Point cloud annotation device, method, and program

    公开(公告)号:US12106438B2

    公开(公告)日:2024-10-01

    申请号:US17608735

    申请日:2019-05-08

    IPC分类号: G06T19/00 G06T7/00

    摘要: Annotation can be easily performed on a three-dimensional point cloud and a working time can be reduced. An interface unit 22 displays a point cloud indicating a three-dimensional point on an object, and receives designation of a three-dimensional point indicating an annotation target object and designation of a three-dimensional point not indicating the annotation target object. A candidate cluster calculation unit 32 calculates a value of a predetermined evaluation function indicating a likelihood of a point cloud cluster being the annotation target object based on the designation of a three-dimensional point for point cloud clusters obtained by clustering the point clouds. A cluster selection and storage designation unit 34 causes the interface unit 22 to display the point cloud clusters in descending order of the value of the evaluation function, and receives a selection of a point cloud cluster to be annotated. An annotation execution unit 36 executes annotation indicating the annotation target object for each three-dimensional point included in the selected point cloud cluster.

    Detection device, detection method and detection program for linear structure

    公开(公告)号:US11823330B2

    公开(公告)日:2023-11-21

    申请号:US17634595

    申请日:2019-08-19

    IPC分类号: G06T17/20 G06F30/18 G01B11/00

    摘要: An object of the present disclosure is to provide a technique for creating a three-dimensional model of a line-like structure from a point cloud obtained using three-dimensional laser measuring equipment and detecting a three-dimensional model of a cable. A detection apparatus according to the disclosure includes a point cloud data input unit 12 that reads point cloud data where a structure that is present in a three-dimensional space is represented by a point cloud that is present in the three-dimensional space, a rule-based three-dimensional model generation unit 15 that combines linearly disposed point clouds into a group and generates a three-dimensional model of a line-like structure using a direction vector configured with point clouds included in the group, a machine learning-based three-dimensional model generation unit 14 that generates a three-dimensional model of a line-like structure based on a database that links point clouds and line-like structures, and a three-dimensional model merging unit that selects one of a plurality of three-dimensional models of line-like structures generated at an identical position in the three-dimensional space as a three-dimensional model of a line-like structure that is present in the three-dimensional space and merges three-dimensional models of the line-like structures that are present in the three-dimensional space.

    Depth superresolution device, depth superresolution method, and program

    公开(公告)号:US11900622B2

    公开(公告)日:2024-02-13

    申请号:US17425916

    申请日:2020-01-27

    IPC分类号: G06T7/50 G06T3/40

    摘要: Dense depth information can be generated using only a monocular image and sparse depth information.
    A depth hyper-resolving apparatus 100 includes: an input data processing unit 22 that outputs a hierarchical input image and hierarchical input depth information by resolution conversion in accordance with a predetermined number of tiers for an input image and input depth information; a depth continuity estimation unit 24 that derives hierarchical estimated depth continuity based on the hierarchical input image; a depth continuity mask deriving unit 26 that outputs a hierarchical depth continuity mask representing values of locations depending on whether a depth is continuous based on the hierarchical input image and the hierarchical estimated depth continuity; and a cost function minimization unit 30 that derives hyper-resolved depth information to minimize a cost function expressed by using the hierarchical input depth information, the hierarchical depth continuity mask, and the hyper-resolved depth information.