Point cloud data clustering and classification using implicit geometry representation
    1.
    发明授权
    Point cloud data clustering and classification using implicit geometry representation 有权
    点云数据聚类和使用隐式几何表示的分类

    公开(公告)号:US09245170B1

    公开(公告)日:2016-01-26

    申请号:US13534499

    申请日:2012-06-27

    IPC分类号: G06K9/00 G06K9/62

    摘要: An image processing system comprising a data repository and an image processor. The data repository is configured to store image data. The image processor is configured to place the image data into a three-dimensional mesh. The image processor is further configured to identify vectors of the image data in the three-dimensional mesh. The image processor is further configured to identify a number of clusters in the vectors of the image data in the three-dimensional mesh.

    摘要翻译: 一种包括数据存储库和图像处理器的图像处理系统。 数据存储库被配置为存储图像数据。 图像处理器被配置为将图像数据放置成三维网格。 图像处理器还被配置为识别三维网格中的图像数据的向量。 图像处理器还被配置为识别三维网格中的图像数据的矢量中的多个聚类。

    Spatial data compression using implicit geometry
    2.
    发明授权
    Spatial data compression using implicit geometry 有权
    使用隐式几何空间数据压缩

    公开(公告)号:US08525835B1

    公开(公告)日:2013-09-03

    申请号:US12711931

    申请日:2010-02-24

    IPC分类号: G06T15/10

    摘要: A plurality of data from a first coordinate system is transformed into a plurality of metadata, each metadata comprising a location identifier and a value summarizing an amount of data points in the first coordinate system associated with a corresponding location in the second coordinate identified by the location identifier. A metadata is formed only when a non-zero value is assigned to a location.

    摘要翻译: 将来自第一坐标系的多个数据变换为多个元数据,每个元数据包括位置标识符和总结第一坐标系中的数据点的数量的值,该数据点与由该位置识别的第二坐标中的对应位置相关联 标识符 仅当将非零值分配给某个位置时才形成元数据。

    Grammar-based, cueing method of object recognition, and a system for performing same
    3.
    发明授权
    Grammar-based, cueing method of object recognition, and a system for performing same 有权
    基于语法的对象识别的提示方法,以及用于执行对象识别的系统

    公开(公告)号:US08483478B1

    公开(公告)日:2013-07-09

    申请号:US12685495

    申请日:2010-01-11

    IPC分类号: G06K9/00

    CPC分类号: G06K9/48

    摘要: In an embodiment, a grammar-based, cueing method of object recognition is disclosed. The method may include or comprise accessing cells that define a portion of a three-dimensional (3-D) scene, assigning occupation parameters to the cells to define a plurality of occupied cells and at least one vacant cell, and assigning localization parameters to the occupied cells based on the occupation parameters of their respective neighboring cells. The method may further include or comprise characterizing a plurality of the occupied cells as geometric cues based on their respective occupation and localization parameters, and identifying a target geometric shape associated with the geometric cues.

    摘要翻译: 在一个实施例中,公开了一种基于语法的提示对象识别方法。 该方法可以包括或包括访问定义三维(3-D)场景的一部分的小区,向小区分配占用参数以定义多个被占用的小区和至少一个空闲小区,以及将定位参数分配给 基于其各自相邻小区的占用参数占用的小区。 该方法还可以包括或包括基于它们各自的占用和定位参数将多个占用的小区表征为几何提示,以及识别与几何提示相关联的目标几何形状。