Originally developed in fields such as robotics and autonomous driving with image-based navigation in mind, deep learning-based single-image depth estimation (SIDE) has found great interest in the wider image analysis community. Remote sensing is no exception, as the possibility to estimate height maps from single aerial or satellite imagery bears great potential in the context of topographic reconstruction. A few pioneering investigations have demonstrated the general feasibility of single image height prediction from optical remote sensing images and motivate further studies in that direction. With this paper, we present the first-ever demonstration of deep learning-based single image height prediction for the other important sensor modality in remote sensing: synthetic aperture radar (SAR) data. Besides the adaptation of a convolutional neural network (CNN) architecture for SAR intensity images, we present a workflow for the generation of training data, and extensive experimental results for different SAR imaging modes and test sites. Since we put a particular emphasis on transferability, we are able to confirm that deep learning-based single-image height estimation is not only possible, but also transfers quite well to unseen data, even if acquired by different imaging modes and imaging parameters.
Tomographic SAR Reconstruction for Forest Height Estimation
University of Cambridge（剑桥大学）；United Nations Office for Outer Space Affairs（联合国外层空间事务厅）；UK Department for Energy Security and Net Zero（英国能源安全与净零部）；INSEC TEC；Drexel University（卓克索大学）
本文提出直接由二维 SLC SAR 图像利用深度学习估计森林冠层高度，并评估 SLC 数量影响；结果表明绕过完整层析处理会使误差增加 16%–21%。
3D-SAR Tomography and Machine Learning for High-Resolution Tree Height Estimation
University of Cambridge（剑桥大学）；United Nations Office for Outer Space Affairs（联合国外层空间事务厅）；UK Department for Energy Security and Net Zero（英国能源安全与净零部）；INSEC TEC；Drexel University（卓克索大学）
Technical University of Munich（慕尼黑工业大学）；German Aerospace Center (DLR)（德国航空航天中心）
Building height retrieval from synthetic aperture radar (SAR) imagery is of great importance for urban applications, yet highly challenging owing to the complexity of SAR data. This paper addresses the issue of building height retrieval in large-scale urban areas from a single TerraSAR-X spotlight or stripmap image. Based on the radar viewing geometry, we propose that this problem can be formulated as a bounding box regression problem and therefore allows for integrating height data from multiple data sources in generating ground truth on a larger scale. We introduce building footprints from g…
An Object-Based Deep Learning Approach for Building Height Estimation from Single SAR Images
Department of Electrical, Computer and Biomedical Engineering, University of Pavia（电子、计算机与生物医学工程系，帕维亚大学）；Department of Engineering, University of Sannio（工程系，萨尼奥大学）
Technische Universität München（慕尼黑工业大学）；German Aerospace Center（德国航空航天中心）
Multi-baseline interferometric synthetic aperture radar (InSAR) techniques are effective approaches for retrieving the 3-D information of urban areas. In order to obtain a plausible reconstruction, it is necessary to use more than twenty interferograms. Hence, these methods are commonly not appropriate for large-scale 3-D urban mapping using TanDEM-X data where only a few acquisitions are available in average for each city. This work proposes a new SAR tomographic processing framework to work with those extremely small stacks, which integrates the non-local filtering into SAR tomography invers…
A Deep Learning Approach to Estimate Canopy Height and Uncertainty by Integrating Seasonal Optical, SAR and Limited GEDI LiDAR Data over Northern Forests
Beyond Backscatter: InSAR coherence from detected SAR images
Department of Aerospace Engineering, University of the Bundeswehr Munich（联邦国防军 Munich航空航天工程系）；Microwaves and Radar Institute, German Aerospace Center (DLR)（德国航空航天中心 (DLR) 微波与雷达研究所）
OceanSAR-2: A Universal Feature Extractor for SAR Ocean Observation
Galeio, Paris, France（法国加利欧）；LOPS, Ifremer, Plouzané, France（法国若特默尔实验室）；OceanScope, Brest, France（法国海洋观测中心）；Nanjing University of Information Science and Technology, Nanjing, China（中国信息科学技术大学）
The segmentation of synthetic aperture radar (SAR) images is a longstanding yet challenging task, not only because of the presence of speckle, but also due to the variations of surface backscattering properties in the images. Tremendous investigations have been made to eliminate the speckle effects for the segmentation of SAR images, while few work devotes to dealing with the variations of backscattering coefficients in the images. In order to overcome both the two difficulties, this paper presents a novel SAR image segmentation method by exploiting a multi-scale active contour model based on …
This paper presents two approaches for filter design based on stochastic distances for intensity speckle reduction. A window is defined around each pixel, overlapping samples are compared and only those which pass a goodness-of-fit test are used to compute the filtered value. The tests stem from stochastic divergences within the Information Theory framework. The technique is applied to intensity Synthetic Aperture Radar (SAR) data with homogeneous regions using the Gamma model. The first approach uses a Nagao-Matsuyama-type procedure for setting the overlapping samples, and the second uses the…
A machine learning approach for image classification in synthetic aperture RADAR
Department of Mathematics and Statistics University of Limerick（数学与统计学系利默里克大学）；Health Research Institute (HRI)（健康研究中心）；Department of Computer Science and Information Systems University of Limerick（计算机科学与信息系统系利默里克大学）
Large-Scale Avalanche Mapping from SAR Images with Deep Learning-based Change Detection
Department of Theoretical and Applied Sciences, University of Insubria（理论与应用科学系，意大利因布里亚大学）；Department of Science and High Technology, University of Insubria（科学与高新技术系，意大利因布里亚大学）
Closed-Form Nonlocal Shrinkage for Multiplicative Image Denoising and SAR Despeckling
School of Electronic Engineering, Xidian University（西安电子科技大学电子工程学院）；Kunshan Innovation Institute of Xidian University（西安电子科技大学昆山创新研究院）；University of Montenegro（黑山大学）；KTH Royal Institute of Technology（瑞典皇家理工学院）；Macquarie University（麦考瑞大学）
Speckle reduction is a longstanding topic in synthetic aperture radar (SAR) images. Many different schemes have been proposed for the restoration of intensity SAR images. Among the different possible approaches, methods based on convolutional neural networks (CNNs) have recently shown to reach state-of-the-art performance for SAR image restoration. CNN training requires good training data: many pairs of speckle-free / speckle-corrupted images. This is an issue in SAR applications, given the inherent scarcity of speckle-free images. To handle this problem, this paper analyzes different strategi…
ETH Zurich（苏黎世联邦理工学院）；Norwegian Institute of Bioeconomy Research（挪威生物经济研究所）；University of Zurich（苏黎世大学）
Monitoring and managing Earth's forests in an informed manner is an important requirement for addressing challenges like biodiversity loss and climate change. While traditional in situ or aerial campaigns for forest assessments provide accurate data for analysis at regional level, scaling them to entire countries and beyond with high temporal resolution is hardly possible. In this work, we propose a method based on deep ensembles that densely estimates forest structure variables at country-scale with 10-meter resolution, using freely available satellite imagery as input. Our method jointly tra…
A Complex-valued SAR Foundation Model Based on Physically Inspired Representation Learning
Aerospace Information Research Institute, Chinese Academy of Sciences（中国科学院空天信息研究院）；School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences（中国科学院大学电子电气与通信工程学院）；University of Chinese Academy of Sciences（中国科学院大学）
SARLO-80: Worldwide Slant SAR Language Optic Dataset 80cm
DEMR-ONERA – The French Aerospace Lab, Université Paris-Saclay（法国航空航天实验室DEMR-ONERA，巴黎-萨克雷大学）；DTIS-ONERA – The French Aerospace Lab, Université Paris-Saclay（法国航空航天实验室DTIS-ONERA，巴黎-萨克雷大学）；Hugging Face
Reconstructing Building Height from Spaceborne TomoSAR Point Clouds Using a Dual-Topology Network
The Chair of Data Science in Earth Observation, Technical University of Munich (TUM)（地球观测数据科学教授职位，慕尼黑技术大学）；Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心）；School of Engineering and Design, Technical University of Munich (TUM)（工程与设计学院，慕尼黑技术大学）
Shanghai Jiao Tong University（上海交通大学）；Shanghai AI Laboratory（上海人工智能实验室）
Automatic and accurate tumor segmentation on medical images is in high demand to assist physicians with diagnosis and treatment. However, it is difficult to obtain massive amounts of annotated training data required by the deep-learning models as the manual delineation process is often tedious and expertise required. Although self-supervised learning (SSL) scheme has been widely adopted to address this problem, most SSL methods focus only on global structure information, ignoring the key distinguishing features of tumor regions: local intensity variation and large size distribution. In this pa…
IRSTEA（法国国家环境与农业科学技术研究院）；University of Montpellier（蒙彼利埃大学）；LIRMM laboratory（蒙彼利埃计算机科学、机器人技术与微电子实验室）；CIRAD（法国农业研究发展中心）；Envylis Cie（Envylis 公司）
Mapping winter vegetation quality coverage is a challenge problem of remote sensing. This is due to the cloud coverage in winter period, leading to use radar rather than optical images. The objective of this paper is to provide a better understanding of the capabilities of radar Sentinel-1 and deep learning concerning about mapping winter vegetation quality coverage. The analysis presented in this paper is carried out on multi-temporal Sentinel-1 data over the site of La Rochelle, France, during the campaign in December 2016. This dataset were processed in order to produce an intensity radar d…
Observations of seabed texture with synthetic aperture sonar are dependent upon several factors. In this work, we focus on collection geometry with respect to isotropic and anisotropic textures. The low grazing angle of the collection geometry, combined with orientation of the sonar path relative to anisotropic texture, poses a significant challenge for image-alignment and other multi-view scene understanding frameworks. We previously proposed using features captured from estimated seabed relief to improve scene understanding. While several methods have been developed to estimate seabed relief…
GeoFormer: A Lightweight Swin Transformer for Joint Building Height and Footprint Estimation from Sentinel Imagery
Department of Civil, Architectural and Environmental System Engineering, Sungkyunkwan University（成均馆大学土木、建筑与环境系统工程系）；School of Geography, University of Leeds（利兹大学地理学院）；Interdisciplinary Program for Crisis, Disaster and Risk Management, Sungkyunkwan University（成均馆大学危机、灾害与风险管理跨学科项目）
Deep Self-Supervised Disturbance Mapping with the OPERA Sentinel-1 Radiometric Terrain Corrected SAR Backscatter Product
University of California - Los Angeles（加利福尼亚大学洛杉矶分校）；Jet Propulsion Laboratory, California Institute of Technology（加州理工学院喷气推进实验室）；Joint Institute for Regional Earth System Science and Engineering, University of California - Los Angeles（加利福尼亚大学洛杉矶分校区域地球系统科学与工程联合研究所）
本文基于 OPERA RTC-S1 数据训练无需标签的自监督 vision transformer，通过逐像素基线分布偏差检测地表扰动，并在三地灾害事件中取得优于现有方法的结果。
WV-Net: A foundation model for SAR WV-mode satellite imagery trained using contrastive self-supervised learning on 10 million images
University of Hawai‘i at Mānoa（夏威夷大学马诺阿分校）；University of Washington（华盛顿大学）；University of New Hampshire（新罕布什尔大学）；Univ. Brest（布雷斯特大学）；CNRS（法国国家科学研究中心）；IRD（法国发展研究所）；Ifremer（法国海洋开发研究院）；IUEM（欧洲海洋科学研究所）
Do Echo Top Heights Improve Deep Learning Nowcasts?
Kempelen Institute of Intelligent Technologies（智能技术研究所）；Faculty of information Technology（信息技术学院）；Brno University of Technology（布拉格技术大学）；Department of Geoscience and Remote Sensing（地质与遥感系）；Delft University of Technology（代尔夫特技术大学）
