Pub Date : 2024-10-11DOI: 10.1109/JSTARS.2024.3478848
Qingjiang Xiao;Liaoying Zhao;Shuhan Chen;Xiaorun Li
In recent years, tensor representation-based approaches have been widely studied in hyperspectral anomaly detection. However, these methods still suffer from two key issues. First, the various complex regularizations imposed on the background components increase the cost of selecting the best regularized parameters and fail to maximize the effectiveness between these prior regularizations. Second, most of them tend to utilize multiple prior knowledge to describe background components, but show obvious deficiencies in mining prior information of abnormal components. To address these two problems simultaneously, we propose an enhanced low-rank and smoothness fusion regularization plus saliency prior (ELRSF-SP) approach. To be specific, for the first problem, we design a weighted tensor-correlated total variation (wt-CTV) to simultaneously characterize the low-rank and smoothness properties of the background tensor. The wt-CTV avoids an additional regularization parameter to balance the two prior regularizations and fully considers the prior distribution information of the singular values of the gradient tensor, thereby improving the ability and flexibility to cope with practical problems. For the second problem, we construct a saliency weight tensor as a constraint of the anomaly tensor to improve the contrast between abnormal pixels and the background. Meanwhile, the tensor $ell _{1}$ -norm is introduced in ELRSF-SP to characterize the sparsity of the anomaly tensor. Finally, for the optimization of ELRSF-SP, an effective algorithm based on the alternating direction method of multipliers is derived. Extensive experiments demonstrate the effectiveness of the ELRSF-SP approach.
{"title":"Hyperspectral Anomaly Detection via Enhanced Low-Rank and Smoothness Fusion Regularization Plus Saliency Prior","authors":"Qingjiang Xiao;Liaoying Zhao;Shuhan Chen;Xiaorun Li","doi":"10.1109/JSTARS.2024.3478848","DOIUrl":"https://doi.org/10.1109/JSTARS.2024.3478848","url":null,"abstract":"In recent years, tensor representation-based approaches have been widely studied in hyperspectral anomaly detection. However, these methods still suffer from two key issues. First, the various complex regularizations imposed on the background components increase the cost of selecting the best regularized parameters and fail to maximize the effectiveness between these prior regularizations. Second, most of them tend to utilize multiple prior knowledge to describe background components, but show obvious deficiencies in mining prior information of abnormal components. To address these two problems simultaneously, we propose an enhanced low-rank and smoothness fusion regularization plus saliency prior (ELRSF-SP) approach. To be specific, for the first problem, we design a weighted tensor-correlated total variation (wt-CTV) to simultaneously characterize the low-rank and smoothness properties of the background tensor. The wt-CTV avoids an additional regularization parameter to balance the two prior regularizations and fully considers the prior distribution information of the singular values of the gradient tensor, thereby improving the ability and flexibility to cope with practical problems. For the second problem, we construct a saliency weight tensor as a constraint of the anomaly tensor to improve the contrast between abnormal pixels and the background. Meanwhile, the tensor \u0000<inline-formula><tex-math>$ell _{1}$</tex-math></inline-formula>\u0000-norm is introduced in ELRSF-SP to characterize the sparsity of the anomaly tensor. Finally, for the optimization of ELRSF-SP, an effective algorithm based on the alternating direction method of multipliers is derived. Extensive experiments demonstrate the effectiveness of the ELRSF-SP approach.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"17 ","pages":"18987-19002"},"PeriodicalIF":4.7,"publicationDate":"2024-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10714010","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142524233","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}
Pine wilt disease (PWD) is a severe and highly contagious forest disease that poses a significant challenge to sustainable development. This study utilizes autonomous aerial vehicle (AAV) remote sensing and RGB images while combining deep learning techniques to address the challenge of detecting infected trees. The proposed You Only Look Once (YOLO)-PWD model integrates the squeeze-and-excitation network and convolutional block attention module to improve feature extraction capabilities. In addition, the integration of a bidirectional feature pyramid network enhances the capture of global scene information and adapts to complex environmental variations. We further enhance the detection accuracy by incorporating a dynamic convolutional kernel, ensuring the system's suitability for deployment on edge devices such as AAVs. Compared with the original YOLOv5s model, YOLO-PWD demonstrates a significant improvement in recall rate, with an increase of 14.2%, and achieves an impressive average precision (AP) of 95.2% for detecting discolored pine trees. The precision, recall, and AP for dead pine trees are also enhanced, with precision increasing by 9.7% and AP by 6.7%. Despite a mere 0.9MB increase in model size, the F1-score for discolored pine trees was improved by 4.1%, and the F1-score for dead pine trees increased by 3.3%. Experimental results suggest that the YOLO-PWD model can better meet the requirements of PWD detection by AAV remote sensing in large epidemic areas. This advancement has significant implications for the protection of pine forest resources and contributes to environmentally sustainable development.
{"title":"Detection of Pine Wilt Disease Using AAV Remote Sensing With an Improved YOLO Model","authors":"Lina Wang;Jijing Cai;Tingting Wang;Jiayi Zhao;Thippa Reddy Gadekallu;Kai Fang","doi":"10.1109/JSTARS.2024.3478333","DOIUrl":"https://doi.org/10.1109/JSTARS.2024.3478333","url":null,"abstract":"Pine wilt disease (PWD) is a severe and highly contagious forest disease that poses a significant challenge to sustainable development. This study utilizes autonomous aerial vehicle (AAV) remote sensing and RGB images while combining deep learning techniques to address the challenge of detecting infected trees. The proposed You Only Look Once (YOLO)-PWD model integrates the squeeze-and-excitation network and convolutional block attention module to improve feature extraction capabilities. In addition, the integration of a bidirectional feature pyramid network enhances the capture of global scene information and adapts to complex environmental variations. We further enhance the detection accuracy by incorporating a dynamic convolutional kernel, ensuring the system's suitability for deployment on edge devices such as AAVs. Compared with the original YOLOv5s model, YOLO-PWD demonstrates a significant improvement in recall rate, with an increase of 14.2%, and achieves an impressive average precision (AP) of 95.2% for detecting discolored pine trees. The precision, recall, and AP for dead pine trees are also enhanced, with precision increasing by 9.7% and AP by 6.7%. Despite a mere 0.9MB increase in model size, the F1-score for discolored pine trees was improved by 4.1%, and the F1-score for dead pine trees increased by 3.3%. Experimental results suggest that the YOLO-PWD model can better meet the requirements of PWD detection by AAV remote sensing in large epidemic areas. This advancement has significant implications for the protection of pine forest resources and contributes to environmentally sustainable development.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"17 ","pages":"19230-19242"},"PeriodicalIF":4.7,"publicationDate":"2024-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10714013","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142555112","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 : 2024-10-11DOI: 10.1109/JSTARS.2024.3479224
Sihao Luo;Li Ma;Xiaoquan Yang;Qian Du
We propose a novel multilevel unsupervised domain adaptive framework for single-stage object detection in remote sensing images. Our framework combines pixel-level adaptation together with feature-level adaptation in a progressive learning scheme. Pixel-level adaptation usually suffers from the imperfect translation problem with respect to local region deformation. To address this problem, we introduce a semantically important region-attentive pixel-level domain adaptation based on a cycleGAN-like translation design, which incorporates an attention module and a learnable normalization function to facilitate shape transformation and image style transfer across domains. Moreover, to adapt single-stage detector while removing the need for explicit local features, we introduce the attention-guided multiscale feature-level domain adaptation, which employs multiple domain discriminators at different scales to perform multiscale feature alignment for objects of different sizes. This alignment process is guided from global to local by exploiting a self-attention mechanism that allows the model to gradually recognize local regions. The experimental results on several remote sensing datasets demonstrate the validity of our proposed framework. Compared with the baseline detector trained on the source dataset, our approach consistently improves the detection performance on the target dataset by 9.1%–16.0% mAP and achieves state-of-the-art results under various datasets.
{"title":"Multilevel Unsupervised Domain Adaptation for Single-Stage Object Detection in Remote Sensing Images","authors":"Sihao Luo;Li Ma;Xiaoquan Yang;Qian Du","doi":"10.1109/JSTARS.2024.3479224","DOIUrl":"https://doi.org/10.1109/JSTARS.2024.3479224","url":null,"abstract":"We propose a novel multilevel unsupervised domain adaptive framework for single-stage object detection in remote sensing images. Our framework combines pixel-level adaptation together with feature-level adaptation in a progressive learning scheme. Pixel-level adaptation usually suffers from the imperfect translation problem with respect to local region deformation. To address this problem, we introduce a semantically important region-attentive pixel-level domain adaptation based on a cycleGAN-like translation design, which incorporates an attention module and a learnable normalization function to facilitate shape transformation and image style transfer across domains. Moreover, to adapt single-stage detector while removing the need for explicit local features, we introduce the attention-guided multiscale feature-level domain adaptation, which employs multiple domain discriminators at different scales to perform multiscale feature alignment for objects of different sizes. This alignment process is guided from global to local by exploiting a self-attention mechanism that allows the model to gradually recognize local regions. The experimental results on several remote sensing datasets demonstrate the validity of our proposed framework. Compared with the baseline detector trained on the source dataset, our approach consistently improves the detection performance on the target dataset by 9.1%–16.0% mAP and achieves state-of-the-art results under various datasets.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"17 ","pages":"19420-19435"},"PeriodicalIF":4.7,"publicationDate":"2024-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10715498","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142579104","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}
Conventional ship detection using synthetic aperture radar (SAR) is typically limited to fully-focused SAR images, limiting the development of real-time SAR ship detection. Ship detection in the SAR range-compressed domain holds significant real-time potential as it obviates the need for complete imaging and reduces data transmission. However, range-compressed data are solely compressed in range, resulting in a defocused representation in azimuth, which differs from SAR images. The previously proposed methods often fail to effectively incorporate the characteristics of range-compressed domain. In light of this circumstance, we propose an SAR ship detection network, YOLO-range compressed (YOLO-RC), which utilizes amplitude gradient and geometric scale characteristics in the range-compressed domain for improved performance. In YOLO-RC, amplitude gradient guided feature extraction module is specifically designed to leverage the different gradient variation trends of ship in both the range and azimuth dimensions. Moreover, we incorporate a large receptive field pyramid head, employing a pyramid-like structure to enhance receptive field and achieve more precise fitting of ship geometry for improved detection capability. Considering the scarcity of range-compressed ship samples, we conduct experiments using a publicly available self-built dataset. Experimental results on the dataset demonstrate that the proposed network achieves an F 1 -score of 83.78% and an average precision of 84.09%, outperforming most existing SAR ship detection methods with better detection capability in SAR range-compressed domain.
传统的合成孔径雷达（SAR）船舶探测通常仅限于全聚焦 SAR 图像，限制了实时 SAR 船舶探测的发展。合成孔径雷达测距压缩域的船舶探测具有巨大的实时潜力，因为它无需完整成像，并减少了数据传输。然而，测距压缩数据仅在测距范围内进行压缩，导致方位角表示失焦，这与合成孔径雷达图像不同。以前提出的方法往往不能有效地结合测距压缩域的特点。有鉴于此，我们提出了一种合成孔径雷达舰船检测网络--YOLO-range compressed（YOLO-RC），它利用了测距压缩域中的振幅梯度和几何尺度特性来提高性能。在 YOLO-RC 中，专门设计了振幅梯度引导特征提取模块，以利用船舶在测距和方位维度上的不同梯度变化趋势。此外，我们还加入了一个大型感受野金字塔头，采用类似金字塔的结构来增强感受野，实现更精确的船舶几何拟合，从而提高探测能力。考虑到范围压缩船舶样本的稀缺性，我们使用公开的自建数据集进行了实验。在该数据集上的实验结果表明，所提出的网络的 F1 分数达到 83.78%，平均精度达到 84.09%，优于大多数现有的 SAR 船舶检测方法，在 SAR 范围压缩域中具有更强的检测能力。
{"title":"YOLO-RC: SAR Ship Detection Guided by Characteristics of Range-Compressed Domain","authors":"Xiangdong Tan;Xiangguang Leng;Ru Luo;Zhongzhen Sun;Kefeng Ji;Gangyao Kuang","doi":"10.1109/JSTARS.2024.3478390","DOIUrl":"https://doi.org/10.1109/JSTARS.2024.3478390","url":null,"abstract":"Conventional ship detection using synthetic aperture radar (SAR) is typically limited to fully-focused SAR images, limiting the development of real-time SAR ship detection. Ship detection in the SAR range-compressed domain holds significant real-time potential as it obviates the need for complete imaging and reduces data transmission. However, range-compressed data are solely compressed in range, resulting in a defocused representation in azimuth, which differs from SAR images. The previously proposed methods often fail to effectively incorporate the characteristics of range-compressed domain. In light of this circumstance, we propose an SAR ship detection network, YOLO-range compressed (YOLO-RC), which utilizes amplitude gradient and geometric scale characteristics in the range-compressed domain for improved performance. In YOLO-RC, amplitude gradient guided feature extraction module is specifically designed to leverage the different gradient variation trends of ship in both the range and azimuth dimensions. Moreover, we incorporate a large receptive field pyramid head, employing a pyramid-like structure to enhance receptive field and achieve more precise fitting of ship geometry for improved detection capability. Considering the scarcity of range-compressed ship samples, we conduct experiments using a publicly available self-built dataset. Experimental results on the dataset demonstrate that the proposed network achieves an F\u0000<sub>1</sub>\u0000-score of 83.78% and an average precision of 84.09%, outperforming most existing SAR ship detection methods with better detection capability in SAR range-compressed domain.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"17 ","pages":"18834-18851"},"PeriodicalIF":4.7,"publicationDate":"2024-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10713968","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142524239","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}
Low-frequency ultrawideband synthetic aperture radar (UWB SAR) has high-resolution imaging and foliage-penetrating ability, which can detect the foliage-concealed target. However, due to the jungle detection environment and the low-frequency UWB SAR characteristics, there are often some nontarget strong scattering points in low-frequency UWB SAR images, which may increase the difficulty of foliage-concealed target change detection. To improve the change detection rate of the foliage-concealed target, a foliage-concealed target change detection strategy based on image stacks in low-frequency UWB SAR images is proposed. In image preprocessing, a relative radiometric correction method based on the bidirectional linear regression model is presented, which can eliminate the low-frequency UWB SAR image changes caused by nontarget factors. Besides, in change detection processing, multiple difference images are first obtained by subtracting the image to be detected from multiple reference images. Then, the Gaussian probability density function is used to model the distribution of the amplitude of these difference images. Finally, the generalized likelihood ratio test is used for target change detection, which effectively suppresses the interference, such as tree trunk clutter. Experimental results tested on the CARABAS-II SAR dataset demonstrate the correctness and effectiveness of the proposed strategy, which can improve the change detection probability of the foliage-concealed target with the lower false alarm rate.
低频超宽带合成孔径雷达（UWB SAR）具有高分辨率成像和穿透落叶能力，可以探测到隐藏在落叶中的目标。然而，由于丛林探测环境和低频 UWB SAR 特性，低频 UWB SAR 图像中往往存在一些非目标强散射点，这可能会增加叶面隐蔽目标变化探测的难度。为了提高叶面隐藏目标的变化检测率，本文提出了一种基于低频 UWB SAR 图像中图像堆栈的叶面隐藏目标变化检测策略。在图像预处理中，提出了一种基于双向线性回归模型的相对辐射校正方法，该方法可以消除由非目标因素引起的低频 UWB SAR 图像变化。此外，在变化检测处理中，首先要从多幅参考图像中减去待检测图像，得到多幅差分图像。然后，使用高斯概率密度函数对这些差分图像的振幅分布进行建模。最后，利用广义似然比检验进行目标变化检测，从而有效抑制树干杂波等干扰。在 CARABAS-II SAR 数据集上测试的实验结果表明了所提策略的正确性和有效性，它可以提高树叶遮挡目标的变化检测概率，并降低误报率。
{"title":"Low-Frequency Ultrawideband Synthetic Aperture Radar Foliage-Concealed Target Change Detection Strategy Based on Image Stacks","authors":"Hongtu Xie;Shiliang Yi;Jinfeng He;Yuanjie Zhang;Zheng Lu;Nannan Zhu","doi":"10.1109/JSTARS.2024.3477602","DOIUrl":"https://doi.org/10.1109/JSTARS.2024.3477602","url":null,"abstract":"Low-frequency ultrawideband synthetic aperture radar (UWB SAR) has high-resolution imaging and foliage-penetrating ability, which can detect the foliage-concealed target. However, due to the jungle detection environment and the low-frequency UWB SAR characteristics, there are often some nontarget strong scattering points in low-frequency UWB SAR images, which may increase the difficulty of foliage-concealed target change detection. To improve the change detection rate of the foliage-concealed target, a foliage-concealed target change detection strategy based on image stacks in low-frequency UWB SAR images is proposed. In image preprocessing, a relative radiometric correction method based on the bidirectional linear regression model is presented, which can eliminate the low-frequency UWB SAR image changes caused by nontarget factors. Besides, in change detection processing, multiple difference images are first obtained by subtracting the image to be detected from multiple reference images. Then, the Gaussian probability density function is used to model the distribution of the amplitude of these difference images. Finally, the generalized likelihood ratio test is used for target change detection, which effectively suppresses the interference, such as tree trunk clutter. Experimental results tested on the CARABAS-II SAR dataset demonstrate the correctness and effectiveness of the proposed strategy, which can improve the change detection probability of the foliage-concealed target with the lower false alarm rate.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"17 ","pages":"19817-19830"},"PeriodicalIF":4.7,"publicationDate":"2024-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10713238","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142636549","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 : 2024-10-10DOI: 10.1109/JSTARS.2024.3477606
Ryuhei Hamaguchi;Aito Fujita;Keisuke Nemoto
This article presents a novel convolutional neural network (CNN) architecture for segmenting significantly small and crowded objects in remote sensing imagery. Although such small objects are characteristic in the remote sensing domain, the previous works mostly follow the state-of-the-art CNN models designed for ground-based images and have yet to fully explore the method for segmenting the small objects. To this end, we propose a network with no downsampling layers by utilizing dilated convolutions. We find that naive use of dilated convolutions with “increasing” dilation rates fails to capture local relationships among neighboring features, resulting in grid-like noise in the prediction. To alleviate this problem, we propose a novel scheme of “increasing-decreasing” dilation rates. Specifically, we propose a network module with decreasing dilation rates and attach it to the dilated backbone to reconnect the neighboring pixels of the backbone features. In the experiments, we evaluated the proposed model on six remote sensing datasets, where the model showed remarkably high performance, especially for small objects.
{"title":"Small Object Segmentation Using Dilated Convolutions With Increasing-Decreasing Dilation","authors":"Ryuhei Hamaguchi;Aito Fujita;Keisuke Nemoto","doi":"10.1109/JSTARS.2024.3477606","DOIUrl":"https://doi.org/10.1109/JSTARS.2024.3477606","url":null,"abstract":"This article presents a novel convolutional neural network (CNN) architecture for segmenting significantly small and crowded objects in remote sensing imagery. Although such small objects are characteristic in the remote sensing domain, the previous works mostly follow the state-of-the-art CNN models designed for ground-based images and have yet to fully explore the method for segmenting the small objects. To this end, we propose a network with no downsampling layers by utilizing dilated convolutions. We find that naive use of dilated convolutions with “increasing” dilation rates fails to capture local relationships among neighboring features, resulting in grid-like noise in the prediction. To alleviate this problem, we propose a novel scheme of “increasing-decreasing” dilation rates. Specifically, we propose a network module with decreasing dilation rates and attach it to the dilated backbone to reconnect the neighboring pixels of the backbone features. In the experiments, we evaluated the proposed model on six remote sensing datasets, where the model showed remarkably high performance, especially for small objects.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"17 ","pages":"19016-19034"},"PeriodicalIF":4.7,"publicationDate":"2024-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10713922","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142524087","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 : 2024-10-10DOI: 10.1109/JSTARS.2024.3476029
Brandon Voelker;Pietro Milillo;Amin Tavakkoliestahbanati;Valentina Macchiarulo;Giorgia Giardina;Michael Recla;Michael Schmitt;Marzia Cescon;Yasemin D. Aktas;Emily So
Accurate and rapid postearthquake structural damage assessment is of vital importance for humanitarian relief. Remote sensing techniques have the potential to map large areas with reduced data latency but are limited by several factors, including accuracy (compared to in-situ monitoring campaigns) and data acquisition frequency. Current damage assessment techniques relying on remote sensing data enable rapid assessment in situations where on-site reconnaissance is not possible or desirable. Yet, these techniques rely on different scales, measurement methods, and spatial resolutions, making it difficult to assimilate many different damage products in a homogeneous damage map. Here, we present the results of the U.K.’s Earthquake Engineering Field Investigation Team's remote-sensing-based reconnaissance mission, which was carried out in the aftermath of the series of earthquakes that struck Turkey and Syria in February 2023. We use a set of publicly available damage maps based on synthetic aperture radar, optical imaging, and ground-based reports as well as in-house developed damage products and assess their relative accuracies. We describe the process of supporting on-site reconnaissance planning by creating maps that describe the building stock and diversity of damage in southeast Turkey to assist field survey teams in selecting regions that represent a diverse sample of building typologies and damage levels. Our results show that satellite-based remote sensing damage maps disagree with each other, and extensive validation data are still required to characterize the accuracy of each method at both high and medium resolution. Finally, we provide recommendations for planning and validation of future earthquake response efforts.
{"title":"The EEFIT Remote Sensing Reconnaissance Mission for the February 2023 Turkey Earthquakes","authors":"Brandon Voelker;Pietro Milillo;Amin Tavakkoliestahbanati;Valentina Macchiarulo;Giorgia Giardina;Michael Recla;Michael Schmitt;Marzia Cescon;Yasemin D. Aktas;Emily So","doi":"10.1109/JSTARS.2024.3476029","DOIUrl":"https://doi.org/10.1109/JSTARS.2024.3476029","url":null,"abstract":"Accurate and rapid postearthquake structural damage assessment is of vital importance for humanitarian relief. Remote sensing techniques have the potential to map large areas with reduced data latency but are limited by several factors, including accuracy (compared to in-situ monitoring campaigns) and data acquisition frequency. Current damage assessment techniques relying on remote sensing data enable rapid assessment in situations where on-site reconnaissance is not possible or desirable. Yet, these techniques rely on different scales, measurement methods, and spatial resolutions, making it difficult to assimilate many different damage products in a homogeneous damage map. Here, we present the results of the U.K.’s Earthquake Engineering Field Investigation Team's remote-sensing-based reconnaissance mission, which was carried out in the aftermath of the series of earthquakes that struck Turkey and Syria in February 2023. We use a set of publicly available damage maps based on synthetic aperture radar, optical imaging, and ground-based reports as well as in-house developed damage products and assess their relative accuracies. We describe the process of supporting on-site reconnaissance planning by creating maps that describe the building stock and diversity of damage in southeast Turkey to assist field survey teams in selecting regions that represent a diverse sample of building typologies and damage levels. Our results show that satellite-based remote sensing damage maps disagree with each other, and extensive validation data are still required to characterize the accuracy of each method at both high and medium resolution. Finally, we provide recommendations for planning and validation of future earthquake response efforts.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"17 ","pages":"19160-19173"},"PeriodicalIF":4.7,"publicationDate":"2024-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10713507","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142536326","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 : 2024-10-10DOI: 10.1109/JSTARS.2024.3478069
Ge Jiang;Derek D. Lichti;Tiangang Yin;Wai Yeung Yan
Airborne light detection and ranging (LiDAR) data often suffer from noisy returns hovering in empty space within the collected 3-D point clouds. This can be attributed to system-induced factors, such as timing jitter and range walk error, or instantaneous air conditions, such as smoke, rain, clouds, etc. These floating points are indeed outliers, which significantly affect the subsequent analytical processes. Though various point cloud denoising methods are proposed based on sparsity assumption and elevation, they are highly unlikely to remove both clustered and scattered noisy points, especially those located close to the point clouds. Meanwhile, the performance of existing methods does not perform well when noisy points appear close to the ground or on rugged terrain. Accordingly, we propose a maximum entropy based outlier removal (MEOR) method for airborne LiDAR point clouds. More specifically, the proposed method includes two stages, i.e., one global coarse outlier removal stage (MEOR-G) and the subsequent local refined outlier removal stage (MEOR-L). In each stage, the MEOR algorithm is exploited to 1) produce an elevation histogram for the point clouds, 2) search for the elevation threshold to distinguish noisy points and valid points, and 3) remove noisy points and preserve valid data points. We conduct several comprehensive experiments to compare the performance of our proposed MEOR against four other existing noisy point removal methods on four LiDAR datasets. The experimental results demonstrate that MEOR significantly outperforms four other denoising methods by simultaneously removing clustered and scattered noisy points and achieves an improvement by 0.126–99.815%, 0–100%, 0.001–8.454%, and 0.053–99.691% in terms of recall, precision, overall accuracy, and F1 score, respectively.
机载光探测和测距（LiDAR）数据经常会出现噪声回波，盘旋在所采集的三维点云的空白处。这可归因于系统引起的因素，如定时抖动和测距误差，或瞬时空气条件，如烟、雨、云等。这些浮动点确实是离群值，会严重影响后续的分析过程。虽然基于稀疏性假设和仰角提出了多种点云去噪方法，但这些方法都很难去除聚类和散乱的噪声点，尤其是位于点云附近的噪声点。同时，当噪声点靠近地面或出现在崎岖地形上时，现有方法的性能也不理想。因此，我们针对机载激光雷达点云提出了一种基于最大熵的离群点去除（MEOR）方法。具体来说，该方法包括两个阶段，即一个全局粗略离群点去除阶段（MEOR-G）和随后的局部精细离群点去除阶段（MEOR-L）。在每个阶段中，MEOR 算法用于：1）生成点云的高程直方图；2）搜索高程阈值以区分噪声点和有效点；3）去除噪声点并保留有效数据点。我们进行了多项综合实验，在四个激光雷达数据集上比较了我们提出的 MEOR 与其他四种现有噪声点去除方法的性能。实验结果表明，MEOR 通过同时去除聚类和分散的噪声点，明显优于其他四种去噪方法，在召回率、精度、总精度和 F1 分数方面分别提高了 0.126%-99.815%、0-100%、0.001-8.454% 和 0.053-99.691%。
{"title":"A Maximum Entropy Based Outlier Removal for Airborne LiDAR Point Clouds","authors":"Ge Jiang;Derek D. Lichti;Tiangang Yin;Wai Yeung Yan","doi":"10.1109/JSTARS.2024.3478069","DOIUrl":"https://doi.org/10.1109/JSTARS.2024.3478069","url":null,"abstract":"Airborne light detection and ranging (LiDAR) data often suffer from noisy returns hovering in empty space within the collected 3-D point clouds. This can be attributed to system-induced factors, such as timing jitter and range walk error, or instantaneous air conditions, such as smoke, rain, clouds, etc. These floating points are indeed outliers, which significantly affect the subsequent analytical processes. Though various point cloud denoising methods are proposed based on sparsity assumption and elevation, they are highly unlikely to remove both clustered and scattered noisy points, especially those located close to the point clouds. Meanwhile, the performance of existing methods does not perform well when noisy points appear close to the ground or on rugged terrain. Accordingly, we propose a maximum entropy based outlier removal (MEOR) method for airborne LiDAR point clouds. More specifically, the proposed method includes two stages, i.e., one global coarse outlier removal stage (MEOR-G) and the subsequent local refined outlier removal stage (MEOR-L). In each stage, the MEOR algorithm is exploited to 1) produce an elevation histogram for the point clouds, 2) search for the elevation threshold to distinguish noisy points and valid points, and 3) remove noisy points and preserve valid data points. We conduct several comprehensive experiments to compare the performance of our proposed MEOR against four other existing noisy point removal methods on four LiDAR datasets. The experimental results demonstrate that MEOR significantly outperforms four other denoising methods by simultaneously removing clustered and scattered noisy points and achieves an improvement by 0.126–99.815%, 0–100%, 0.001–8.454%, and 0.053–99.691% in terms of recall, precision, overall accuracy, and F1 score, respectively.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"17 ","pages":"19130-19145"},"PeriodicalIF":4.7,"publicationDate":"2024-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10713301","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142524128","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 : 2024-10-10DOI: 10.1109/JSTARS.2024.3477989
Rong Shen;Mou Wang;Jiangbo Hu;Yanbo Wen;Shunjun Wei;Xiaoling Zhang;Ling Fan
Synthetic aperture radar tomography (TomoSAR) can acquire high resolution in height direction by forming a large synthetic aperture along the tomographic direction. Compressed sensing (CS) is widely utilized in TomoSAR imaging to reduce the costs of data sensing. Nevertheless, traditional CS-based algorithms are limited to computational complexity and the nontrivial parameters' tuning. To address such problems, an efficient unfolded deep shrinkage-thresholding network is proposed for TomoSAR imaging in this article. The proposed method adopts convolutional neural network module to learn a generalized nonlinear sparse transformation operator, showing great benefits in exploring the optimal prior. Besides, the hyperparameters of the optimization framework are learned by end-to-end learning mechanism instead of manual-defined, which obviously improves the efficiency of imaging process. Inspired by residual network, the residual learning is introduced to reconstruction blocks of the proposed imaging network, improving the robustness of the network. In addition, the training dataset is constructed from point cloud data based on TomoSAR imaging principles, enhancing the network's ability to extract structural information. Finally, extensive simulation and measured experimental results show the effectiveness of the proposed method, obtaining high-quality imaging results while maintaining high computational efficiency.
{"title":"Deep SAR Tomography: A Model-Inspired Approach With Learned Sparse Regularizer","authors":"Rong Shen;Mou Wang;Jiangbo Hu;Yanbo Wen;Shunjun Wei;Xiaoling Zhang;Ling Fan","doi":"10.1109/JSTARS.2024.3477989","DOIUrl":"https://doi.org/10.1109/JSTARS.2024.3477989","url":null,"abstract":"Synthetic aperture radar tomography (TomoSAR) can acquire high resolution in height direction by forming a large synthetic aperture along the tomographic direction. Compressed sensing (CS) is widely utilized in TomoSAR imaging to reduce the costs of data sensing. Nevertheless, traditional CS-based algorithms are limited to computational complexity and the nontrivial parameters' tuning. To address such problems, an efficient unfolded deep shrinkage-thresholding network is proposed for TomoSAR imaging in this article. The proposed method adopts convolutional neural network module to learn a generalized nonlinear sparse transformation operator, showing great benefits in exploring the optimal prior. Besides, the hyperparameters of the optimization framework are learned by end-to-end learning mechanism instead of manual-defined, which obviously improves the efficiency of imaging process. Inspired by residual network, the residual learning is introduced to reconstruction blocks of the proposed imaging network, improving the robustness of the network. In addition, the training dataset is constructed from point cloud data based on TomoSAR imaging principles, enhancing the network's ability to extract structural information. Finally, extensive simulation and measured experimental results show the effectiveness of the proposed method, obtaining high-quality imaging results while maintaining high computational efficiency.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"17 ","pages":"18870-18881"},"PeriodicalIF":4.7,"publicationDate":"2024-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10713215","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142524245","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 : 2024-10-10DOI: 10.1109/JSTARS.2024.3477593
Changjie Chen;Yong Yang;Shuying Huang;Hangyuan Lu;Weiguo Wan;Shengna Wei;Wenying Wen;Shuzhao Wang
Pansharpening is to fuse a panchromatic (PAN) image with a multispectral (MS) image to obtain a high-spatial-resolution MS (HRMS) image. Although the denoising diffusion probabilistic model can generate high-quality image details, its inherent stochasticity can lead to spectral and spatial distortions in the pansharpening task, and the adding noise method for fixed-size images can weaken the generalization of the model at different scales. To address these issues, a novel pansharpening method based on prior-guided dual-branch diffusion model (PDDM) is proposed. First, a dual-branch diffusion model for different information flows from MS and PAN images is constructed to achieve the spatial and spectral fidelity, which is developed by a collaborative and adversarial learning strategy. Then, to guide detail recovery and reduce the uncertainty of the generated detail information, two pregeneration modules based on different prior information are designed for pixel-to-pixel reconstruction. Finally, a focus module is constructed to fuse the features from the dual-branch and improve the generalization of the proposed PDDM. Extensive experiments on multiple satellite datasets demonstrate that the proposed PDDM has superior performance compared to state-of-the-art methods.
泛锐化是将全色（PAN）图像与多光谱（MS）图像融合，以获得高空间分辨率的多光谱（HRMS）图像。尽管去噪扩散概率模型可以生成高质量的图像细节，但其固有的随机性会导致泛锐化任务中的光谱和空间失真，而且固定尺寸图像的添加噪声方法会削弱模型在不同尺度下的泛化能力。为了解决这些问题，本文提出了一种基于先验引导双分支扩散模型（PDDM）的新型泛锐化方法。首先，针对 MS 和 PAN 图像的不同信息流构建双分支扩散模型，以实现空间和光谱保真度。然后，为了指导细节恢复并减少生成细节信息的不确定性，设计了两个基于不同先验信息的预生成模块，用于像素到像素的重建。最后，构建了一个聚焦模块，以融合双分支的特征，提高所提出的 PDDM 的泛化能力。在多个卫星数据集上进行的广泛实验证明，与最先进的方法相比，所提出的 PDDM 性能更优越。
{"title":"PDDM: Prior-Guided Dual-Branch Diffusion Model for Pansharpening","authors":"Changjie Chen;Yong Yang;Shuying Huang;Hangyuan Lu;Weiguo Wan;Shengna Wei;Wenying Wen;Shuzhao Wang","doi":"10.1109/JSTARS.2024.3477593","DOIUrl":"https://doi.org/10.1109/JSTARS.2024.3477593","url":null,"abstract":"Pansharpening is to fuse a panchromatic (PAN) image with a multispectral (MS) image to obtain a high-spatial-resolution MS (HRMS) image. Although the denoising diffusion probabilistic model can generate high-quality image details, its inherent stochasticity can lead to spectral and spatial distortions in the pansharpening task, and the adding noise method for fixed-size images can weaken the generalization of the model at different scales. To address these issues, a novel pansharpening method based on prior-guided dual-branch diffusion model (PDDM) is proposed. First, a dual-branch diffusion model for different information flows from MS and PAN images is constructed to achieve the spatial and spectral fidelity, which is developed by a collaborative and adversarial learning strategy. Then, to guide detail recovery and reduce the uncertainty of the generated detail information, two pregeneration modules based on different prior information are designed for pixel-to-pixel reconstruction. Finally, a focus module is constructed to fuse the features from the dual-branch and improve the generalization of the proposed PDDM. Extensive experiments on multiple satellite datasets demonstrate that the proposed PDDM has superior performance compared to state-of-the-art methods.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"17 ","pages":"18882-18897"},"PeriodicalIF":4.7,"publicationDate":"2024-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10713214","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142524194","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：