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
技術領域
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

In certain embodiments, the number of threads operating in parallel may be determined based on the computing device, such as any of the computing devices of FIGS. 1 and 2, that implements Distification. For example, a computing device with 4 CPU cores may run 4 threads at once. However, a more powerful computer, with 8 CPU cores, may run 10 threads at once.

The Distify method may also be implemented across several computing devices or systems (each having their own unique number of CPU cores) at once in a networked environment, for example, across any one or more of the computing devices shown in FIG. 2. In such an embodiment, the networked computers can be configured to Distify images or frames in a shared configuration, where certain computers can be allocated different workloads or threading tasks depending, for example, on the processing power of the individual computers. For example, a network of 10 computers may be used where the 3D data is allocated across the network, where 4 computers each having 4 CPU cores each run 4 Distification threads, and where the remaining 6 computers each having 8 CPU cores and each run 10 Distification threads, for a total of 84 total Distification threads allocated across the shared network running at the same time.

3D Image Distification and Prediction Models

Distify can be performed, for example, as a preprocessing technique for a variety of applications, including, for example, for generating output feature vectors used to train 3D predictive models or used as input into such predictive models to make predictions with respect to 3D imagery. In various embodiments described herein, the a 3D prediction model may be used to determine a risk factor associated with user activity or behavior.

權利要求

1
微信群二維碼
意見反饋