白丝美女被狂躁免费视频网站,500av导航大全精品,yw.193.cnc爆乳尤物未满,97se亚洲综合色区,аⅴ天堂中文在线网官网

Systems and methods for 3D image distification

專利號
US11176414B1
公開日期
2021-11-16
申請人
STATE FARM MUTUAL AUTOMOBILE INSURANCE COMPANY(US IL Bloomington)
發(fā)明人
Elizabeth Flowers; Puneit Dua; Eric Balota; Shanna L. Phillips
IPC分類
G06K9/62; G06K9/42; G06K9/00
技術(shù)領(lǐng)域
3d,2d,image,images,or,computing,matrix,in,2d3d,model
地域: IL IL Bloomington

摘要

Systems and methods are described for Distification of 3D imagery. A computing device may obtain a three dimensional (3D) image that includes rules defining a 3D point cloud used to generate a two dimensional (2D) image matrix. The 2D image matrix may include 2D matrix point(s) mapped to the 3D image, where each 2D matrix point can be associated with a horizontal coordinate and a vertical coordinate. The computing device can generate an output feature vector that includes, for at least one of the 2D matrix points, the horizontal coordinate and the vertical coordinate of the 2D matrix point, and a depth coordinate of a 3D point in the 3D point cloud of the 3D image. The 3D point can have a nearest horizontal and vertical coordinate pair that corresponds to the horizontal and vertical coordinates of the at least one 2D matrix point.

說明書

Each of the 3D points have a horizontal coordinate (e.g., x-value), vertical coordinate (e.g., y-value) and depth coordinate (e.g., z-value) defined by the point cloud 406 of the 3D image 404. Plane 408 indicates depth coordinates (z-values) defined in the original point cloud 406 of the 3D image, for example, depth coordinates Z1 (450), Z2 (452), and Ze (454), where Ze defines the “end” Z coordinate of the depth axis in the 3D point cloud.

In some embodiments, the 3D image 404 could include rules that define the 3D point cloud 406. For example, in some embodiments, the rules can require the 3D points to be defined in a certain ordering, sequence or format, such as with the ordering, sequencing, and formatting required by a 3D file format, e.g., the PLY or PCD file formats.

The 3D points (e.g., points 460, 462, and 464) in 3D point cloud 406 can each have a corresponding 2D coordinate pair (i.e., a horizontal and vertical coordinate pair) with respect to a 2D-axis of 3D image 404. As described above, there may be a direct mapping of the points of the 3D image 404 with respect to the 2D matrix points of the 2D image matrix 402. In other aspects, there may be no direct mapping of the points of the 3D image 404 with respect to the 2D matrix points of the 2D image matrix 402, such that a 3D point in the point cloud 406 resides within a rectangular 3D space defined by four 2D matrix points (not shown) of the 2D image matrix 402. For example, 3D point 464 resides within a 3D space defined by four 2D matrix points, for example, 2D matrix points (X17, Y3), (X18, Y3), (X17, Y4) and (X18, Y4) of the 2D image matrix 402, and has a depth coordinate (e.g., z-value) of Z4.

權(quán)利要求

1
微信群二維碼
意見反饋