利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

14 条记录 (耗时 0.019 秒)

    Dense three-dimensional correspondence estimation with multi-level metric learning and hierarchical matching
    5.
    发明授权
    Dense three-dimensional correspondence estimation with multi-level metric learning and hierarchical matching 有权

    公开(公告)号：US10832084B2

    公开(公告)日：2020-11-10

    申请号：US16526306

    申请日：2019-07-30

    申请人： NEC Laboratories America, Inc.

    发明人： Quoc-Huy Tran ,  Mohammed E. Fathy Salem ,  Muhammad Zeeshan Zia ,  Paul Vernaza ,  Manmohan Chandraker

    IPC分类号： G06K9/62 ,  G06T17/00 ,  G06T19/00

    摘要： A method for estimating dense 3D geometric correspondences between two input point clouds by employing a 3D convolutional neural network (CNN) architecture is presented. The method includes, during a training phase, transforming the two input point clouds into truncated distance function voxel grid representations, feeding the truncated distance function voxel grid representations into individual feature extraction layers with tied weights, extracting low-level features from a first feature extraction layer, extracting high-level features from a second feature extraction layer, normalizing the extracted low-level features and high-level features, and applying deep supervision of multiple contrastive losses and multiple hard negative mining modules at the first and second feature extraction layers. The method further includes, during a testing phase, employing the high-level features capturing high-level semantic information to obtain coarse matching locations, and refining the coarse matching locations with the low-level features to capture low-level geometric information for estimating precise matching locations.

    Dense correspondence estimation with multi-level metric learning and hierarchical matching
    7.
    发明授权
    Dense correspondence estimation with multi-level metric learning and hierarchical matching 有权

    公开(公告)号：US10679075B2

    公开(公告)日：2020-06-09

    申请号：US16029126

    申请日：2018-07-06

    申请人： NEC Laboratories America, Inc.

    发明人： Quoc-Huy Tran ,  Mohammed E. F. Salem ,  Muhammad Zeeshan Zia ,  Paul Vernaza ,  Manmohan Chandraker

    IPC分类号： G06K9/00 ,  G06K9/62 ,  G06N3/04 ,  G06K9/46 ,  G06K9/66 ,  G06N3/08 ,  G06T17/05

    摘要： Systems and methods for correspondence estimation and flexible ground modeling include communicating two-dimensional (2D) images of an environment to a correspondence estimation module, including a first image and a second image captured by an image capturing device. First features, including geometric features and semantic features, are hierarchically extract from the first image with a first convolutional neural network (CNN) according to activation map weights, and second features, including geometric features and semantic features, are hierarchically extracted from the second image with a second CNN according to the activation map weights. Correspondences between the first features and the second features are estimated, including hierarchical fusing of geometric correspondences and semantic correspondences. A 3-dimensional (3D) model of a terrain is estimated using the estimated correspondences belonging to the terrain surface. Relative locations of elements and objects in the environment are determined according to the 3D model of the terrain. A user is notified of the relative locations.

    DENSE THREE-DIMENSIONAL CORRESPONDENCE ESTIMATION WITH MULTI-LEVEL METRIC LEARNING AND HIERARCHICAL MATCHING
    9.
    发明申请
    DENSE THREE-DIMENSIONAL CORRESPONDENCE ESTIMATION WITH MULTI-LEVEL METRIC LEARNING AND HIERARCHICAL MATCHING 审中-公开

    公开(公告)号：US20200058156A1

    公开(公告)日：2020-02-20

    申请号：US16526306

    申请日：2019-07-30

    申请人： NEC Laboratories America, Inc.

    发明人： Quoc-Huy Tran ,  Mohammed E. Fathy Salem ,  Muhammad Zeeshan Zia ,  Paul Vernaza ,  Manmohan Chandraker

    IPC分类号： G06T15/08 ,  G06K9/62 ,  G06K9/72 ,  G06N3/04 ,  G06N3/08 ,  G06T15/10

    摘要： A method for estimating dense 3D geometric correspondences between two input point clouds by employing a 3D convolutional neural network (CNN) architecture is presented. The method includes, during a training phase, transforming the two input point clouds into truncated distance function voxel grid representations, feeding the truncated distance function voxel grid representations into individual feature extraction layers with tied weights, extracting low-level features from a first feature extraction layer, extracting high-level features from a second feature extraction layer, normalizing the extracted low-level features and high-level features, and applying deep supervision of multiple contrastive losses and multiple hard negative mining modules at the first and second feature extraction layers. The method further includes, during a testing phase, employing the high-level features capturing high-level semantic information to obtain coarse matching locations, and refining the coarse matching locations with the low-level features to capture low-level geometric information for estimating precise matching locations.