu;Hanming Gu;Zeyun Shi;Haibo Huang;Yuan Zhou","doi":"10.1109/LGRS.2024.3494763","DOIUrl":"https://doi.org/10.1109/LGRS.2024.3494763","url":null,"abstract":"Seismic exploration risk can be decreased by high-precision migration techniques. Imaging anisotropic multicomponent seismic data in areas with developed cracks and sedimentation is challenging. We introduce an efficient anisotropic wave separation elastic reverse time migration (RTM) to image anisotropic multicomponent seismic data in this letter. The elastic waves are decomposed into P- and S-waves for subsequent anisotropic wave separation elastic RTM (AWSERTM) to reduce crosstalk noise and improve imaging accuracy. In this new method, the pseudo-decoupled wave equations of transverse isotropic (TI) media with a vertical symmetry axis vertical transversely isotropic (VTI) are derived based on the decomposition of the anisotropic elastic stiffness parameters into anisotropic P- and S-wave stiffness parameters. Forward and backward anisotropic P- and S-waves can then be efficiently obtained by numerical solution of the pseudo-decoupled wave equations using the finite difference (FD) method. Combining the vector imaging condition, the high-quality AWSERTM’s results can be obtained. Synthetic examples from the modified HESS VTI model demonstrate the correctness and progressiveness of the proposed method.","PeriodicalId":91017,"journal":{"name":"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society","volume":"21 ","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2024-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142650592","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-11DOI: 10.1109/LGRS.2024.3494815
Qian Wang;Jinming Shi;Jiachen Liu;Jiulun Fan
Aurora is the most visible manifestation of the sun’s effect on Earth. The ground-based all-sky imager (ASI) can observe a wealth of multiscale morphological features. Auroral image classification is an important tool for studying magnetospheric regimes and dynamic activities of aurora. Previous studies of automated auroral image classification focused more on auroral large-scale features across the entire image, ignoring small-scale auroral structures. In this letter, we introduce an object detection approach to investigate the small-scale features of auroral morphology. Since the small-scale auroral structures are nonrigid, morphologically diverse, and undefined boundaries, pixel-level labeling is labor-intensive and error-prone for human experts. Therefore, a weakly supervised object detection method for auroral vortexes is proposed in the absence of pixel-level annotations. We first perform global semantic identification and coarse localization using image-level labels as supervision. Considering the motion properties of vortexes, the global and local semantic information in a spatiotemporal volume is leveraged as semantic and location continuity constraints to generate high-confidence pseudo-labels. The experiments demonstrate that the proposed method can identify the vortexes more accurately. The method can retrieve small-scale auroral events in the aurora image dataset, allowing the study of the correlation of multiscale auroral events to be carried out.
{"title":"Weakly Supervised Vortex Detection for Studying Correlation Between Multiscale Auroral Events","authors":"Qian Wang;Jinming Shi;Jiachen Liu;Jiulun Fan","doi":"10.1109/LGRS.2024.3494815","DOIUrl":"https://doi.org/10.1109/LGRS.2024.3494815","url":null,"abstract":"Aurora is the most visible manifestation of the sun’s effect on Earth. The ground-based all-sky imager (ASI) can observe a wealth of multiscale morphological features. Auroral image classification is an important tool for studying magnetospheric regimes and dynamic activities of aurora. Previous studies of automated auroral image classification focused more on auroral large-scale features across the entire image, ignoring small-scale auroral structures. In this letter, we introduce an object detection approach to investigate the small-scale features of auroral morphology. Since the small-scale auroral structures are nonrigid, morphologically diverse, and undefined boundaries, pixel-level labeling is labor-intensive and error-prone for human experts. Therefore, a weakly supervised object detection method for auroral vortexes is proposed in the absence of pixel-level annotations. We first perform global semantic identification and coarse localization using image-level labels as supervision. Considering the motion properties of vortexes, the global and local semantic information in a spatiotemporal volume is leveraged as semantic and location continuity constraints to generate high-confidence pseudo-labels. The experiments demonstrate that the proposed method can identify the vortexes more accurately. The method can retrieve small-scale auroral events in the aurora image dataset, allowing the study of the correlation of multiscale auroral events to be carried out.","PeriodicalId":91017,"journal":{"name":"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society","volume":"22 ","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2024-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142691218","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-11DOI: 10.1109/LGRS.2024.3495043
Minghao Tong;Zhanchuan Cai;Mingwen Zhu
Mare Serenitatis (28°N, 17.5°E) has undergone intricate volcanic events, leading to the deposition of basaltic lava flows from various stages in the basin. This study presents prospective geological insights into the mare basalts within Mare Serenitatis by using data from the Chang’E-2 Lunar Microwave Sounder (CELMS), thereby aiding in enhancing comprehension of magma dynamics, thermal evolution, and volcanic activities. The following are the results obtained from this study: 1) the potential geological information in Mare Serenitatis was analyzed using brightness temperature (TB), identifying potential connections between deep-seated units within the basin; 2) the distribution and causes of TB anomalies in Mare Serenitatis were investigated, revealing that daytime hot anomalies mainly occur at its southern rim, with TiO2 abundance (TA) being the primary influencing factor. The nighttime cold anomalies appear near several craters and extend with depth; and 3) an untypical TB anomaly was observed in the central region of Mare Serenitatis, exhibiting lower TB at daytime and higher TB at nighttime. This study suggests the presence of a material with a lower loss tangent on the surface of the central region of Mare Serenitatis and suggests that this material is related to Mg-rich rock.
Mare Serenitatis（北纬28°，东经17.5°）经历了错综复杂的火山活动，导致盆地内不同阶段的玄武岩熔岩流沉积。本研究利用嫦娥二号月球微波探测仪（CELMS）提供的数据，提出了对半月母海区玄武岩的前瞻性地质见解，从而有助于加深对岩浆动力学、热演化和火山活动的理解。本研究取得了以下成果：1）利用亮度温度（TB）分析了半月海潜在的地质信息，确定了盆地内深层单元之间的潜在联系；2）研究了半月海亮度温度异常的分布和原因，发现白天的热异常主要出现在南缘，主要影响因素是二氧化钛丰度（TA）。夜间的冷异常出现在几个陨石坑附近，并随着深度的增加而扩展；以及 3）在塞雷尼塔蒂斯海中部地区观测到一种非典型的结核异常，表现为白天结核较低，夜间结核较高。这项研究表明，在海神庙海中部地区的表面存在一种损耗正切值较低的物质，并认为这种物质与富镁岩石有关。
{"title":"Potential Geological Information of Mare Basalts in Mare Serenitatis Using CELMS Data","authors":"Minghao Tong;Zhanchuan Cai;Mingwen Zhu","doi":"10.1109/LGRS.2024.3495043","DOIUrl":"https://doi.org/10.1109/LGRS.2024.3495043","url":null,"abstract":"Mare Serenitatis (28°N, 17.5°E) has undergone intricate volcanic events, leading to the deposition of basaltic lava flows from various stages in the basin. This study presents prospective geological insights into the mare basalts within Mare Serenitatis by using data from the Chang’E-2 Lunar Microwave Sounder (CELMS), thereby aiding in enhancing comprehension of magma dynamics, thermal evolution, and volcanic activities. The following are the results obtained from this study: 1) the potential geological information in Mare Serenitatis was analyzed using brightness temperature (TB), identifying potential connections between deep-seated units within the basin; 2) the distribution and causes of TB anomalies in Mare Serenitatis were investigated, revealing that daytime hot anomalies mainly occur at its southern rim, with TiO2 abundance (TA) being the primary influencing factor. The nighttime cold anomalies appear near several craters and extend with depth; and 3) an untypical TB anomaly was observed in the central region of Mare Serenitatis, exhibiting lower TB at daytime and higher TB at nighttime. This study suggests the presence of a material with a lower loss tangent on the surface of the central region of Mare Serenitatis and suggests that this material is related to Mg-rich rock.","PeriodicalId":91017,"journal":{"name":"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society","volume":"22 ","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2024-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142691738","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-11DOI: 10.1109/LGRS.2024.3495974
Vicky Feliren;Fithrothul Khikmah;Irfan Dwiki Bhaswara;Bahrul I. Nasution;Alex M. Lechner;Muhamad Risqi U. Saputra
In recent years, the integration of deep learning techniques with remote sensing technology has revolutionized the way natural hazards, such as floods, are monitored and managed. However, existing methods for flood segmentation using remote sensing data often overlook the utility of correlative features among multispectral satellite information. In this study, we introduce a progressive cross-attention network (ProCANet), a deep learning model that progressively applies both self- and cross-attention mechanisms to multispectral features, generating optimal feature combinations for flood segmentation. The proposed model was compared with state-of-the-art approaches using the Sen1Floods11 dataset and our bespoke flood data generated for the Citarum River basin, Indonesia. Our model demonstrated superior performance with the highest intersection over union (IoU) score of 0.815. Our results in this study, coupled with the ablation assessment comparing scenarios with and without attention across various modalities, open a promising path for enhancing the accuracy of flood analysis using remote sensing technology.
{"title":"Progressive Cross-Attention Network for Flood Segmentation Using Multispectral Satellite Imagery","authors":"Vicky Feliren;Fithrothul Khikmah;Irfan Dwiki Bhaswara;Bahrul I. Nasution;Alex M. Lechner;Muhamad Risqi U. Saputra","doi":"10.1109/LGRS.2024.3495974","DOIUrl":"https://doi.org/10.1109/LGRS.2024.3495974","url":null,"abstract":"In recent years, the integration of deep learning techniques with remote sensing technology has revolutionized the way natural hazards, such as floods, are monitored and managed. However, existing methods for flood segmentation using remote sensing data often overlook the utility of correlative features among multispectral satellite information. In this study, we introduce a progressive cross-attention network (ProCANet), a deep learning model that progressively applies both self- and cross-attention mechanisms to multispectral features, generating optimal feature combinations for flood segmentation. The proposed model was compared with state-of-the-art approaches using the Sen1Floods11 dataset and our bespoke flood data generated for the Citarum River basin, Indonesia. Our model demonstrated superior performance with the highest intersection over union (IoU) score of 0.815. Our results in this study, coupled with the ablation assessment comparing scenarios with and without attention across various modalities, open a promising path for enhancing the accuracy of flood analysis using remote sensing technology.","PeriodicalId":91017,"journal":{"name":"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society","volume":"22 ","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2024-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142761456","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-08DOI: 10.1109/LGRS.2024.3494543
Wenqian Zhou;Hanlin Wu;Pei Deng
Existing remote sensing (RS) image-text retrieval methods generally fall into two categories: dual-stream approaches and single-stream approaches. Dual-stream models are efficient but often lack sufficient interaction between visual and textual modalities, while single-stream models offer high accuracy but suffer from prolonged inference time. To pursue a tradeoff between efficiency and accuracy, we propose a novel coarse-to-fine image-text retrieval (CFITR) framework that integrates both dual-stream and single-stream architectures into a two-stage retrieval process. Our method begins with a dual-stream hashing module (DSHM) to perform coarse retrieval by leveraging precomputed hash codes for efficiency. In the subsequent fine retrieval stage, a single-stream module (SSM) refines these results using a joint transformer to improve accuracy through enhanced cross-modal interactions. We introduce a local feature enhancement module (LFEM) based on convolutions to capture detailed local features and a postprocessing similarity reranking (PPSR) algorithm that optimizes retrieval results without additional training. Extensive experiments on the RSICD and RSITMD datasets demonstrate that our CFITR framework significantly improves retrieval accuracy and supports real-time performance. Our code is publicly available at https://github.com/ZhWenQian/CFITR .
{"title":"Toward Efficient and Accurate Remote Sensing Image–Text Retrieval With a Coarse-to-Fine Approach","authors":"Wenqian Zhou;Hanlin Wu;Pei Deng","doi":"10.1109/LGRS.2024.3494543","DOIUrl":"https://doi.org/10.1109/LGRS.2024.3494543","url":null,"abstract":"Existing remote sensing (RS) image-text retrieval methods generally fall into two categories: dual-stream approaches and single-stream approaches. Dual-stream models are efficient but often lack sufficient interaction between visual and textual modalities, while single-stream models offer high accuracy but suffer from prolonged inference time. To pursue a tradeoff between efficiency and accuracy, we propose a novel coarse-to-fine image-text retrieval (CFITR) framework that integrates both dual-stream and single-stream architectures into a two-stage retrieval process. Our method begins with a dual-stream hashing module (DSHM) to perform coarse retrieval by leveraging precomputed hash codes for efficiency. In the subsequent fine retrieval stage, a single-stream module (SSM) refines these results using a joint transformer to improve accuracy through enhanced cross-modal interactions. We introduce a local feature enhancement module (LFEM) based on convolutions to capture detailed local features and a postprocessing similarity reranking (PPSR) algorithm that optimizes retrieval results without additional training. Extensive experiments on the RSICD and RSITMD datasets demonstrate that our CFITR framework significantly improves retrieval accuracy and supports real-time performance. Our code is publicly available at \u0000<uri>https://github.com/ZhWenQian/CFITR</uri>\u0000.","PeriodicalId":91017,"journal":{"name":"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society","volume":"22 ","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2024-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142691721","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-08DOI: 10.1109/LGRS.2024.3494739
Weichen Li;Jun Wang;Fang Li;Xiaohong Meng;Biao Xi
The presence of remanent magnetization introduces uncertainties in the processing and interpretation of magnetic data. In the literature, a variety of methods have been proposed to extract the intensity and direction of remanent magnetization. However, the existing methods still have some limitations, such as biases in results due to the use of inaccurate prior information and the complex computational process of extracting remanent magnetization information, especially from superimposed anomalies by multiple field sources. In this study, we develop an effective method to extract the intensity and direction of the remanent magnetization based on deep learning. We first use an improved U-Net as the backbone network to obtain the feature of spatial location and remanent magnetization parameters of anomalies and fuse the extracted multiscale feature information. At the same time, residual connections are added between the convolution layers to alleviate the loss of information and reduce gradient disappearance. The network, through continuous training, can directly learn the nonlinear mapping relationship between anomalies and the remanent magnetization intensity and direction, without the need for a prior information and complex calculations. Subsequently, we test the proposed method on synthetic examples and field data example in Yeshan region. All the outcomes demonstrate the capability in accurately extracting intensity and direction of remanent magnetization.
{"title":"Extraction of Remanent Magnetization Intensity and Direction Based on ResU-Net","authors":"Weichen Li;Jun Wang;Fang Li;Xiaohong Meng;Biao Xi","doi":"10.1109/LGRS.2024.3494739","DOIUrl":"https://doi.org/10.1109/LGRS.2024.3494739","url":null,"abstract":"The presence of remanent magnetization introduces uncertainties in the processing and interpretation of magnetic data. In the literature, a variety of methods have been proposed to extract the intensity and direction of remanent magnetization. However, the existing methods still have some limitations, such as biases in results due to the use of inaccurate prior information and the complex computational process of extracting remanent magnetization information, especially from superimposed anomalies by multiple field sources. In this study, we develop an effective method to extract the intensity and direction of the remanent magnetization based on deep learning. We first use an improved U-Net as the backbone network to obtain the feature of spatial location and remanent magnetization parameters of anomalies and fuse the extracted multiscale feature information. At the same time, residual connections are added between the convolution layers to alleviate the loss of information and reduce gradient disappearance. The network, through continuous training, can directly learn the nonlinear mapping relationship between anomalies and the remanent magnetization intensity and direction, without the need for a prior information and complex calculations. Subsequently, we test the proposed method on synthetic examples and field data example in Yeshan region. All the outcomes demonstrate the capability in accurately extracting intensity and direction of remanent magnetization.","PeriodicalId":91017,"journal":{"name":"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society","volume":"22 ","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2024-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142691216","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-08DOI: 10.1109/LGRS.2024.3494552
Shuxian Dong;Wei Feng;Yijun Long;Wenxing Bao;Ke Li;Gabriel Dauphin;Mengdao Xing;Yinghui Quan
In the hyperspectral image (HSI) classification, convolutional neural networks (CNNs)-based approaches often struggle with the scarcity of labeled samples. The letter proposes an HSI classification method based on data expansion and consistency regularization with small samples. Specifically, we leverage the pixel-pair feature (PPF) to expand the dataset, which facilitates the adequate tuning of CNN parameters and alleviates the issue of overfitting. In addition, a designed CNN structure is employed to extract discriminative features from the limited number of labeled PPFs and numerous unlabeled PPFs. The CNN is trained via minimizing the weighted sum of supervised and unsupervised losses, where the supervised loss is calculated through the cross-entropy function while the unsupervised loss is evaluated with the consistency regularization item. Moreover, reliable references required in the consistency regularization item are provided after making an exponential moving average (EMA) on the outputs of CNNs at different training epochs. Ultimately, we conduct experiments on three real HSI datasets, and the results show that the proposed approach gains superior classification accuracy compared to several existing CNN-based approaches.
{"title":"Hyperspectral Image Classification Method Based on Data Expansion and Consistency Regularization With Small Samples","authors":"Shuxian Dong;Wei Feng;Yijun Long;Wenxing Bao;Ke Li;Gabriel Dauphin;Mengdao Xing;Yinghui Quan","doi":"10.1109/LGRS.2024.3494552","DOIUrl":"https://doi.org/10.1109/LGRS.2024.3494552","url":null,"abstract":"In the hyperspectral image (HSI) classification, convolutional neural networks (CNNs)-based approaches often struggle with the scarcity of labeled samples. The letter proposes an HSI classification method based on data expansion and consistency regularization with small samples. Specifically, we leverage the pixel-pair feature (PPF) to expand the dataset, which facilitates the adequate tuning of CNN parameters and alleviates the issue of overfitting. In addition, a designed CNN structure is employed to extract discriminative features from the limited number of labeled PPFs and numerous unlabeled PPFs. The CNN is trained via minimizing the weighted sum of supervised and unsupervised losses, where the supervised loss is calculated through the cross-entropy function while the unsupervised loss is evaluated with the consistency regularization item. Moreover, reliable references required in the consistency regularization item are provided after making an exponential moving average (EMA) on the outputs of CNNs at different training epochs. Ultimately, we conduct experiments on three real HSI datasets, and the results show that the proposed approach gains superior classification accuracy compared to several existing CNN-based approaches.","PeriodicalId":91017,"journal":{"name":"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society","volume":"22 ","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2024-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142691650","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-07DOI: 10.1109/LGRS.2024.3493249
Zhen Zhang;Tao Peng;Liang Liao;Jing Xiao;Mi Wang
Vehicle detection and tracking in satellite video is essential in remote sensing (RS) applications. However, upon the statistical analysis of existing datasets, we find that the dim vehicles with low radiation intensity and limited contrast against the background are rarely annotated, which leads to the poor effect of existing approaches in detecting moving vehicles under low radiation conditions. In this letter, we address the challenge by building a small and dim moving cars (SDM-Car) dataset with a multitude of annotations for dim vehicles in satellite videos, which is collected by the Luojia 3–01 satellite and comprises 99 high-quality videos. Furthermore, we propose a method based on image enhancement and attention mechanisms to improve the detection accuracy of dim vehicles, serving as a benchmark for evaluating the dataset. Finally, we assess the performance of several representative methods on SDM-Car and present insightful findings. The dataset is openly available at https://github.com/TanedaM/SDM-Car .
{"title":"SDM-Car: A Dataset for Small and Dim Moving Vehicles Detection in Satellite Videos","authors":"Zhen Zhang;Tao Peng;Liang Liao;Jing Xiao;Mi Wang","doi":"10.1109/LGRS.2024.3493249","DOIUrl":"https://doi.org/10.1109/LGRS.2024.3493249","url":null,"abstract":"Vehicle detection and tracking in satellite video is essential in remote sensing (RS) applications. However, upon the statistical analysis of existing datasets, we find that the dim vehicles with low radiation intensity and limited contrast against the background are rarely annotated, which leads to the poor effect of existing approaches in detecting moving vehicles under low radiation conditions. In this letter, we address the challenge by building a small and dim moving cars (SDM-Car) dataset with a multitude of annotations for dim vehicles in satellite videos, which is collected by the Luojia 3–01 satellite and comprises 99 high-quality videos. Furthermore, we propose a method based on image enhancement and attention mechanisms to improve the detection accuracy of dim vehicles, serving as a benchmark for evaluating the dataset. Finally, we assess the performance of several representative methods on SDM-Car and present insightful findings. The dataset is openly available at \u0000<uri>https://github.com/TanedaM/SDM-Car</uri>\u0000.","PeriodicalId":91017,"journal":{"name":"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society","volume":"21 ","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2024-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142713818","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-07DOI: 10.1109/LGRS.2024.3491108
Shuo Ma;Teng Li;Shuangshuang Zhai
With the maneuverability and flexibility of UAVs, UAV-based remote sensing images have been widely applied for urban monitoring of infrastructure, such as buildings, bridges, dams, and so on. However, with the increasing amount of data collected by UAVs, challenges arise in contour segmentation tasks due to the large data volume, high resolution of remote sensing images, inconsistent building shapes, and imbalanced distribution of building and background pixels. To address these challenges, this letter proposes a deep learning method for infrastructure contour segmentation based on adaptive hidden-layer feature fusion. It introduces an adaptive layer selection and fusion network (ALSFN), consisting of an encoder network, an adaptive layer selection mechanism (ALSM), and a decoder network. Furthermore, this letter proposes a composite loss function that includes the evaluation of the boundary and the Tversky index to train the proposed neural network. Validation experiments conducted on real UAV remote sensing datasets show that the proposed method achieves high accuracy and reliability for infrastructure contour segmentation tasks.
{"title":"Adaptive Layer Selection and Fusion Network for Infrastructure Contour Segmentation Using UAV Remote Sensing Images","authors":"Shuo Ma;Teng Li;Shuangshuang Zhai","doi":"10.1109/LGRS.2024.3491108","DOIUrl":"https://doi.org/10.1109/LGRS.2024.3491108","url":null,"abstract":"With the maneuverability and flexibility of UAVs, UAV-based remote sensing images have been widely applied for urban monitoring of infrastructure, such as buildings, bridges, dams, and so on. However, with the increasing amount of data collected by UAVs, challenges arise in contour segmentation tasks due to the large data volume, high resolution of remote sensing images, inconsistent building shapes, and imbalanced distribution of building and background pixels. To address these challenges, this letter proposes a deep learning method for infrastructure contour segmentation based on adaptive hidden-layer feature fusion. It introduces an adaptive layer selection and fusion network (ALSFN), consisting of an encoder network, an adaptive layer selection mechanism (ALSM), and a decoder network. Furthermore, this letter proposes a composite loss function that includes the evaluation of the boundary and the Tversky index to train the proposed neural network. Validation experiments conducted on real UAV remote sensing datasets show that the proposed method achieves high accuracy and reliability for infrastructure contour segmentation tasks.","PeriodicalId":91017,"journal":{"name":"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society","volume":"22 ","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2024-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142691664","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The multireceiver synthetic aperture sonar (SAS) data are usually converted to equivalent monostatic data through the displaced phase center approximation (DPCA) before the monostatic imaging. However, the DPCA error is azimuth-variant in the wide-beam case, resulting in the traditional algorithms compensating for the DPCA error in the extended Doppler domain of each receiver, which obviously increases the computational complexity. To solve the problem, this letter analyzes the space-variant characteristics of the DPCA error and discovers that the DPCA error exhibits significant receiver-variant and weak azimuth-variant characteristics. Based on this, a subaperture preprocessing is proposed to reduce computational complexity without sacrificing imaging accuracy. The proposed algorithm compensates for the DPCA error uniformly within the subaperture using the DPCA error at the center of the subaperture and then superposes all subapertures coherently to obtain equivalent monostatic data. The weak azimuth-variant characteristic ensures that the subapertures are very sparse, Additionally, the algorithm allows data recording and preprocessing to be synchronized, significantly reducing the imaging waiting time further. The simulated data and actual data experiments verify the effectiveness of the proposed algorithm.
{"title":"A Real-Time Subaperture Preprocessing for Multireceiver Wide-Beam SAS Imaging","authors":"Jiafeng Zhang;Guangli Cheng;Jinsong Tang;Haoran Wu","doi":"10.1109/LGRS.2024.3493097","DOIUrl":"https://doi.org/10.1109/LGRS.2024.3493097","url":null,"abstract":"The multireceiver synthetic aperture sonar (SAS) data are usually converted to equivalent monostatic data through the displaced phase center approximation (DPCA) before the monostatic imaging. However, the DPCA error is azimuth-variant in the wide-beam case, resulting in the traditional algorithms compensating for the DPCA error in the extended Doppler domain of each receiver, which obviously increases the computational complexity. To solve the problem, this letter analyzes the space-variant characteristics of the DPCA error and discovers that the DPCA error exhibits significant receiver-variant and weak azimuth-variant characteristics. Based on this, a subaperture preprocessing is proposed to reduce computational complexity without sacrificing imaging accuracy. The proposed algorithm compensates for the DPCA error uniformly within the subaperture using the DPCA error at the center of the subaperture and then superposes all subapertures coherently to obtain equivalent monostatic data. The weak azimuth-variant characteristic ensures that the subapertures are very sparse, Additionally, the algorithm allows data recording and preprocessing to be synchronized, significantly reducing the imaging waiting time further. The simulated data and actual data experiments verify the effectiveness of the proposed algorithm.","PeriodicalId":91017,"journal":{"name":"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society","volume":"22 ","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2024-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142761438","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","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：