利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

181 条记录 (耗时 0.027 秒)

    Techniques for image co-registration
    1.
    发明授权
    Techniques for image co-registration 有权

    公开(公告)号：US11024044B2

    公开(公告)日：2021-06-01

    申请号：US15716425

    申请日：2017-09-26

    申请人： DigitalGlobe, Inc.

    发明人： Grzegorz Miecznik

    IPC分类号： G06K9/32 ,  G06T7/32 ,  G06T7/207 ,  G06T7/35

    摘要： Techniques for improving image co-registration. One aspect relates to improving Mutual Information techniques by making the histogram bin widths used therein depend on the amount of signal noise. Another aspect relates to populating the bins by integrating the signal probability in each bin. A third aspect relates to converting top-of-the-atmosphere image data to surface reflectance data, and then using surface reflectance data in the Mutual Information technique for determining a correlation surface. The fourth aspect relates to registering higher-resolution images with lower-resolution images by down-sampling the higher-resolution image. The last aspect relates to a technique for determining the accuracy of the co-registration by synthesizing a perfectly-registered image in a second wavelength band from an image in a first wavelength band and then using Mutual Information between the two images to create a correlation surface.

    BROAD AREA GEOSPATIAL OBJECT DETECTION USING AUTOGENERATED DEEP LEARNING MODELS
    3.
    发明申请
    BROAD AREA GEOSPATIAL OBJECT DETECTION USING AUTOGENERATED DEEP LEARNING MODELS 审中-公开

    公开(公告)号：US20200118292A1

    公开(公告)日：2020-04-16

    申请号：US16553060

    申请日：2019-08-27

    申请人： DigitalGlobe, Inc.

    发明人： Adam Estrada ,  Andrew Jenkins ,  Benjamin Brock ,  Chris Mangold

    IPC分类号： G06T7/73 ,  G06T5/00 ,  G06K9/46 ,  G06K9/00 ,  G06K9/62 ,  G06T7/33

    摘要： A system for automated geospatial image analysis comprising a deep learning model that receives orthorectified geospatial images, pre-labeled to demarcate objects of interest. The module presents marked geospatial images and a second set of unmarked, optimized, training geospatial images to a convolutional neural network. This process may be repeated so that an image analysis software module can detect multiple object types or categories. The image analysis software module receives orthorectified geospatial images from one or more geospatial image caches. Using a multi-scale sliding window submodule, image analysis software scans geospatial images, detects objects present and geospatially locates them.

    UNSUPERVISED LAND USE AND LAND COVER DETECTION
    7.
    发明申请
    UNSUPERVISED LAND USE AND LAND COVER DETECTION 审中-公开

    公开(公告)号：US20180336394A1

    公开(公告)日：2018-11-22

    申请号：US15812124

    申请日：2017-11-14

    申请人： DigitalGlobe, Inc.

    发明人： Georgios Ouzounis

    IPC分类号： G06K9/00 ,  G06K9/62 ,  G06K9/40 ,  G06T7/11

    摘要： A system and methods for unsupervised land use and land cover detection using a classifier that produces a plurality of class image layers which are filtered to remove misclassified same-label pixel groupings, a class resolution module that reduces multiple pixel labels to a single one if applicable and a reconstruction module that generates the output land use and land cover image.

    Advanced semi-automated vector editing in two and three dimensions
    8.
    发明授权
    Advanced semi-automated vector editing in two and three dimensions 有权

    公开(公告)号：US10133928B2

    公开(公告)日：2018-11-20

    申请号：US14681043

    申请日：2015-04-07

    申请人： DigitalGlobe, Inc.

    发明人： Seth Malitz ,  Jacek Grodecki

    IPC分类号： G06K9/00

    摘要： A system for advanced vector editing, comprising a vector analysis server that analyzes vector information, a routing calculation server that calculates routes from the vector information, and a rendering engine that produces visualizations from the routing information, and several methods for advanced vector editing in two- and three-dimensional visualizations.