Automatic satellite building construction monitoring
Moscow Institute of Physics and Technology (National Research University)(莫斯科物理技术学院(国立研究型大学));Lomonosov Moscow State University(罗蒙诺索夫莫斯科国立大学);Bauman Moscow State Technical University(鲍曼莫斯科国立技术大学)
Insaf Ashrapov, Dmitriy Malakhov, Anton Marchenkov, Anton Lulin, Dani El-Ayyass
One of the promising applications of satellite images is building construction monitoring. It allows to control the construction progress around the world even in the locations that are hard to reach. One of the main hurdles of this approach is the interpretation of the image data. In this paper, we have employed several novel deep learning techniques to tackle the problem. Various image segmentation and object detection networks were combined into a unified pipeline, which was then used to determine the building construction progress.
DV3+HED+: A DCNNs-based Framework to Monitor Temporary Works and ESAs in Railway Construction Project Using VHR Satellite Images
Aerospace Information Research Institute, Chinese Academy of Sciences(中国科学院空天信息创新研究院);Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences(中国科学院遥感与数字地球研究所);Ping An Technology (Shenzhen) Co., Ltd(平安科技(深圳)有限公司);China Institute of Water Resources and Hydropower Research(中国水利水电科学研究院)
Advancing Applications of Satellite Photogrammetry: Novel Approaches for Built-up Area Modeling and Natural Environment Monitoring using Stereo/Multi-view Satellite Image-derived 3D Data
Monitoring Pasture Restoration from Satellite Image Time Series: Caveats and Opportunities
Lund University(隆德大学);RISE Research Institutes of Sweden(瑞典RISE研究院);Climate AI Nordics(北欧气候人工智能中心);Swedish Centre for Impacts of Climate Extremes (CLIMES)(瑞典气候极端影响中心(CLIMES))
Space2Ground 2.0: A Multi-Source Dataset and Framework for Agricultural Monitoring through Fusion of Street-Level and Satellite Imagery
Operational Unit BEYOND Centre, IAASARS, National Observatory of Athens(雅典国家天文台IAASARS研究所BEYOND中心业务单元);DHI Water & Environment(DHI水环境公司);Artificial Intelligence Group, Wageningen University & Research(瓦赫宁根大学及研究中心人工智能组)
Machine Learning for Glacier Monitoring in the Hindu Kush Himalaya
Mila(米拉);University of Texas at El Paso(得克萨斯大学埃尔帕索分校);Integrated Centre for Mountain Development(山地发展综合中心);Microsoft AI for Good Research Lab(微软AI公益研究实验室);University of Wisconsin - Madison(威斯康星大学麦迪逊分校)
Learning a Joint Embedding of Multiple Satellite Sensors: A Case Study for Lake Ice Monitoring
Swiss Federal Institute of Technology, Zurich(苏黎世联邦理工学院);Swiss Federal Institute of Aquatic Science and Technology(瑞士联邦水科学与技术研究所);University of Zurich(苏黎世大学)
融合使用不同传感器获取的卫星图像一直是地球观测的一个长期挑战,特别是在光学和合成孔径雷达(SAR)图像等不同模式之间。在这里,我们探讨了联合分析的图像从不同的传感器在光的表示学习:我们建议学习一个联合嵌入的多个卫星传感器在一个深神经网络。我们的应用问题是监测高山湖泊的湖冰。为了达到瑞士全球气候观测系统(GCOS)办公室的时间分辨率要求,我们结合了三个图像源:Sentinel-1 SAR(S1-SAR),Terra MODIS和Suomi-NPP VIIRS。光学域和SAR域之间以及传感器分辨率之间的巨大差距使其成为传感器融合问题的一个具有挑战性的实例。我们的方法可以归类为以数据驱动的方式学习的后期融合。所提出的网络架构具有单独的编码分支,为每个图像传感器,它馈入到一个单一的潜在嵌入。即,由所有输入共享的共同特征表示,使得后续处理步骤提供可比较的输出,而不管使用哪种输入图像。通过融合卫星数据,我们以91%的时间分辨率绘制了湖冰图< 1.5 days. The network produces spatially explicit lake ice maps with pixel-wise accuracies >(mIoU得分分别> 60%),并在不同的湖泊和冬季进行了很好的概括。此外,它为确定目标湖泊的重要冰起冰落日期提供了一种新的技术水平,在许多情况下满足了全球气候观测系统…
Generating Synthetic Satellite Imagery With Deep-Learning Text-to-Image Models -- Technical Challenges and Implications for Monitoring and Verification
Berliner Hochschule für Technik(柏林应用技术大学);Princeton University(普林斯顿大学);Einstein Center Digital Future(爱因斯坦数字未来中心)
Monitoring the Impacts of a Tailings Dam Failure Using Satellite Images
Colorado School of Mines(科罗拉多矿业大学)
利用卫星图像监测溃坝情况为第一反应者提供了有效的早期干预管理。同样重要的是,要监测淹没区的时空变化,以跟踪灾后恢复情况。2019年1月25日,位于巴西Brumadinho的Córrego do Feijão铁矿的尾矿坝倒塌。这场灾难造成230多人死亡,30人失踪,造成数十亿美元的损失。本研究使用哨兵2号卫星图像绘制淹没区地图,并评估和描绘受溃坝影响的土地利用和土地覆盖情况。这些图像对应于1月22日(崩溃前3天)和2月2日(崩溃后7天)的数据捕获。该地区的卫星图像在灾难发生之前和之后进行了分类,采用了机器学习算法。为了有足够的土地覆盖类型来验证算法的质量和准确性,定义了7类:矿山,森林,建筑物,河流,农业,清水和草地。开发的分类算法产生了很高的准确性(99%)的图像之前崩溃。本文使用两种不同的模型来确定土地覆盖影响,1)通过使用“之后”图像中的训练网络,以及2)通过创建第二个网络,在“之后”图像的点的子集中进行训练,然后比较两个训练网络的土地覆盖结果。在第一个模型中,将训练好的网络应用于“之后”的图像,准确率仍然很高(86%),但低于使用第二个模型(98%)。这一战略可通过利用公开提供的卫星信息以较低的成本用于监测和评估,在发生大坝坍塌或预算较大的情况下,可通过飞越有关地区获得更高分辨率和更快的数据。
Enhancing Maritime Situational Awareness through End-to-End Onboard Raw Data Analysis
European Space Agency(欧洲空间局);University of Naples Federico II(那不勒斯费德里科二世大学);Ben-Gurion University of the Negev(本-古里安大学内盖夫分校);University of Campania “L. Vanvitelli”(坎帕尼亚大学“L.万维泰利”分校);Advanced Concepts and Studies Office, European Space Agency(欧洲空间局先进概念与研究办公室)
Reconstructing Satellites in 3D from Amateur Telescope Images
College of Future Technology(未来技术学院);National Biomedical Imaging Center(国家生物医学成像中心);College of Engineering(工程学院);State Key Laboratory of Multimedia Information Processing(多媒体信息处理国家重点实验室);National Engineering Research Center of Visual Technology(视觉技术国家工程研究中心);School of Computer Science(计算机科学学院);Beijing Jingdun Technology Co., Ltd.(北京竞 Dunn 技术有限公司);National Laboratory on Adaptive Optics(自适应光学国家实验室);Institute of Optics and Electronics(光学与电子学研究所);Chinese Academy of Sciences(中国科学院)
A satellite foundation model for improved wealth monitoring
Department of Computer Science, Stanford University(斯坦福大学计算机科学系);Department of Earth System Science, Stanford University(斯坦福大学地球系统科学系);Center on Food Security and the Environment, Stanford University(斯坦福大学食品安全与环境中心);Development Economics Data Group, World Bank Group(世界银行发展经济学数据组);Department of Environmental Social Science, Stanford University(斯坦福大学环境社会科学系)
Mapping Global Floods with 10 Years of Satellite Radar Data
Microsoft AI for Good Research Lab(微软人工智能公益研究院);Cooperative Institute for Meteorological Satellite Studies, University of Wisconsin-Madison(威斯康星大学麦迪逊分校合作气象卫星研究所)
Segment Anything for Satellite Imagery: A Strong Baseline and a Regional Dataset for Automatic Field Delineation
University of Modena and Reggio Emilia(摩德纳和雷吉奥艾米利亚大学);ABACO Group SpA(ABACO集团);Institute of Informatics and Telematics, National Research Council(信息与电信研究所,国家研究 council)
Predicting butterfly species presence from satellite imagery using soft contrastive regularisation
The Alan Turing Institute, the UK(英国阿尔安·图灵研究所);Wageningen University & Research, the NL(瓦赫宁根大学与研究中心);University College London, the UK(伦敦大学学院);UK Centre for Ecology & Hydrology, the UK(英国生态与水文研究中心)
Using Game Engines and Machine Learning to Create Synthetic Satellite Imagery for a Tabletop Verification Exercise
Berliner Hochschule für Technik(柏林技术应用科学大学);Program on Science and Global Security, Princeton University(普林斯顿大学科学与全球安全项目);Einstein Center Digital Future, Berlin(柏林爱因斯坦数字未来中心)