中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

20 records (took 0.025 seconds)

    GENERATING REALISTIC POINT CLOUDS
    13.
    发明申请
    GENERATING REALISTIC POINT CLOUDS 有权

    公开(公告)号：US20220230387A1

    公开(公告)日：2022-07-21

    申请号：US17713108

    申请日：2022-04-04

    Applicant: Waymo LLC

    Inventor： Yin Zhou ,  Dragomir Anguelov ,  Zhangjie Cao

    IPC: G06T17/00 ,  G06N20/00 ,  G06N3/04 ,  G06V20/10

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating realistic full-scene point clouds. One of the methods includes obtaining an initial scene point cloud characterizing an initial scene in an environment; obtaining, for each of one or more objects, an object point cloud that characterizes the object;
    and processing a first input comprising the initial scene point cloud and the one or more object point clouds using a first neural network that is configured to process the first input to generate a final scene point cloud that characterizes a transformed scene that has the one or more objects added to the initial scene.

    MULTI-MODAL 3-D POSE ESTIMATION
    14.
    发明申请
    MULTI-MODAL 3-D POSE ESTIMATION 有权

    公开(公告)号：US20220156965A1

    公开(公告)日：2022-05-19

    申请号：US17505900

    申请日：2021-10-20

    Applicant: Waymo LLC

    Inventor： Jingxiao Zheng ,  Xinwei Shi ,  Alexander Gorban ,  Junhua Mao ,  Andre Liang Cornman ,  Yang Song ,  Ting Liu ,  Ruizhongtai Qi ,  Yin Zhou ,  Congcong Li ,  Dragomir Anguelov

    IPC: G06T7/73 ,  G06K9/62 ,  G06K9/00

    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for estimating a 3-D pose of an object of interest from image and point cloud data. In one aspect, a method includes obtaining an image of an environment; obtaining a point cloud of a three-dimensional region of the environment; generating a fused representation of the image and the point cloud; and processing the fused representation using a pose estimation neural network and in accordance with current values of a plurality of pose estimation network parameters to generate a pose estimation network output that specifies, for each of multiple keypoints, a respective estimated position in the three-dimensional region of the environment.

    GENERATING REALISTIC POINT CLOUDS
    16.
    发明申请
    GENERATING REALISTIC POINT CLOUDS 有权

    公开(公告)号：US20210150807A1

    公开(公告)日：2021-05-20

    申请号：US17099589

    申请日：2020-11-16

    Applicant: Waymo LLC

    Inventor： Yin Zhou ,  Dragomir Anguelov ,  Zhangjie Cao

    IPC: G06T17/00 ,  G06N3/04 ,  G06K9/00 ,  G06N20/00

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating realistic full-scene point clouds. One of the methods includes obtaining an initial scene point cloud characterizing an initial scene in an environment; obtaining, for each of one or more objects, an object point cloud that characterizes the object; and processing a first input comprising the initial scene point cloud and the one or more object point clouds using a first neural network that is configured to process the first input to generate a final scene point cloud that characterizes a transformed scene that has the one or more objects added to the initial scene.

    SEMANTIC SEGMENTATION NEURAL NETWORK FOR POINT CLOUDS
    19.
    发明公开
    SEMANTIC SEGMENTATION NEURAL NETWORK FOR POINT CLOUDS 审中-公开

    公开(公告)号：US20240096076A1

    公开(公告)日：2024-03-21

    申请号：US17945325

    申请日：2022-09-15

    Applicant: Waymo LLC

    Inventor： Yin Zhou ,  Ruizhongtai Qi ,  Dragomir Anguelov ,  Minghua Liu ,  Boqing Gong

    IPC: G06V10/82 ,  G06V10/80

    CPC classification number: G06V10/82 ,  G06V10/80

    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a semantic segmentation neural network for point clouds. One of the methods includes: obtaining a plurality of training points divided into a respective plurality of components; obtaining, for each of the respective plurality of components, data identifying a ground truth category for one or more labeled point; processing each training points using a semantic segmentation neural network to generate a semantic segmentation that includes a respective score for each of the plurality of categories; determining a gradient of a loss function that penalizes the semantic segmentation neural network for generating, for points in the component, non-zero scores for categories that are not the ground truth category for any labeled point in the component; and updating, using the gradient, the parameters of the semantic segmentation neural network.

    OBJECT-CENTRIC THREE-DIMENSIONAL AUTO LABELING OF POINT CLOUD DATA
    20.
    发明申请
    OBJECT-CENTRIC THREE-DIMENSIONAL AUTO LABELING OF POINT CLOUD DATA 有权

    公开(公告)号：US20220058818A1

    公开(公告)日：2022-02-24

    申请号：US17407795

    申请日：2021-08-20

    Applicant: Waymo LLC

    Inventor： Ruizhongtai Qi ,  Yin Zhou ,  Dragomir Anguelov ,  Pei Sun

    IPC: G06T7/521 ,  G06T7/20

    Abstract: Methods, computer systems, and apparatus, including computer programs encoded on computer storage media, for performing three-dimensional auto-labeling on sensor data. The system obtains a sensor data segment that includes a temporal sequence of three-dimensional point clouds generated from sensor readings of an environment by one or more sensors. The system identifies, from the sensor data segment, (i) a plurality of object tracks that each corresponds to a different object in the environment and (ii) for each object track, respective initial three-dimensional regions in each of one or more of the point clouds in which the corresponding object appears. The system generates, for each object track, extracted object track data that includes at least the points in the respective initial three-dimensional regions for the object track. The system further generates, for each object track and from the extracted object track data for the object track, an auto labeling output that defines respective refined three-dimensional regions in each of the one or more point clouds.

Patent Agency Ranking